# kilocode - Doramagic AI Context Pack

> Positioning: a pre-install experience and judgment asset. It helps the host AI get off to a good start, but it does not mean the project has already been installed, run, or validated.

## Sufficiency Principle

- **Sufficiency over compression**: The AI Context Pack should be sufficient for the host AI to understand the project's value, capability boundaries, entrypoints, risks, and evidence sources before starting work; it may be layered, but it does not aim for the shortest possible summary.
- **Compression policy**: Compress only noise and duplication, never context that affects judgment or the quality of the work.

## How the Host AI Should Use This

You are reading the AI Context Pack that Doramagic compiled for kilocode. Treat it as pre-work context: help the user understand who it fits, what it can do, how to start, what must be verified after install, and where the risks are. Do not claim that you have already installed, run, or executed the target project.

## Claim Consumption Rules

- **Fact source**: Repo Evidence + Claim/Evidence Graph; the Human Wiki only supplies salience, terminology, and narrative structure.
- **Minimum status for a fact**: `supported`
- `supported`: May be used as a project fact, but the answer must cite the claim_id and evidence path.
- `weak`: Usable only as a low-confidence lead; the user must be asked to keep verifying.
- `inferred`: Usable only for risk notes or open questions; must not be packaged as a project fact.
- `unverified`: Must not be used as fact; state clearly that evidence is insufficient.
- `contradicted`: Must show the conflicting sources and must not force a single version on the user's behalf.

## Who It Fits Best

- **Developers already using host AIs such as Claude/Codex/Cursor/Gemini**: The README or plugin config mentions multiple host AIs. Evidence: `README.md` Claim: `clm_0003` supported 0.86
- **Users who want to bring professional workflows into a host AI**: The repo contains Skill documents. Evidence: `.kilo/skills/gh-issues/SKILL.md`, `.kilo/skills/kilocode-merge-minimizer/SKILL.md`, `.kilo/skills/release-jetbrains/SKILL.md`, `.kilocode/skills/vscode-visual-regression/SKILL.md` et al. Claim: `clm_0004` supported 0.86

## What It Can Do

- **AI Skill / Agent Instruction Asset Library** (Previewable before install): The project contains Skill or Agent instruction files that a host AI can read, useful for bringing professional workflows into hosts like Claude, Codex, or Cursor. Evidence: `.kilo/skills/gh-issues/SKILL.md`, `.kilo/skills/kilocode-merge-minimizer/SKILL.md`, `.kilo/skills/release-jetbrains/SKILL.md`, `.kilocode/skills/vscode-visual-regression/SKILL.md` et al. Claim: `clm_0001` supported 0.86
- **Command-Line Startup or Install Flow** (Verify after install): The project documentation contains runnable commands; real use requires running them in a local or host environment. Evidence: `README.md`, `packages/kilo-docs/pages/gateway/quickstart.md`, `packages/kilo-jetbrains/README.md`, `packages/opencode/README.md` Claim: `clm_0002` supported 0.86

## How to Start

- `npm install -g @kilocode/cli` Evidence: `README.md` Claim: `clm_0005` supported 0.86
- `curl -fsSL https://kilo.ai/cli/install | bash` Evidence: `README.md` Claim: `clm_0006` supported 0.86
- `pnpm add -g @kilocode/cli` Evidence: `README.md` Claim: `clm_0007` supported 0.86
- `curl -s "https://get.sdkman.io" | bash` Evidence: `packages/kilo-jetbrains/README.md` Claim: `clm_0008` supported 0.86
- `npx --package @kilocode/cli kilo` Evidence: `packages/opencode/README.md` Claim: `clm_0009` supported 0.86
- `npm install ai @ai-sdk/openai dotenv` Evidence: `packages/kilo-docs/pages/gateway/quickstart.md` Claim: `clm_0010` unverified 0.25
- `curl -X POST "https://api.kilo.ai/api/gateway/chat/completions" \` Evidence: `packages/kilo-docs/pages/gateway/quickstart.md` Claim: `clm_0011` unverified 0.25

## Continue-or-Stop Decision Card

- **Current recommendation**: Needs admin / security approval
- **Why**: Continuing may involve secrets, accounts, external services, or sensitive context; get admin or security approval first.

### 30-Second Read

- **What to do now**: Needs admin / security approval
- **Minimum safe next step**: Run Prompt Preview first; if credentials or an enterprise environment are involved, get approval before trialing
- **Do not trust yet**: Tool permission boundaries cannot be trusted before install.
- **Continuing will touch**: Command execution, Host AI configuration, Local environment or project files

### What You Can Trust Now

- **Target-audience signal: Developers already using host AIs such as Claude/Codex/Cursor/Gemini** (supported): Backed by a supported claim or project evidence, but that still is not the same as real install results. Evidence: `README.md` Claim: `clm_0003` supported 0.86
- **Target-audience signal: Users who want to bring professional workflows into a host AI** (supported): Backed by a supported claim or project evidence, but that still is not the same as real install results. Evidence: `.kilo/skills/gh-issues/SKILL.md`, `.kilo/skills/kilocode-merge-minimizer/SKILL.md`, `.kilo/skills/release-jetbrains/SKILL.md`, `.kilocode/skills/vscode-visual-regression/SKILL.md` et al. Claim: `clm_0004` supported 0.86
- **Capability exists: AI Skill / Agent Instruction Asset Library** (supported): You can trust that the project contains signals of this capability; whether it fits your specific task still needs trial or after-install verification. Evidence: `.kilo/skills/gh-issues/SKILL.md`, `.kilo/skills/kilocode-merge-minimizer/SKILL.md`, `.kilo/skills/release-jetbrains/SKILL.md`, `.kilocode/skills/vscode-visual-regression/SKILL.md` et al. Claim: `clm_0001` supported 0.86
- **Capability exists: Command-Line Startup or Install Flow** (supported): You can trust that the project contains signals of this capability; whether it fits your specific task still needs trial or after-install verification. Evidence: `README.md`, `packages/kilo-docs/pages/gateway/quickstart.md`, `packages/kilo-jetbrains/README.md`, `packages/opencode/README.md` Claim: `clm_0002` supported 0.86
- **There are Quick Start / install-command signals** (supported): You can trust that the docs mention a startup or install entrypoint; do not run it directly in your primary environment because of that. Evidence: `README.md` Claim: `clm_0005` supported 0.86

### What You Cannot Trust Yet

- **Tool permission boundaries cannot be trusted before install.** (unverified): MCP/tool projects usually touch files, the network, the browser, or external APIs, so permissions and logs must be checked for real.
- **Real output quality cannot be trusted before install.** (unverified): Prompt Preview can only show how it guides you; it cannot prove result quality in the real project.
- **Host AI version compatibility cannot be trusted before install.** (unverified): Host loading rules and version differences across Claude, Cursor, Codex, Gemini, and others must be verified in a real environment.
- **That it will not pollute your existing host AI's behavior cannot be trusted directly.** (inferred): Skill, plugin, and AGENTS/CLAUDE/GEMINI instructions may change the host AI's default behavior. Evidence: `.kilo/skills/gh-issues/SKILL.md`, `.kilo/skills/kilocode-merge-minimizer/SKILL.md`, `.kilo/skills/release-jetbrains/SKILL.md`, `.kilocode/skills/vscode-visual-regression/SKILL.md` et al.
- **Safe rollback cannot be assumed by default.** (unverified): Unless the project clearly provides uninstall and recovery instructions, verify in an isolated environment first.
- **After a real install, is it compatible with the user's current host AI version?** (unverified): Compatibility can only be verified in the actual host environment.
- **Does the project's output quality meet the user's specific task?** (unverified): The pre-install preview can only show flow and boundaries; it cannot replace real evaluation.
- **Do the install commands require network access, permissions, or global writes?** (unverified): This affects install risk in both enterprise and personal environments. Evidence: `README.md`

### What Continuing Will Touch

- **Command execution**: Package managers, network downloads, the local plugin directory, project config, or the user's home directory. Why: Running the very first command can already change your environment; decide whether it is worth running first. Evidence: `README.md`, `packages/kilo-docs/pages/gateway/quickstart.md`, `packages/kilo-jetbrains/README.md`, `packages/opencode/README.md`
- **Host AI configuration**: The plugin, Skill, or rule-loading config of hosts like Claude/Codex/Cursor/Gemini/OpenCode. Why: Host configuration changes how the AI works afterward and may conflict with the user's existing rules. Evidence: `.kilo/skills/gh-issues/SKILL.md`, `.kilo/skills/kilocode-merge-minimizer/SKILL.md`, `.kilo/skills/release-jetbrains/SKILL.md`, `.kilocode/skills/vscode-visual-regression/SKILL.md` et al.
- **Local environment or project files**: Install results, plugin caches, project config, or local dependency directories. Why: The write scope and rollback path cannot be proven before install and need isolated verification. Evidence: `README.md`, `packages/kilo-docs/pages/gateway/quickstart.md`, `packages/kilo-jetbrains/README.md`, `packages/opencode/README.md`
- **Environment variables / API keys**: Project entry docs explicitly showing API key, token, secret, or account credential configuration. Why: If a real install needs credentials, use test credentials first and go through a permission/compliance review. Evidence: `packages/kilo-docs/pages/ai-providers/cloudflare.md`, `packages/llm/README.md`
- **Host AI context**: The AI Context Pack, Prompt Preview, Skill routing, risk rules, and project facts. Why: Importing context affects the host AI's later judgment, so avoid packaging unverified items as facts.

### Minimum Safe Next Steps

- **Run Prompt Preview first**: Use a pre-install interactive trial to judge whether the way of working fits; it needs no authorization or environment change. (applies when: Applies to any project, especially when output quality is unknown.)
- **Trial-install only in an isolated directory or a test account**: Avoid letting install commands pollute your primary host AI, real projects, or home directory. (applies when: When there are signals of command execution, plugin config, or local writes.)
- **Back up your host AI configuration first**: Skill, plugin, and rule files may change the default behavior of Claude/Cursor/Codex. (applies when: When there is a plugin manifest, a Skill, or a host rule entrypoint.)
- **Do not use real production credentials**: Once an environment variable / API key enters the host or toolchain, it can create account and compliance risk. (applies when: When environment signals like API, TOKEN, KEY, or SECRET appear.)
- **After install, verify just one minimal task**: Verify loading, compatibility, output quality, and rollback first, then decide whether to use it deeply. (applies when: When moving from a trial into a real workflow.)

### Exit Plan

- **Preserve the pre-install state**: Record the original host config and project state so you can later judge whether it is recoverable.
- **Be ready to remove the host plugin / Skill / rule entrypoint**: If behavior is off after the trial install, you can restore the host AI to its pre-trial state.
- **Record the install commands and written paths**: Without clear uninstall instructions, you at least need to know which directories or configs to clean up manually.
- **Be ready to revoke test API keys or tokens**: If test credentials leak or are misused, you can cut losses quickly.
- **If there is no rollback path, do not enter your primary environment**: No rollback is a blocker before continuing; do not proceed on trust or luck.

## What Can Only Be Previewed

- Explain who the project fits and what it can do
- Demonstrate a typical conversation flow based on project docs
- Help the user decide whether it is worth installing or researching further

## What Must Be Verified After Install

- Actually installing the Skill, plugin, or CLI
- Running scripts, modifying local files, or accessing external services
- Verifying real output quality, performance, and compatibility

## Boundary & Risk Decision Card

- **Mistaking the pre-install preview for a real run**: The user may overestimate how much configuration, permission, and compatibility verification the project has already done. Mitigation: Clearly separate prompt_preview_can_do from runtime_required. Claim: `clm_0012` inferred 0.45
- **Command execution will modify the local environment**: Install commands may write to the user's home directory, the host plugin directory, or project configuration. Mitigation: Run in an isolated environment or a test account first. Evidence: `README.md`, `packages/kilo-docs/pages/gateway/quickstart.md`, `packages/kilo-jetbrains/README.md`, `packages/opencode/README.md` Claim: `clm_0013` supported 0.86
- **To confirm**: After a real install, is it compatible with the user's current host AI version?. Why: Compatibility can only be verified in the actual host environment.
- **To confirm**: Does the project's output quality meet the user's specific task?. Why: The pre-install preview can only show flow and boundaries; it cannot replace real evaluation.
- **To confirm**: Do the install commands require network access, permissions, or global writes?. Why: This affects install risk in both enterprise and personal environments.

## Pre-Work Working Context

### Loading Order

- First read how_to_use.host_ai_instruction to establish the boundaries of this pre-install judgment asset.
- Read claim_graph_summary to confirm facts come from the Claim/Evidence Graph, not the Human Wiki narrative.
- Then read intended_users, capabilities, and quick_start_candidates to judge whether the user is a match.
- When you need to carry out a concrete task, check role_skill_index first, then evidence_index.
- For real install, file modification, network access, performance, or compatibility questions, turn to risk_card and boundaries.runtime_required.

### Task Routes

- **AI Skill / Agent Instruction Asset Library**: Use role_skill_index / evidence_index to help the user pick a usable role, Skill, or workflow first. Boundary: Can be experienced via a pre-install Prompt. Evidence: `.kilo/skills/gh-issues/SKILL.md`, `.kilo/skills/kilocode-merge-minimizer/SKILL.md`, `.kilo/skills/release-jetbrains/SKILL.md`, `.kilocode/skills/vscode-visual-regression/SKILL.md` et al. Claim: `clm_0001` supported 0.86
- **Command-Line Startup or Install Flow**: State that this is an after-install capability first, then give a pre-install checklist. Boundary: Must be verified after a real install or run. Evidence: `README.md`, `packages/kilo-docs/pages/gateway/quickstart.md`, `packages/kilo-jetbrains/README.md`, `packages/opencode/README.md` Claim: `clm_0002` supported 0.86

### Context Scale

- Total files: 7208
- Important-file coverage: 40/7208
- Evidence index entries: 80
- Role / Skill entries: 7

### Handling Insufficient Evidence

- **missing_evidence**: State that evidence is insufficient and ask the user for the target file, a README section, or after-install verification records; do not fill in facts.
- **out_of_scope_request**: State that the task is beyond the current AI Context Pack's evidence scope and suggest the user check the Human Manual or verify after a real install.
- **runtime_request**: Provide a pre-install checklist and command sources, but do not run commands for the user or claim they have been run.
- **source_conflict**: Show the conflicting sources side by side, mark them as unverified, and do not force a single version.

## Prompt Recipes

### Fit assessment

- Goal: Judge whether this project fits the user's current task.
- Expected output: A fit conclusion, key reasons, evidence citations, what can be previewed before install, what must be verified after install, and a next-step recommendation.

```text
Based on the AI Context Pack for kilocode, ask me 3 necessary questions first, then judge whether it fits my task. The answer must cover: who it fits, what it can do, what it cannot do, whether it is worth installing, and where the evidence comes from. Every project fact must cite evidence_refs, source_paths, or a claim_id.
```

### Pre-install experience

- Goal: Let the user feel the core workflow before installing, while avoiding packaging the preview as real capability or a marketing promise.
- Expected output: An experience script with boundary labels, an after-install verification checklist, and a cautious recommendation; with no real-run promises or strong marketing language.

```text
Treat kilocode as a pre-install experience asset, not an already-installed tool or a real runtime environment.

Output exactly four parts:
1. Ask me 3 necessary questions first.
2. Give an "experience script": use the three labels [Previewable before install], [Must verify after install], and [Insufficient evidence] to show how it might guide the workflow.
3. Give an after-install verification checklist: list which capabilities can only be confirmed after a real install, real host loading, and a real project run.
4. Give a cautious recommendation: only "worth researching/trialing further", "add information before deciding", or "not recommended to continue"; do not endorse the project.

Hard boundaries:
- Do not claim you have installed, run, executed tests, modified files, or produced real results.
- Do not write promise-like phrasing such as "auto-adapts", "guarantees passing", "perfect fit", or "strongly recommend installing".
- If you describe how it works after install, you must use a conditional such as "if installed successfully and the host loads the Skill correctly, it might...".
- The experience script may only be written as "example lines / hypothetical flow": use "might ask / might suggest / might show", not "has written, has generated, has passed, is running, is generating".
- Prompt Preview does not hand out install commands; if the user is ready to trial, only prompt them to read Quick Start and the Risk Card first and to verify in an isolated environment.
- Every project fact must come from a supported claim, evidence_refs, or source_paths; inferred/unverified items can only be risks or open questions.

```

### Role / Skill selection

- Goal: Pick the best-matching asset from the project's roles or Skills.
- Expected output: A list of candidate roles or Skills, each with an applicable scenario, evidence paths, risk boundary, and whether after-install verification is needed.

```text
Read role_skill_index and recommend 3-5 of the most relevant roles or Skills for my target task. For each recommendation, state the applicable scenario, likely output, risk boundary, and evidence_refs.
```

### Risk pre-check

- Goal: Identify environment, permission, rule-conflict, and quality risks before installing or adopting.
- Expected output: A checklist of environment, permission, dependency, license, host-conflict, quality risk, and unknown items.

```text
Based on risk_card, boundaries, and quick_start_candidates, give me a pre-install risk pre-check list. Do not run commands for me; only explain what I should check, why, and what impact a failure would have.
```

### Host AI kickoff instruction

- Goal: Turn the project context into a host AI instruction for the start of a conversation.
- Expected output: A pre-work instruction with clear boundaries and clear evidence citations, suitable to copy to a host AI.

```text
Based on the AI Context Pack for kilocode, generate a pre-work instruction I can paste to my host AI. This instruction must obey not_runtime=true and must not claim the project has been installed, run, or produced real results.
```

## Role / Skill Index

- Indexed 7 role / Skill / project-doc entries.

- **gh-issues** (skill): Use when creating, triaging, or commenting on GitHub issues for the Kilo VS Code extension or JetBrains plugin via gh . Covers issue templates, project board assignment, title conventions, and required gh scopes. Activation hint: When the user's task is highly relevant to the workflow described by “gh-issues”, use it for a pre-install experience first, then decide whether to install. Evidence: `.kilo/skills/gh-issues/SKILL.md`
- **kilocode-merge-minimizer** (skill): Use when changing shared upstream-owned files to add Kilo-specific behavior, editing kilocode change markers in shared code, or moving additive behavior out of shared code to reduce upstream merge conflicts. Do not use for changes confined to Kilo-owned paths such as packages/kilo-vscode/ or packages/kilo-ui/ . Activation hint: When the user's task is highly relevant to the workflow described by “kilocode-merge-minimizer”, use it for a pre-install experience first, then decide whether to install. Evidence: `.kilo/skills/kilocode-merge-minimizer/SKILL.md`
- **release-jetbrains** (skill): Use when releasing the Kilo JetBrains plugin -- resolve a version "next rc" or explicit , run the prepare workflow, edit and commit a filtered human-readable changelog on the release PR, then watch publish to completion. Activation hint: When the user's task is highly relevant to the workflow described by “release-jetbrains”, use it for a pre-install experience first, then decide whether to install. Evidence: `.kilo/skills/release-jetbrains/SKILL.md`
- **vscode-visual-regression** (skill): Write Storybook stories and visual regression tests for the Kilo VS Code extension webview UI Activation hint: When the user's task is highly relevant to the workflow described by “vscode-visual-regression”, use it for a pre-install experience first, then decide whether to install. Evidence: `.kilocode/skills/vscode-visual-regression/SKILL.md`
- **effect** (skill): Work with Effect v4 / effect-smol TypeScript code in this repo Activation hint: When the user's task is highly relevant to the workflow described by “effect”, use it for a pre-install experience first, then decide whether to install. Evidence: `.opencode/skills/effect/SKILL.md`
- **agents-sdk** (skill): Build AI agents on Cloudflare Workers using the Agents SDK. Load when creating stateful agents, durable workflows, real-time WebSocket apps, scheduled tasks, MCP servers, or chat applications. Covers Agent class, state management, callable RPC, Workflows integration, and React hooks. Activation hint: When the user's task is highly relevant to the workflow described by “agents-sdk”, use it for a pre-install experience first, then decide whether to install. Evidence: `packages/opencode/test/fixture/skills/agents-sdk/SKILL.md`
- **cloudflare** (skill): Comprehensive Cloudflare platform skill covering Workers, Pages, storage KV, D1, R2 , AI Workers AI, Vectorize, Agents SDK , networking Tunnel, Spectrum , security WAF, DDoS , and infrastructure-as-code Terraform, Pulumi . Use for any Cloudflare development task. Activation hint: When the user's task is highly relevant to the workflow described by “cloudflare”, use it for a pre-install experience first, then decide whether to install. Evidence: `packages/opencode/test/fixture/skills/cloudflare/SKILL.md`

## Evidence Index

- Indexed 80 evidence entries.

- **Changesets** (documentation): This directory contains changeset files used to track changes for the next release. Evidence: `.changeset/README.md`
- **AGENTS.md** (documentation): Kilo CLI is an open source AI coding agent that generates code from natural language, automates tasks, and supports 500+ AI models. Evidence: `AGENTS.md`
- **Installation** (documentation): English 简体中文 繁體中文 한국어 Deutsch Español Français Italiano Dansk 日本語 Polski Русский Bosanski العربية Norsk Português Brasil ไทย Türkçe Українська বাংলা Ελληνικά Tiếng Việt Evidence: `README.md`
- **Kilo GitHub Action** (documentation): A GitHub Action that integrates Kilo AI https://kilo.ai directly into your GitHub workflow. Evidence: `github/README.md`
- **Locale Glossaries** (documentation): Use this folder for locale-specific translation guidance that supplements .opencode/agent/translator.md . Evidence: `.opencode/glossary/README.md`
- **CI containers** (documentation): Prebuilt images intended to speed up GitHub Actions jobs by baking in large, slow-to-install dependencies. These are designed for Linux jobs that can use job.container in workflows. Evidence: `packages/containers/README.md`
- **Readme** (documentation): This is a temporary package used primarily for GitHub Copilot compatibility. Evidence: `packages/core/src/github-copilot/README.md`
- **Core Tool Architecture** (documentation): This folder owns Core's one local tool representation, process and Location registration, effective lookup, and settlement. Evidence: `packages/core/src/tool/AGENTS.md`
- **Effect Drizzle SQLite** (documentation): This package vendors a Drizzle Effect SQLite adapter for this repo. Evidence: `packages/effect-drizzle-sqlite/AGENTS.md`
- **@opencode-ai/http-recorder** (documentation): Record real Effect HTTP and WebSocket traffic once, then replay it from deterministic JSON cassettes. Evidence: `packages/http-recorder/README.md`
- **Project Overview** (documentation): This is the Kilo Code documentation site. Kilo Code is the leading open source agentic engineering platform. Evidence: `packages/kilo-docs/AGENTS.md`
- **@kilocode/kilo-gateway** (documentation): Unified Kilo Gateway package for OpenCode providing authentication, AI provider integration, and API access. Evidence: `packages/kilo-gateway/README.md`
- **AGENTS.md — Kilo JetBrains Plugin** (documentation): - Split-mode plugin with three Gradle modules: shared/ , frontend/ , backend/ . The module descriptors are kilo.jetbrains.shared.xml , kilo.jetbrains.frontend.xml , kilo.jetbrains.backend.xml — these must stay in sync with plugin.xml 's block. - Reference template for the split-mode structure: https://github.com/JetBrains/intellij-platform-modular-plugin-template - Official docs: https://plugins.jetbrains.com/docs/intellij/split-mode-for-remote-development.html - Kotlin source goes under {module}/src/main/kotlin/ai/kilocode/jetbrains/ . Package name is ai.kilocode.jetbrains matches group in root build.gradle.kts . - The root plugin.xml is wiring only: keep plugin metadata and the block ther… Evidence: `packages/kilo-jetbrains/AGENTS.md`
- **Kilo JetBrains** (documentation): AI coding agent plugin for JetBrains IDEs. Evidence: `packages/kilo-jetbrains/README.md`
- **AGENTS.md** (documentation): This file provides guidance to agents when working with code in this repository. Evidence: `packages/kilo-vscode/AGENTS.md`
- **Key Features** (documentation): Kilo is the all-in-one agentic engineering platform. Build, ship, and iterate faster with the most popular open source coding agent. Evidence: `packages/kilo-vscode/README.md`
- **LLM Package Guide** (documentation): - Prefer HttpClient.HttpClient / HttpClientResponse.HttpClientResponse over web fetch / Response at package boundaries. - Use Stream.Stream for streaming data flow. Avoid ad hoc async generators or manual web reader loops unless an Effect Stream API cannot model the behavior. - Use Effect Schema codecs for JSON encode/decode Schema.fromJsonString ... instead of direct JSON.parse / JSON.stringify in implementation code. - In Effect.gen , yield yieldable errors directly return yield new MyError ... instead of Effect.fail new MyError ... . - Use Effect.void instead of Effect.succeed undefined when the successful value is intentionally void. Evidence: `packages/llm/AGENTS.md`
- **@opencode-ai/llm** (documentation): Schema-first LLM core for opencode. One typed request, response, event, and tool language; provider quirks live in adapters, not in calling code. Evidence: `packages/llm/README.md`
- **Kilo CLI package guidelines** (documentation): - Run : bun run --conditions=browser ./src/index.ts - Test : bun test all tests or bun test test/tool/tool.test.ts single test - Typecheck : bun run typecheck runs tsgo --noEmit Evidence: `packages/opencode/AGENTS.md`
- **Kilo Code CLI** (documentation): The AI coding agent built for the terminal. Generate code from natural language, automate tasks, and run terminal commands -- powered by 500+ AI models. Evidence: `packages/opencode/README.md`
- **Readme** (documentation): This is a plugin to simulate a remote environment locally. Add this to .kilo/kilo.jsonc : Evidence: `packages/opencode/src/control-plane/dev/README.md`
- **OpenAI Responses WebSocket** (documentation): Enabled by default on local , dev , and beta . On latest and prod , set KILO EXPERIMENTAL WEBSOCKETS=true . Evidence: `packages/opencode/src/plugin/openai/README.md`
- **HttpApi Route Patterns** (documentation): Use HttpApiBuilder.group ... for normal HTTP endpoints, including streaming HTTP responses such as server-sent events. Handlers should yield stable services once while building the handler layer, then close over those services in endpoint implementations. Evidence: `packages/opencode/src/server/routes/instance/httpapi/AGENTS.md`
- **Session LLM Runtime Boundaries** (documentation): ../llm.ts is the opencode session LLM service. It owns opencode concerns: auth, config, model/provider resolution, plugins, permissions, telemetry headers, and runtime selection. It is the only file in this area that should know about the full session request shape. Evidence: `packages/opencode/src/session/llm/AGENTS.md`
- **Goal** (documentation): tl;dr All of these APIs work, are properly type-checked, and are sync events are backwards compatible with Bus : Evidence: `packages/opencode/src/sync/README.md`
- **Upstream Merge Automation** (documentation): Scripts for automating the merge of upstream opencode changes into Kilo. Evidence: `script/upstream/README.md`
- **Package** (package_manifest): { "$schema": "https://json.schemastore.org/package.json", "name": "@kilocode/kilo", "description": "AI-powered development tool", "private": true, "type": "module", "packageManager": "bun@1.3.14", "scripts": { "dev": "bun run --cwd packages/opencode --conditions=browser src/index.ts", "dev:stats": "bun sst shell --stage=production -- bun run --cwd packages/stats/app dev", "dev:local": "bun run packages/opencode/script/dev-local.ts", "dev:storybook": "bun --cwd packages/storybook storybook", "lint": "oxlint", "typecheck": "bun turbo typecheck", "upgrade-opentui": "bun run script/upgrade-opentui.ts", "postinstall": "bun run --cwd packages/core fix-node-pty && bun run script/setup-git.ts", "pr… Evidence: `package.json`
- **Contributing to Kilo CLI** (documentation): See the Documentation for details on contributing https://kilo.ai/docs/contributing . Evidence: `CONTRIBUTING.md`
- **Package** (package_manifest): { "$schema": "https://json.schemastore.org/package.json", "version": "7.4.13", "name": "@opencode-ai/core", "type": "module", "license": "MIT", "private": true, "scripts": { "db": "bun drizzle-kit", "migration": "bun run script/migration.ts", "fix-node-pty": "bun run script/fix-node-pty.ts", "test": "bun test --only-failures", "test:ci": "mkdir -p .artifacts/unit && bun test --timeout 30000 --reporter=junit --reporter-outfile=.artifacts/unit/junit.xml", "typecheck": "tsgo --noEmit" }, "bin": { "opencode": "./bin/opencode" }, "exports": { "./public": "./src/public/index.ts", "./session/runner": "./src/session/runner/index.ts", "./system-context": "./src/system-context/index.ts", "./ ": "./sr… Evidence: `packages/core/package.json`
- **Package** (package_manifest): { "$schema": "https://json.schemastore.org/package.json", "version": "7.4.13", "name": "@opencode-ai/effect-drizzle-sqlite", "type": "module", "license": "MIT", "private": true, "scripts": { "test": "bun test --timeout 30000 --only-failures", "test:ci": "mkdir -p .artifacts/unit && bun test --timeout 30000 --reporter=junit --reporter-outfile=.artifacts/unit/junit.xml", "typecheck": "tsgo --noEmit" }, "exports": { ".": "./src/index.ts", "./effect-sqlite": "./src/effect-sqlite/index.ts", "./effect-sqlite/migrator": "./src/effect-sqlite/migrator.ts", "./sqlite-core/effect": "./src/sqlite-core/effect/index.ts" }, "devDependencies": { "@effect/sql-sqlite-bun": "catalog:", "@tsconfig/bun": "catal… Evidence: `packages/effect-drizzle-sqlite/package.json`
- **Package** (package_manifest): { "$schema": "https://json.schemastore.org/package.json", "version": "7.4.13", "name": "@opencode-ai/effect-sqlite-node", "type": "module", "license": "MIT", "private": true, "scripts": { "typecheck": "tsgo --noEmit" }, "exports": { ".": "./src/index.ts" }, "devDependencies": { "@tsconfig/bun": "catalog:", "@types/node": "catalog:", "@typescript/native-preview": "catalog:" }, "dependencies": { "effect": "catalog:" }, "peerDependencies": {} } Evidence: `packages/effect-sqlite-node/package.json`
- **Package** (package_manifest): { "$schema": "https://json.schemastore.org/package.json", "version": "7.4.13", "name": "@opencode-ai/http-recorder", "description": "Record and replay Effect HTTP client traffic with deterministic cassettes", "type": "module", "license": "MIT", "private": true, "repository": { "type": "git", "url": "git+https://github.com/Kilo-Org/kilocode.git", "directory": "packages/http-recorder" }, "homepage": "https://github.com/Kilo-Org/kilocode/tree/main/packages/http-recorder", "bugs": "https://github.com/Kilo-Org/kilocode/issues", "keywords": "effect", "http", "recording", "replay", "testing", "vcr" , "engines": { "node": " =22" }, "scripts": { "test": "bun test --timeout 30000 --only-failures", "t… Evidence: `packages/http-recorder/package.json`
- **Package** (package_manifest): { "name": "@kilocode/kilo-console", "version": "7.4.13", "private": true, "type": "module", "scripts": { "dev": "vite --host 127.0.0.1 --port 3017", "build": "vite build", "preview": "vite preview --host 127.0.0.1 --port 3018", "test": "bun test src", "test:ci": "mkdir -p .artifacts/unit && bun test src --reporter=junit --reporter-outfile=.artifacts/unit/junit.xml", "typecheck": "tsgo --noEmit" }, "dependencies": { "@kilocode/kilo-indexing": "workspace: ", "@kilocode/kilo-web-ui": "workspace: ", "@kilocode/sdk": "workspace: ", "@lottiefiles/dotlottie-web": "0.74.0", "@pierre/diffs": "catalog:", "@solidjs/router": "catalog:", "ghostty-web": "0.4.0", "solid-js": "catalog:", "yaml": "2.8.3" },… Evidence: `packages/kilo-console/package.json`
- **Package** (package_manifest): { "name": "@kilocode/kilo-docs", "version": "7.4.13", "private": true, "scripts": { "dev": "next dev --webpack --port 3002", "build": "next build --webpack", "lint": "bun run --cwd ../.. lint packages/kilo-docs", "start": "next start", "test": "vitest run", "test:ci": "mkdir -p .artifacts/unit && vitest run --reporter=junit --outputFile=.artifacts/unit/junit.xml", "typecheck": "tsc --noEmit" }, "dependencies": { "@docsearch/css": "^4", "@docsearch/js": "^4", "@markdoc/markdoc": "^0.5.4", "@markdoc/next.js": "^0.5.0", "@vscode/codicons": "^0.0.44", "@xyflow/react": "12.10.2", "js-yaml": "^4.1.0", "mermaid": "11.15.0", "next": "^16.1.5", "posthog-js": "^1.335.3", "prismjs": "^1.30.0", "react"… Evidence: `packages/kilo-docs/package.json`
- **Package** (package_manifest): { "$schema": "https://json.schemastore.org/package.json", "name": "@kilocode/kilo-gateway", "version": "7.4.13", "type": "module", "license": "MIT", "description": "Unified Kilo Gateway package for OpenCode - authentication, provider, and API integration", "keywords": "kilo", "kilocode", "opencode", "auth", "plugin", "provider", "ai", "llm" , "exports": { ".": "./src/index.ts", "./autocomplete": "./src/autocomplete.ts", "./fim": "./src/fim.ts", "./edit": "./src/edit.ts", "./edit-prompt": "./src/edit-prompt.ts", "./tui": "./src/tui.ts" }, "files": "dist" , "scripts": { "typecheck": "tsgo --noEmit", "build": "tsc", "test:ci": "mkdir -p .artifacts/unit && bun test test --dots --reporter=junit… Evidence: `packages/kilo-gateway/package.json`
- **Package** (package_manifest): { "$schema": "https://json.schemastore.org/package.json", "name": "@kilocode/kilo-i18n", "version": "7.4.13", "type": "module", "license": "MIT", "description": "Kilo-specific i18n translations and overrides", "exports": { "./ ": "./src/ .ts" }, "scripts": { "typecheck": "tsgo --noEmit" }, "devDependencies": { "@tsconfig/node22": "catalog:", "@types/bun": "catalog:", "typescript": "catalog:", "@typescript/native-preview": "catalog:" }, "dependencies": {}, "peerDependencies": {} } Evidence: `packages/kilo-i18n/package.json`
- **Package** (package_manifest): { "$schema": "https://json.schemastore.org/package.json", "name": "@kilocode/kilo-indexing", "version": "7.4.13", "type": "module", "license": "MIT", "description": "Standalone indexing engine and host helpers for Kilo Code", "keywords": "kilo", "kilocode", "indexing", "plugin", "search", "embeddings" , "exports": { ".": "./src/index.ts", "./config": "./src/config.ts", "./detect": "./src/detect.ts", "./embedding-models": "./src/kilo-embedding-models.ts", "./engine": "./src/indexing/index.ts", "./file-extensions": "./src/file-extensions.ts", "./server": "./src/server/routes.ts", "./status": "./src/status.ts" }, "files": "dist", "src" , "scripts": { "typecheck": "tsgo --noEmit", "build": "tsc… Evidence: `packages/kilo-indexing/package.json`
- **Package** (package_manifest): { "name": "@kilocode/kilo-jetbrains", "private": true, "scripts": { "build": "bun script/build.ts", "build:production": "bun script/build.ts --production", "typecheck": "./gradlew typecheck", "test": "./gradlew test", "test:ci": "bun script/test-ci.ts" }, "version": "7.4.11", "dependencies": {}, "devDependencies": {}, "peerDependencies": {} } Evidence: `packages/kilo-jetbrains/package.json`
- **Package** (package_manifest): { "$schema": "https://json.schemastore.org/package.json", "name": "@kilocode/kilo-memory", "version": "7.4.13", "type": "module", "license": "MIT", "description": "Project memory storage, indexing, recall, and command helpers for Kilo Code", "keywords": "kilo", "kilocode", "memory", "agent" , "exports": { ".": "./src/index.ts", "./autosave-status": "./src/autosave-status.ts", "./capture": "./src/capture/capture.ts", "./commands": "./src/commands.ts", "./decisions": "./src/decisions.ts", "./digest": "./src/capture/digest.ts", "./effect": "./src/effect/index.ts", "./effect/capture": "./src/effect/capture.ts", "./effect/config": "./src/effect/config.ts", "./effect/errors": "./src/effect/errors… Evidence: `packages/kilo-memory/package.json`
- **Package** (package_manifest): { "$schema": "https://json.schemastore.org/package.json", "name": "@kilocode/sandbox", "version": "7.4.13", "type": "module", "license": "MIT", "private": true, "description": "OS-neutral sandbox profiles and launch preparation for Kilo Code", "exports": { ".": "./src/index.ts" }, "files": "src" , "scripts": { "typecheck": "tsgo --noEmit", "test": "bun test --timeout 30000", "test:ci": "mkdir -p .artifacts/unit && bun test --timeout 30000 --dots --reporter=junit --reporter-outfile=.artifacts/unit/junit.xml" }, "dependencies": { "@anthropic-ai/sandbox-runtime": "catalog:", "effect": "catalog:", "ipaddr.js": "catalog:" }, "devDependencies": { "@effect/platform-node": "catalog:", "@tsconfig/bu… Evidence: `packages/kilo-sandbox/package.json`
- **Package** (package_manifest): { "$schema": "https://json.schemastore.org/package.json", "name": "@kilocode/kilo-telemetry", "version": "7.4.13", "type": "module", "license": "MIT", "description": "Telemetry for Kilo CLI - PostHog analytics integration", "exports": { ".": "./src/index.ts" }, "files": "dist" , "scripts": { "typecheck": "tsgo --noEmit", "build": "tsc", "test": "bun test", "test:ci": "mkdir -p .artifacts/unit && bun test --reporter=junit --reporter-outfile=.artifacts/unit/junit.xml" }, "dependencies": { "posthog-node": "4.4.0", "@kilocode/kilo-gateway": "workspace: " }, "devDependencies": { "@tsconfig/bun": "catalog:", "@types/bun": "catalog:", "typescript": "catalog:", "@typescript/native-preview": "catalo… Evidence: `packages/kilo-telemetry/package.json`
- **Package** (package_manifest): { "name": "@kilocode/kilo-ui", "version": "7.4.13", "type": "module", "license": "MIT", "exports": { "./font": "./src/components/font.tsx", "./button": "./src/components/button.tsx", "./code": "./src/components/code.tsx", "./diff": "./src/components/diff.tsx", "./diff-ssr": "./src/components/diff-ssr.tsx", "./dialog": "./src/components/dialog.tsx", "./icon": "./src/components/icon.tsx", "./icon-button": "./src/components/icon-button.tsx", "./list": "./src/components/list.tsx", "./provider-icon": "./src/components/provider-icon.tsx", "./spinner": "./src/components/spinner.tsx", "./text-field": "./src/components/text-field.tsx", "./toast": "./src/components/toast.tsx", "./tooltip": "./src/com… Evidence: `packages/kilo-ui/package.json`
- **Package** (package_manifest): { "name": "kilo-code", "displayName": "Kilo Code: AI Coding Agent, Copilot, and Autocomplete", "description": "Open Source AI coding agent that generates code from natural language, automates tasks, and runs terminal commands. Features inline autocomplete, browser automation, automated refactoring, and custom modes for planning, coding, and debugging. Supports 500+ AI models including Claude Anthropic , Gemini, Grok, GPT, Codex and GLM.", "version": "7.4.13", "icon": "assets/icons/logo-outline-black.png", "galleryBanner": { "color": " FFFFFF", "theme": "light" }, "publisher": "kilocode", "repository": { "type": "git", "url": "https://github.com/Kilo-Org/kilocode.git", "directory": "packages… Evidence: `packages/kilo-vscode/package.json`
- **Package** (package_manifest): { "name": "@kilocode/kilo-web-ui", "version": "7.4.13", "type": "module", "license": "MIT", "exports": { ".": "./src/index.ts", "./package.json": "./package.json", "./accordion": "./src/components/accordion.tsx", "./alert": "./src/components/alert.tsx", "./alert-dialog": "./src/components/alert-dialog.tsx", "./animated-number": "./src/components/animated-number.tsx", "./app-icon": "./src/components/app-icon.tsx", "./avatar": "./src/components/avatar.tsx", "./badge": "./src/components/badge.tsx", "./basic-tool": "./src/components/basic-tool.tsx", "./button": "./src/components/button.tsx", "./button-group": "./src/components/button-group.tsx", "./card": "./src/components/card.tsx", "./chart":… Evidence: `packages/kilo-web-ui/package.json`
- **Package** (package_manifest): { "$schema": "https://json.schemastore.org/package.json", "version": "7.4.13", "name": "@opencode-ai/llm", "type": "module", "license": "MIT", "private": true, "scripts": { "setup:recording-env": "bun run script/setup-recording-env.ts", "test": "bun test --timeout 30000 --only-failures", "test:ci": "mkdir -p .artifacts/unit && bun test --timeout 30000 --reporter=junit --reporter-outfile=.artifacts/unit/junit.xml", "typecheck": "tsgo --noEmit" }, "exports": { ".": "./src/index.ts", "./route": "./src/route/index.ts", "./provider": "./src/provider.ts", "./providers": "./src/providers/index.ts", "./providers/amazon-bedrock": "./src/providers/amazon-bedrock.ts", "./providers/anthropic": "./src/p… Evidence: `packages/llm/package.json`
- **Package** (package_manifest): { "$schema": "https://json.schemastore.org/package.json", "version": "7.4.13", "name": "@kilocode/cli", "type": "module", "license": "MIT", "private": false, "scripts": { "typecheck": "tsgo --noEmit", "test": "bun run script/test-runner.ts", "test:httpapi": "bun run script/httpapi-exercise.ts --mode coverage --fail-on-missing --fail-on-skip && bun run script/httpapi-exercise.ts --mode auth --fail-on-missing --fail-on-skip && bun run script/httpapi-exercise.ts --mode effect --fail-on-missing --fail-on-skip", "bench:test": "bun run script/bench-test-suite.ts", "profile:test": "bun run script/profile-test-files.ts", "build": "bun run script/build.ts", "dev": "bun run --conditions=browser ./src… Evidence: `packages/opencode/package.json`
- **Package** (package_manifest): { "$schema": "https://json.schemastore.org/package.json", "name": "@kilocode/plugin-atomic-chat", "version": "7.4.13", "description": "Kilo Code plugin for Atomic Chat: auto-detection and dynamic model discovery OpenAI-compatible local API ", "type": "module", "license": "MIT", "exports": { ".": "./src/index.ts" }, "files": "src" , "scripts": { "typecheck": "tsgo --noEmit", "test": "vitest run", "test:ci": "mkdir -p .artifacts/unit && vitest run --reporter=junit --outputFile=.artifacts/unit/junit.xml", "test:watch": "vitest" }, "dependencies": { "@kilocode/plugin": "workspace: " }, "devDependencies": { "@tsconfig/node22": "catalog:", "@types/node": "catalog:", "typescript": "catalog:", "@ty… Evidence: `packages/plugin-atomic-chat/package.json`
- **Package** (package_manifest): { "$schema": "https://json.schemastore.org/package.json", "name": "@kilocode/plugin", "version": "7.4.13", "type": "module", "license": "MIT", "scripts": { "typecheck": "tsgo --noEmit", "build": "tsc" }, "exports": { ".": "./src/index.ts", "./tool": "./src/tool.ts", "./tui": "./src/tui.ts" }, "files": "dist" , "dependencies": { "@kilocode/sdk": "workspace: ", "effect": "catalog:", "zod": "catalog:" }, "peerDependencies": { "@opentui/core": " =0.3.4", "@opentui/solid": " =0.3.4", "@opentui/keymap": " =0.3.4" }, "peerDependenciesMeta": { "@opentui/core": { "optional": true }, "@opentui/keymap": { "optional": true }, "@opentui/solid": { "optional": true } }, "devDependencies": { "@opentui/core… Evidence: `packages/plugin/package.json`
- **Package** (package_manifest): { "$schema": "https://json.schemastore.org/package", "name": "@opencode-ai/script", "license": "MIT", "dependencies": { "semver": "^7.6.3" }, "devDependencies": { "@types/bun": "catalog:", "@types/semver": "^7.5.8" }, "exports": { ".": "./src/index.ts" }, "version": "7.4.13", "peerDependencies": {} } Evidence: `packages/script/package.json`
- **Package** (package_manifest): { "$schema": "https://json.schemastore.org/package.json", "name": "@kilocode/sdk", "version": "7.4.13", "type": "module", "license": "MIT", "scripts": { "typecheck": "tsgo --noEmit", "build": "bun ./script/build.ts" }, "exports": { ".": "./src/index.ts", "./client": "./src/client.ts", "./server": "./src/server.ts", "./v2": "./src/v2/index.ts", "./v2/client": "./src/v2/client.ts", "./v2/gen/client": "./src/v2/gen/client/index.ts", "./v2/server": "./src/v2/server.ts" }, "files": "dist" , "devDependencies": { "@hey-api/openapi-ts": "0.90.10", "@tsconfig/node22": "catalog:", "@types/cross-spawn": "catalog:", "@types/node": "catalog:", "@typescript/native-preview": "catalog:", "typescript": "cat… Evidence: `packages/sdk/js/package.json`
- **Package** (package_manifest): { "$schema": "https://json.schemastore.org/package.json", "name": "@opencode-ai/server", "version": "7.4.13", "private": true, "type": "module", "license": "MIT", "exports": { "./ ": "./src/ .ts" }, "scripts": { "typecheck": "tsgo --noEmit" }, "dependencies": { "@opencode-ai/core": "workspace: ", "drizzle-orm": "catalog:", "effect": "catalog:" }, "devDependencies": { "@tsconfig/bun": "catalog:", "@types/bun": "catalog:", "@typescript/native-preview": "catalog:" }, "peerDependencies": {} } Evidence: `packages/server/package.json`
- **Package** (package_manifest): { "$schema": "https://json.schemastore.org/package.json", "name": "@opencode-ai/storybook", "private": true, "type": "module", "scripts": { "storybook": "storybook dev -p 6006", "build": "storybook build" }, "devDependencies": { "@tailwindcss/vite": "catalog:", "@opencode-ai/ui": "workspace: ", "@solidjs/meta": "catalog:", "@storybook/addon-a11y": "^10.2.13", "@storybook/addon-docs": "^10.2.13", "@storybook/addon-links": "^10.2.13", "@storybook/addon-onboarding": "^10.2.13", "@storybook/addon-vitest": "^10.2.13", "@tsconfig/node22": "catalog:", "@types/node": "catalog:", "@types/react": "18.0.25", "react": "18.2.0", "solid-js": "catalog:", "storybook": "^10.2.13", "storybook-solidjs-vite":… Evidence: `packages/storybook/package.json`
- **Package** (package_manifest): { "$schema": "https://json.schemastore.org/package.json", "name": "@opencode-ai/tui", "version": "7.4.13", "private": true, "type": "module", "license": "MIT", "scripts": { "test": "bun test --timeout 30000 --only-failures", "test:ci": "mkdir -p .artifacts/unit && bun test --timeout 30000 --reporter=junit --reporter-outfile=.artifacts/unit/junit.xml", "typecheck": "tsgo --noEmit" }, "exports": { ".": "./src/index.tsx", "./builtins": "./src/feature-plugins/builtins.ts", "./config": "./src/config/index.tsx", "./context/args": "./src/context/args.tsx", "./context/epilogue": "./src/context/epilogue.tsx", "./context/exit": "./src/context/exit.tsx", "./context/kv": "./src/context/kv.tsx", "./cont… Evidence: `packages/tui/package.json`
- **Package** (package_manifest): { "name": "@opencode-ai/ui", "version": "7.4.13", "type": "module", "license": "MIT", "exports": { "./package.json": "./package.json", "./ ": "./src/components/ .tsx", "./session-diff": "./src/components/session-diff.ts", "./i18n/ ": "./src/i18n/ .ts", "./pierre": "./src/pierre/index.ts", "./pierre/ ": "./src/pierre/ .ts", "./hooks": "./src/hooks/index.ts", "./context": "./src/context/index.ts", "./context/ ": "./src/context/ .tsx", "./styles": "./src/styles/index.css", "./styles/tailwind": "./src/styles/tailwind/index.css", "./theme": "./src/theme/index.ts", "./theme/ ": "./src/theme/ .ts", "./theme/context": "./src/theme/context.tsx", "./icons/provider": "./src/components/provider-icons/t… Evidence: `packages/ui/package.json`
- **Package** (package_manifest): { "name": "@kilocode/upstream-merge", "version": "7.4.13", "private": true, "type": "module", "description": "Scripts for automating upstream opencode merges into Kilo", "scripts": { "merge": "bun run merge.ts", "merge:dry-run": "bun run merge.ts --dry-run", "merge:report": "bun run merge.ts --report-only", "transform:names": "bun run transforms/package-names.ts", "transform:imports": "bun run codemods/transform-imports.ts", "transform:strings": "bun run codemods/transform-strings.ts", "transform:all": "bun run transforms/package-names.ts && bun run codemods/transform-imports.ts && bun run codemods/transform-strings.ts", "versions": "bun run transforms/preserve-versions.ts", "fix:markers":… Evidence: `script/upstream/package.json`
- **Test Fixtures Guide** (documentation): The tmpdir function in fixture/fixture.ts creates temporary directories for tests with automatic cleanup. Evidence: `packages/opencode/test/AGENTS.md`
- **Server Test Guide** (documentation): Use these patterns for server and HttpApi middleware tests in this directory. Evidence: `packages/opencode/test/server/AGENTS.md`
- **Using Google Gemini With Kilo Code** (documentation): Kilo Code supports Google's Gemini family of models through the Google AI Gemini API. Evidence: `packages/kilo-docs/pages/ai-providers/gemini.md`
- **GitHub Issues** (skill_instruction): Use this skill whenever you create or manage a GitHub issue with gh for either the VS Code extension or the JetBrains plugin. Evidence: `.kilo/skills/gh-issues/SKILL.md`
- **Kilo Merge Minimizer** (skill_instruction): Use this skill whenever a normal development task touches shared upstream-owned code and includes Kilo-specific behavior, especially for marker cleanup, extraction work, or kilocode change annotations. Evidence: `.kilo/skills/kilocode-merge-minimizer/SKILL.md`
- The remaining 20 evidence entries are in `AI_CONTEXT_PACK.json` or `EVIDENCE_INDEX.json`.

## Rules the Host AI Must Follow

- **Treat this asset as pre-work context, not a runtime environment.**: The AI Context Pack contains only an evidence-backed understanding of the project, not the project's executable state. Evidence: `.changeset/README.md`, `AGENTS.md`, `README.md`
- **When answering the user, distinguish what can be previewed from what can only be verified after install.**: The consumer value of the pre-install experience comes from reducing bad installs and misjudgments, not from pretending to be a real run. Evidence: `.changeset/README.md`, `AGENTS.md`, `README.md`

## Questions the User Should Answer First

- Which host AI or local environment do you plan to use it in?
- Do you just want to experience the workflow first, or are you ready to actually install?
- What matters most to you: install cost, output quality, or conflicts with your existing rules?

## Acceptance Checks

- Every capability claim can be traced back to a file path in evidence_refs.
- AI_CONTEXT_PACK.md does not package previews as a real run.
- The user can understand who it fits, what it can do, how to start, and the risk boundaries within 3 minutes.

---

## Doramagic Context Augmentation

The following sections strengthen the repository context for a host AI. Human Manual data is a reading route, and pitfall notes become operating constraints.

## Human Manual Outline

Usage rule: this is only a reading route and salience signal, not factual authority. Concrete claims must still return to repo evidence or Claim Graph.

Host AI hard rules:
- Do not treat page titles, section order, summaries, or importance values as factual project evidence.
- When explaining the Human Manual outline, state that it is only a reading route or salience signal.
- Capability, installation, compatibility, runtime state, and risk claims must cite repo evidence, source paths, or Claim Graph.

- **Repository Overview & Monorepo Architecture**: importance `high`
  - source_paths: README.md, AGENTS.md, CONTRIBUTING.md, RELEASING.md, package.json
- **AI Provider & Model Ecosystem**: importance `high`
  - source_paths: packages/core/src/plugin/provider.ts, packages/core/src/plugin/provider/anthropic.ts, packages/core/src/plugin/provider/openai-compatible.ts, packages/core/src/plugin/provider/openai.ts, packages/core/src/plugin/provider/google.ts
- **VS Code Extension: Extension Host, Webview, and Autocomplete**: importance `high`
  - source_paths: packages/kilo-vscode/src/extension.ts, packages/kilo-vscode/src/KiloProvider.ts, packages/kilo-vscode/src/services/autocomplete/index.ts, packages/kilo-vscode/src/services/autocomplete/settings.ts, packages/kilo-vscode/src/services/autocomplete/AutocompleteServiceManager.ts
- **Cross-Platform Surfaces: JetBrains Plugin, CLI, Cloud, KiloClaw**: importance `medium`
  - source_paths: packages/kilo-jetbrains/backend/src/main/kotlin/ai/kilocode/backend/app/KiloBackendAppService.kt, packages/kilo-jetbrains/backend/src/main/kotlin/ai/kilocode/backend/cli/CliServer.kt, packages/kilo-jetbrains/frontend/src/main/kotlin/ai/kilocode/client/session/ui/SessionView.kt, packages/kilo-jetbrains/frontend/src/main/kotlin/ai/kilocode/client/settings/providers/ProvidersConfigurable.kt, packages/kilo-jetbrains/shared/src/main/kotlin/ai/kilocode/rpc/dto/ProviderDto.kt

## Repo Inspection Evidence

- repo_clone_verified: true
- repo_inspection_verified: true
- repo_commit: `a288dbc2ef43eb16f5962a24ecf39b0576b0ed3a`
- inspected_files: `README.md`, `package.json`, `docs/jetbrains-vscode-settings-parity.md`, `packages/containers/README.md`, `packages/containers/script/build.ts`, `packages/containers/tsconfig.json`, `packages/core/drizzle.config.ts`, `packages/core/migration/20260127222353_familiar_lady_ursula/snapshot.json`, `packages/core/migration/20260211171708_add_project_commands/snapshot.json`, `packages/core/migration/20260213144116_wakeful_the_professor/snapshot.json`, `packages/core/migration/20260225215848_workspace/snapshot.json`, `packages/core/migration/20260227213759_add_session_workspace_id/snapshot.json`, `packages/core/migration/20260228203230_blue_harpoon/snapshot.json`, `packages/core/migration/20260303231226_add_workspace_fields/snapshot.json`, `packages/core/migration/20260309230000_move_org_to_state/snapshot.json`, `packages/core/migration/20260312043431_session_message_cursor/snapshot.json`, `packages/core/migration/20260323234822_events/snapshot.json`, `packages/core/migration/20260410174513_workspace-name/snapshot.json`, `packages/core/migration/20260413175956_chief_energizer/snapshot.json`, `packages/core/migration/20260423070820_add_icon_url_override/snapshot.json`

Host AI hard rules:
- Without repo_clone_verified=true, do not claim that the source code has been read.
- Without repo_inspection_verified=true, do not write README, docs, or package-file conclusions as facts.
- Without quick_start_verified=true, do not claim that the Quick Start path has run successfully.

## Doramagic Pitfall Constraints

These rules come from Doramagic discovery, validation, or compilation findings. The host AI must treat them as operating constraints, not background notes.

### Constraint 1: Capability evidence risk requires verification

- Trigger: README/documentation is current enough for a first validation pass.
- Host AI rule: Reproduce the official install and quickstart path in an isolated environment.
- Why it matters: May increase setup, validation, or first-run risk for the user.
- Evidence: capability.assumptions | https://www.npmjs.com/package/@kilocode/cli
- Hard boundary: Do not present this pitfall as solved, verified, or ignorable unless later evidence explicitly closes it.

### Constraint 2: Security or permission risk requires verification

- Trigger: no_demo
- Host AI rule: Reproduce the official install and quickstart path in an isolated environment.
- Why it matters: May increase setup, validation, or first-run risk for the user.
- Evidence: downstream_validation.risk_items | https://www.npmjs.com/package/@kilocode/cli
- Hard boundary: Do not present this pitfall as solved, verified, or ignorable unless later evidence explicitly closes it.

### Constraint 3: Security or permission risk requires verification

- Trigger: no_demo
- Host AI rule: Reproduce the official install and quickstart path in an isolated environment.
- Why it matters: May increase setup, validation, or first-run risk for the user.
- Evidence: risks.scoring_risks | https://www.npmjs.com/package/@kilocode/cli
- Hard boundary: Do not present this pitfall as solved, verified, or ignorable unless later evidence explicitly closes it.