# claude-code-toolkit - 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 claude-code-toolkit. 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: `user-level-reference/skills/arch-analyze/SKILL.md`, `user-level-reference/skills/code-review/SKILL.md`, `user-level-reference/skills/contribute-upstream/SKILL.md`, `user-level-reference/skills/explaining-code/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: `user-level-reference/skills/arch-analyze/SKILL.md`, `user-level-reference/skills/code-review/SKILL.md`, `user-level-reference/skills/contribute-upstream/SKILL.md`, `user-level-reference/skills/explaining-code/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` Claim: `clm_0002` supported 0.86

## How to Start

- `git clone https://github.com/dagonet/claude-code-toolkit` Evidence: `README.md` Claim: `clm_0005` supported 0.86

## Continue-or-Stop Decision Card

- **Current recommendation**: Sandbox trial only
- **Why**: The project has signals of install commands, host configuration, or local writes; do not go straight into your primary environment—trial it in isolation first.

### 30-Second Read

- **What to do now**: Sandbox trial only
- **Minimum safe next step**: Run Prompt Preview first; if you still want to install, trial only in an isolated environment
- **Do not trust yet**: Real output quality 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: `user-level-reference/skills/arch-analyze/SKILL.md`, `user-level-reference/skills/code-review/SKILL.md`, `user-level-reference/skills/contribute-upstream/SKILL.md`, `user-level-reference/skills/explaining-code/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: `user-level-reference/skills/arch-analyze/SKILL.md`, `user-level-reference/skills/code-review/SKILL.md`, `user-level-reference/skills/contribute-upstream/SKILL.md`, `user-level-reference/skills/explaining-code/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` 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

- **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: `AGENTS.md`, `user-level-reference/skills/arch-analyze/SKILL.md`, `user-level-reference/skills/code-review/SKILL.md`, `user-level-reference/skills/contribute-upstream/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`
- **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: `AGENTS.md`, `user-level-reference/skills/arch-analyze/SKILL.md`, `user-level-reference/skills/code-review/SKILL.md`, `user-level-reference/skills/contribute-upstream/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`
- **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.)
- **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.
- **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_0006` 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` Claim: `clm_0007` 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: `user-level-reference/skills/arch-analyze/SKILL.md`, `user-level-reference/skills/code-review/SKILL.md`, `user-level-reference/skills/contribute-upstream/SKILL.md`, `user-level-reference/skills/explaining-code/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` Claim: `clm_0002` supported 0.86

### Context Scale

- Total files: 196
- Important-file coverage: 40/196
- Evidence index entries: 80
- Role / Skill entries: 11

### 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 claude-code-toolkit, 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 claude-code-toolkit 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 claude-code-toolkit, 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 11 role / Skill / project-doc entries.

- **arch-analyze** (skill): Analyzes solution architecture, dependencies, and patterns. Triggers when asking about architecture or project structure analysis. Activation hint: When the user's task is highly relevant to the workflow described by “arch-analyze”, use it for a pre-install experience first, then decide whether to install. Evidence: `user-level-reference/skills/arch-analyze/SKILL.md`
- **code-review** (skill): Performs comprehensive code review. Use when reviewing PRs, branches, code quality, or analyzing changes. Activation hint: When the user's task is highly relevant to the workflow described by “code-review”, use it for a pre-install experience first, then decide whether to install. Evidence: `user-level-reference/skills/code-review/SKILL.md`
- **contribute-upstream** (skill): Push project improvements back to the claude-code-toolkit template. Triggers on /contribute-upstream. Activation hint: When the user's task is highly relevant to the workflow described by “contribute-upstream”, use it for a pre-install experience first, then decide whether to install. Evidence: `user-level-reference/skills/contribute-upstream/SKILL.md`
- **explaining-code** (skill): Explains code via diagrams and analogies. Use when teaching a codebase or answering "how does this work? Activation hint: When the user's task is highly relevant to the workflow described by “explaining-code”, use it for a pre-install experience first, then decide whether to install. Evidence: `user-level-reference/skills/explaining-code/SKILL.md`
- **fix-errors** (skill): Parses build errors and fixes them systematically. Triggers on build failures, compilation errors, or when user reports errors. Activation hint: When the user's task is highly relevant to the workflow described by “fix-errors”, use it for a pre-install experience first, then decide whether to install. Evidence: `user-level-reference/skills/fix-errors/SKILL.md`
- **impact-analysis** (skill): Analyzes the impact of proposed changes on the codebase. Triggers when planning changes or asking about affected areas. Activation hint: When the user's task is highly relevant to the workflow described by “impact-analysis”, use it for a pre-install experience first, then decide whether to install. Evidence: `user-level-reference/skills/impact-analysis/SKILL.md`
- **karpathy-guidelines** (skill): Behavioral guidelines to reduce common LLM coding mistakes. Use when writing, reviewing, or refactoring code. Activation hint: When the user's task is highly relevant to the workflow described by “karpathy-guidelines”, use it for a pre-install experience first, then decide whether to install. Evidence: `user-level-reference/skills/karpathy-guidelines/SKILL.md`
- **orient** (skill): Quickly understand and map a project's structure and architecture. Triggers when exploring new codebases or asking about project layout. Activation hint: When the user's task is highly relevant to the workflow described by “orient”, use it for a pre-install experience first, then decide whether to install. Evidence: `user-level-reference/skills/orient/SKILL.md`
- **refactor** (skill): Identifies code quality issues and suggests refactoring. Triggers on requests to clean up, improve, or refactor code. Activation hint: When the user's task is highly relevant to the workflow described by “refactor”, use it for a pre-install experience first, then decide whether to install. Evidence: `user-level-reference/skills/refactor/SKILL.md`
- **security-audit** (skill): Comprehensive security review including vulnerabilities, code patterns, and secrets. Triggers on security-related questions or audit requests. Activation hint: When the user's task is highly relevant to the workflow described by “security-audit”, use it for a pre-install experience first, then decide whether to install. Evidence: `user-level-reference/skills/security-audit/SKILL.md`
- **sync-template** (skill): Pull template updates into the current project. Triggers on /sync-template. Activation hint: When the user's task is highly relevant to the workflow described by “sync-template”, use it for a pre-install experience first, then decide whether to install. Evidence: `user-level-reference/skills/sync-template/SKILL.md`

## Evidence Index

- Indexed 80 evidence entries.

- **AGENTS.md — Agent-Guided Project Setup** (documentation): AGENTS.md — Agent-Guided Project Setup Evidence: `AGENTS.md`
- **Claude Code Toolkit** (documentation): ! License: MIT https://img.shields.io/badge/License-MIT-blue.svg LICENSE ! Ask DeepWiki https://deepwiki.com/badge.svg https://deepwiki.com/dagonet/claude-code-toolkit Evidence: `README.md`
- **User-Level Rules All Projects** (documentation): This machine runs Windows 11 with Git Bash as the shell. Evidence: `user-level-reference/CLAUDE.md`
- **User-Level Claude Code Configuration Reference** (documentation): User-Level Claude Code Configuration Reference Evidence: `user-level-reference/README.md`
- **Claude Code -- General Behavior** (documentation): At the start of every session: 1. Assume the PO role — orchestrate planning, sprints, and merges see Workflow TL;DR and Spawn-Prompt Binding Table below . Do NOT Read AGENT TEAM.md up front 850+ lines . Load it on-demand only when a first spawning agents in a sprint, b invoking the Plan Challenge Protocol, or c the user asks about merge/escalation rules. 2. Read PROJECT CONTEXT.md — load build commands and workflow config 3. Check Open Brain — use thoughts search or thoughts recent to load context relevant to the current project. Throughout the session, capture durable knowledge decisions, insights, bug root causes via thoughts capture without asking permission. For synthesis-style question… Evidence: `templates/dotnet-maui/CLAUDE.md`
- **Claude Code -- General Behavior** (documentation): At the start of every session: 1. Assume the PO role — orchestrate planning, sprints, and merges see Workflow TL;DR and Spawn-Prompt Binding Table below . Do NOT Read AGENT TEAM.md up front 850+ lines . Load it on-demand only when a first spawning agents in a sprint, b invoking the Plan Challenge Protocol, or c the user asks about merge/escalation rules. 2. Read PROJECT CONTEXT.md — load build commands and workflow config 3. Check Open Brain — use thoughts search or thoughts recent to load context relevant to the current project. Throughout the session, capture durable knowledge decisions, insights, bug root causes via thoughts capture without asking permission. For synthesis-style question… Evidence: `templates/dotnet/CLAUDE.md`
- **Claude Code -- General Behavior** (documentation): At the start of every session: 1. Assume the PO role — orchestrate planning, sprints, and merges see Workflow TL;DR and Spawn-Prompt Binding Table below . Do NOT Read AGENT TEAM.md up front 850+ lines . Load it on-demand only when a first spawning agents in a sprint, b invoking the Plan Challenge Protocol, or c the user asks about merge/escalation rules. 2. Read PROJECT CONTEXT.md — load build commands and workflow config 3. Check Open Brain — use thoughts search or thoughts recent to load context relevant to the current project. Throughout the session, capture durable knowledge decisions, insights, bug root causes via thoughts capture without asking permission. For synthesis-style question… Evidence: `templates/general/CLAUDE.md`
- **Claude Code -- General Behavior** (documentation): At the start of every session: 1. Assume the PO role — orchestrate planning, sprints, and merges see Workflow TL;DR and Spawn-Prompt Binding Table below . Do NOT Read AGENT TEAM.md up front 850+ lines . Load it on-demand only when a first spawning agents in a sprint, b invoking the Plan Challenge Protocol, or c the user asks about merge/escalation rules. 2. Read PROJECT CONTEXT.md — load build commands and workflow config 3. Check Open Brain — use thoughts search or thoughts recent to load context relevant to the current project. Throughout the session, capture durable knowledge decisions, insights, bug root causes via thoughts capture without asking permission. For synthesis-style question… Evidence: `templates/java/CLAUDE.md`
- **Claude Code -- General Behavior** (documentation): At the start of every session: 1. Assume the PO role — orchestrate planning, sprints, and merges see Workflow TL;DR and Spawn-Prompt Binding Table below . Do NOT Read AGENT TEAM.md up front 850+ lines . Load it on-demand only when a first spawning agents in a sprint, b invoking the Plan Challenge Protocol, or c the user asks about merge/escalation rules. 2. Read PROJECT CONTEXT.md — load build commands and workflow config 3. Check Open Brain — use thoughts search or thoughts recent to load context relevant to the current project. Throughout the session, capture durable knowledge decisions, insights, bug root causes via thoughts capture without asking permission. For synthesis-style question… Evidence: `templates/python/CLAUDE.md`
- **Claude Code -- General Behavior** (documentation): At the start of every session: 1. Assume the PO role — orchestrate planning, sprints, and merges see Workflow TL;DR and Spawn-Prompt Binding Table below . Do NOT Read AGENT TEAM.md up front 850+ lines . Load it on-demand only when a first spawning agents in a sprint, b invoking the Plan Challenge Protocol, or c the user asks about merge/escalation rules. 2. Read PROJECT CONTEXT.md — load build commands and workflow config 3. Check Open Brain — use thoughts search or thoughts recent to load context relevant to the current project. Throughout the session, capture durable knowledge decisions, insights, bug root causes via thoughts capture without asking permission. For synthesis-style question… Evidence: `templates/rust-tauri/CLAUDE.md`
- **Contributing to Claude Code Toolkit** (documentation): Contributing to Claude Code Toolkit Evidence: `CONTRIBUTING.md`
- **Architecture** (documentation): Claude Code supports layered configuration: project-level .claude/ overrides user-level ~/.claude/ for same-named items. Evidence: `docs/architecture.md`
- **Getting Started** (documentation): Everything you need to know before running the setup script. This guide covers prerequisites, optional dependencies, and adoption tiers so you can decide how much of the setup to use. Evidence: `docs/getting-started.md`
- **Hook Enforcement Ideas for AGENT TEAM.md Workflows** (documentation): Hook Enforcement Ideas for AGENT TEAM.md Workflows Evidence: `docs/hook-enforcement-ideas.md`
- **Setup Walkthrough** (documentation): Detailed instructions for running setup-project.{sh,ps1} against a target project, plus a manual fallback. For prerequisites and adoption tiers see getting-started.md getting-started.md . For per-variant flag details see templates.md templates.md . For MCP server installation see ../mcp-servers/HOWTO.md ../mcp-servers/HOWTO.md . Evidence: `docs/setup.md`
- **Template Sync** (documentation): After initial setup, keep projects in sync with template changes using two skills. Both skills delegate all deterministic operations hashing, diffing, placeholder replacement, three-way merge to the template-sync-tools MCP server — the AI handles only user interaction and judgment calls. Evidence: `docs/template-sync.md`
- **Template Variants** (documentation): Feature General .NET .NET MAUI Rust/Tauri Java Python --------- --------- ------ ----------- ------------ ------ -------- Language/Framework Any C /.NET .NET MAUI Desktop Rust + TypeScript Tauri v2 Java Spring Boot Python Default Task Source plan-files plan-files plan-files plan-files plan-files plan-files User-level MCP universal git, github, ollama, template-sync, searxng, open-brain + plugins same same same same same Project-level MCP auto-generated none unless --sqlite-db-path dotnet-tools dotnet-tools , windows-mcp rust-tools , windows-mcp none unless --sqlite-db-path none unless --sqlite-db-path Agents 7 8 +dotnet-coder 8 full FlaUI tester 8 +rust-coder 8 +java-coder 8 +python-coder C… Evidence: `docs/templates.md`
- **Post-Setup Verification** (documentation): After applying a template, walk through this checklist to confirm everything is working: Evidence: `docs/verification.md`
- **Workflow Audit** (documentation): Snapshot of the claude-code-toolkit agent workflow as of 2026-04-12: the current shape diagram , known weaknesses W1-W17 , and the follow-up PR roadmap derived from those weaknesses. Evidence: `docs/workflow-audit.md`
- **Architecture Analysis Skill** (skill_instruction): Comprehensive analysis of .NET solution architecture, dependencies, and patterns. Evidence: `user-level-reference/skills/arch-analyze/SKILL.md`
- **Code Review Skill** (skill_instruction): Perform a thorough code review with quality metrics and actionable feedback. Evidence: `user-level-reference/skills/code-review/SKILL.md`
- **Contribute Upstream** (skill_instruction): Push improvements from the current project back to the claude-code-toolkit template. Evidence: `user-level-reference/skills/contribute-upstream/SKILL.md`
- **Skill** (skill_instruction): When explaining code, always include: Evidence: `user-level-reference/skills/explaining-code/SKILL.md`
- **Fix Errors Skill** (skill_instruction): Parse error output and fix issues systematically. Evidence: `user-level-reference/skills/fix-errors/SKILL.md`
- **Impact Analysis Skill** (skill_instruction): Analyze the impact of a proposed change on the codebase. Evidence: `user-level-reference/skills/impact-analysis/SKILL.md`
- **Karpathy Guidelines** (skill_instruction): Behavioral guidelines to reduce common LLM coding mistakes, derived from Andrej Karpathy's observations https://x.com/karpathy/status/2015883857489522876 on LLM coding pitfalls. Adapted from forrestchang/andrej-karpathy-skills https://github.com/forrestchang/andrej-karpathy-skills MIT . Evidence: `user-level-reference/skills/karpathy-guidelines/SKILL.md`
- **Project Orientation Skill** (skill_instruction): Quickly understand the structure and architecture of the current project. Evidence: `user-level-reference/skills/orient/SKILL.md`
- **Refactor Skill** (skill_instruction): Identify code quality issues and refactor problematic code. Evidence: `user-level-reference/skills/refactor/SKILL.md`
- **Security Audit Skill** (skill_instruction): Comprehensive security review including vulnerabilities, code patterns, and secrets. Evidence: `user-level-reference/skills/security-audit/SKILL.md`
- **Sync Template Downstream** (skill_instruction): Pull updates from the claude-code-toolkit template repo into the current project. Evidence: `user-level-reference/skills/sync-template/SKILL.md`
- **License** (source_file): Copyright c 2025-present claude-code-toolkit contributors Evidence: `LICENSE`
- **License** (source_file): Adapted from https://github.com/forrestchang/andrej-karpathy-skills MIT licensed . Evidence: `user-level-reference/skills/karpathy-guidelines/LICENSE`
- **Changelog** (documentation): 2026-07-09 — Session-mining round 3: plan-mode friction, config hygiene 40 Evidence: `CHANGELOG.md`
- **Code of Conduct** (documentation): We are committed to making participation in this project a welcoming experience for everyone, regardless of background or experience level. Evidence: `CODE_OF_CONDUCT.md`
- **Security Policy** (documentation): If you discover a security vulnerability, please report it responsibly. Evidence: `SECURITY.md`
- **MCP Dependency Cleanup and Layering** (documentation): MCP Dependency Cleanup and Layering Evidence: `docs/plans/2026-04-12-mcp-dependency-cleanup.md`
- **PR A — Workflow Documentation Consistency** (documentation): PR A — Workflow Documentation Consistency Evidence: `docs/plans/2026-04-12-pr-a-workflow-doc-consistency.md`
- **PR B — Hook Hardening W1 + W2** (documentation): Date: 2026-04-12 Tier: T3 shell script rewrite + doc update + new plan file Team: coder, code-reviewer, tester Status: Approved, implementing Evidence: `docs/plans/2026-04-12-pr-b-hook-hardening.md`
- **Plan: Wire Superpowers Skills Into Templates and User-Level Reference** (documentation): Plan: Wire Superpowers Skills Into Templates and User-Level Reference Evidence: `docs/plans/2026-04-12-wire-superpowers-skills.md`
- **Context Bloat Baseline — 2026-04-14** (documentation): Context Bloat Baseline — 2026-04-14 Evidence: `docs/plans/2026-04-13-context-baseline.md`
- **Workflow Meta Issues — Context Bloat & Over-Engineering** (documentation): Workflow Meta Issues — Context Bloat & Over-Engineering Evidence: `docs/plans/2026-04-13-workflow-meta-issues.md`
- **Context Bloat Baseline — 2026-04-14** (documentation): Context Bloat Baseline — 2026-04-14 Evidence: `docs/plans/2026-04-14-context-baseline.md`
- **Read Size Gate — User-Level PreToolUse Hook** (documentation): Read Size Gate — User-Level PreToolUse Hook Evidence: `docs/plans/2026-04-14-read-size-gate.md`
- **Context Token Optimization — Templates & user-level-reference** (documentation): Context Token Optimization — Templates & user-level-reference Evidence: `docs/plans/2026-04-19-context-optimization.md`
- **Sync MCP tool references for Open Brain v0.3.0** (documentation): Sync MCP tool references for Open Brain v0.3.0 Evidence: `docs/plans/2026-04-26-open-brain-v030-sync.md`
- **Plan: Environment Hygiene — Clean Start / Clean Finish** (documentation): Plan: Environment Hygiene — Clean Start / Clean Finish Evidence: `docs/plans/2026-04-29-environment-hygiene-dod.md`
- **Sub-Agent Merge Protocol — Documentation Reconciliation Plan consolidated** (documentation): Sub-Agent Merge Protocol — Documentation Reconciliation Plan consolidated Evidence: `docs/plans/2026-05-03-subagent-merge-protocol-fix.md`
- **Claude Code Agent Team Setup** (documentation): 1. Read PROJECT CONTEXT.md first — it defines the project's tech stack, commands, and task source mode github-issues or plan-files . 2. Read this document for roles, workflow, and rules. 3. Look up your mode in the Mode Behavior Table to know where to read tasks, post findings, and close work. Evidence: `templates/dotnet-maui/AGENT_TEAM.md`
- **Project Context** (documentation): - Name : {{PROJECT NAME}} - Tech stack : {{TECH STACK}} - Repository : {{REPO URL}} - Solution file : {{SOLUTION FILE}} - MAUI project : {{MAUI PROJECT}} - Test project : {{TEST PROJECT}} - Branch strategy : main is protected; feature branches per task see AGENT TEAM.md Mode Behavior Table for naming convention Evidence: `templates/dotnet-maui/PROJECT_CONTEXT.md`
- **{{PROJECT NAME}} — Project State** (documentation): {{PROJECT NAME}} — Project State Current Sprint No active sprint. Backlog See GitHub Issues. Evidence: `templates/dotnet-maui/PROJECT_STATE.md`
- **Claude Code Agent Team Setup** (documentation): 1. Read PROJECT CONTEXT.md first — it defines the project's tech stack, commands, and task source mode github-issues or plan-files . 2. Read this document for roles, workflow, and rules. 3. Look up your mode in the Mode Behavior Table to know where to read tasks, post findings, and close work. Evidence: `templates/dotnet/AGENT_TEAM.md`
- **Project Context** (documentation): - Name : {{PROJECT NAME}} - Tech stack : {{TECH STACK}} - Repository : {{REPO URL}} - Solution file : {{SOLUTION FILE}} - Branch strategy : main is protected; feature branches per task see AGENT TEAM.md Mode Behavior Table for naming convention Evidence: `templates/dotnet/PROJECT_CONTEXT.md`
- **{{PROJECT NAME}} — Project State** (documentation): {{PROJECT NAME}} — Project State Current Sprint No active sprint. Backlog See GitHub Issues. Evidence: `templates/dotnet/PROJECT_STATE.md`
- **Claude Code Agent Team Setup** (documentation): 1. Read PROJECT CONTEXT.md first — it defines the project's tech stack, commands, and task source mode github-issues or plan-files . 2. Read this document for roles, workflow, and rules. 3. Look up your mode in the Mode Behavior Table to know where to read tasks, post findings, and close work. Evidence: `templates/general/AGENT_TEAM.md`
- **Project Context** (documentation): - Name : {{PROJECT NAME}} - Tech stack : {{TECH STACK}} - Repository : {{REPO URL}} - Branch strategy : main is protected; feature branches per task see AGENT TEAM.md Mode Behavior Table for naming convention Evidence: `templates/general/PROJECT_CONTEXT.md`
- **{{PROJECT NAME}} — Project State** (documentation): {{PROJECT NAME}} — Project State Current Sprint No active sprint. Backlog See GitHub Issues. Evidence: `templates/general/PROJECT_STATE.md`
- **Claude Code Agent Team Setup** (documentation): 1. Read PROJECT CONTEXT.md first — it defines the project's tech stack, commands, and task source mode github-issues or plan-files . 2. Read this document for roles, workflow, and rules. 3. Look up your mode in the Mode Behavior Table to know where to read tasks, post findings, and close work. Evidence: `templates/java/AGENT_TEAM.md`
- **Project Context** (documentation): - Name : {{PROJECT NAME}} - Repository : {{REPO URL}} - Tech Stack : {{TECH STACK}} Evidence: `templates/java/PROJECT_CONTEXT.md`
- **{{PROJECT NAME}} — Project State** (documentation): {{PROJECT NAME}} — Project State Current Sprint No active sprint. Backlog See GitHub Issues. Evidence: `templates/java/PROJECT_STATE.md`
- **Claude Code Agent Team Setup** (documentation): 1. Read PROJECT CONTEXT.md first — it defines the project's tech stack, commands, and task source mode github-issues or plan-files . 2. Read this document for roles, workflow, and rules. 3. Look up your mode in the Mode Behavior Table to know where to read tasks, post findings, and close work. Evidence: `templates/python/AGENT_TEAM.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: `AGENTS.md`, `README.md`, `user-level-reference/CLAUDE.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: `AGENTS.md`, `README.md`, `user-level-reference/CLAUDE.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.

- **Introduction to the Claude Code Toolkit**: importance `high`
  - source_paths: README.md, AGENTS.md, CHANGELOG.md, CONTRIBUTING.md, CODE_OF_CONDUCT.md
- **Architecture: Layered Config, Agents, Commands, Skills, and Hooks**: importance `high`
  - source_paths: docs/architecture.md, docs/hook-enforcement-ideas.md, hooks/block-bash-vcs.sh, hooks/gate-before-merge.sh, hooks/no-push-main.sh
- **Template Variants and Per-Stack Customization**: importance `high`
  - source_paths: docs/templates.md, docs/template-sync.md, templates/general/CLAUDE.md, templates/general/AGENT_TEAM.md, templates/general/PROJECT_CONTEXT.md
- **Setup, Deployment, Verification, and Workflow Operations**: importance `high`
  - source_paths: setup-project.sh, setup-project.ps1, docs/setup.md, docs/getting-started.md, docs/verification.md

## Repo Inspection Evidence

- repo_clone_verified: true
- repo_inspection_verified: true
- repo_commit: `9021ddc04573597323e53e93c07a6f07d1c94844`
- inspected_files: `README.md`, `docs/architecture.md`, `docs/getting-started.md`, `docs/hook-enforcement-ideas.md`, `docs/plans/2026-04-12-mcp-dependency-cleanup.md`, `docs/plans/2026-04-12-pr-a-workflow-doc-consistency.md`, `docs/plans/2026-04-12-pr-b-hook-hardening.md`, `docs/plans/2026-04-12-wire-superpowers-skills.md`, `docs/plans/2026-04-13-context-baseline.md`, `docs/plans/2026-04-13-workflow-meta-issues.md`, `docs/plans/2026-04-14-context-baseline.md`, `docs/plans/2026-04-14-read-size-gate.md`, `docs/plans/2026-04-19-context-optimization.md`, `docs/plans/2026-04-26-open-brain-v030-sync.md`, `docs/plans/2026-04-29-environment-hygiene-dod.md`, `docs/plans/2026-05-03-subagent-merge-protocol-fix.md`, `docs/setup.md`, `docs/template-sync.md`, `docs/templates.md`, `docs/verification.md`

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://github.com/dagonet/claude-code-toolkit
- 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://github.com/dagonet/claude-code-toolkit
- 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://github.com/dagonet/claude-code-toolkit
- Hard boundary: Do not present this pitfall as solved, verified, or ignorable unless later evidence explicitly closes it.

### Constraint 4: Maintenance risk requires verification

- Trigger: issue_or_pr_quality=unknown。
- 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: evidence.maintainer_signals | https://github.com/dagonet/claude-code-toolkit
- Hard boundary: Do not present this pitfall as solved, verified, or ignorable unless later evidence explicitly closes it.

### Constraint 5: Maintenance risk requires verification

- Trigger: release_recency=unknown。
- 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: evidence.maintainer_signals | https://github.com/dagonet/claude-code-toolkit
- Hard boundary: Do not present this pitfall as solved, verified, or ignorable unless later evidence explicitly closes it.