# liteagents-skill-installer - 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 liteagents-skill-installer. 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: `packages/claude/skills/brainstorming/SKILL.md`, `packages/claude/skills/debug-method/SKILL.md`, `packages/claude/skills/docs-builder/SKILL.md`, `packages/claude/skills/live-canvas/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: `packages/claude/skills/brainstorming/SKILL.md`, `packages/claude/skills/debug-method/SKILL.md`, `packages/claude/skills/docs-builder/SKILL.md`, `packages/claude/skills/live-canvas/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/ampcode/commands/live-canvas/README.md`, `packages/claude/plugins/live-canvas-marketplace/plugins/live-canvas-channel/README.md` Claim: `clm_0002` supported 0.86 ## How to Start - `npx liteagents` Evidence: `README.md` Claim: `clm_0005` supported 0.86 - `npm install -g liteagents` Evidence: `README.md` Claim: `clm_0006` supported 0.86 - `/plugin marketplace add ~/.claude/plugins/live-canvas-marketplace` Evidence: `packages/ampcode/commands/live-canvas/README.md` Claim: `clm_0007` supported 0.86 - `/plugin install live-canvas-channel@live-canvas-marketplace` Evidence: `packages/ampcode/commands/live-canvas/README.md` Claim: `clm_0008` supported 0.86 - `curl http://localhost:8788/health` Evidence: `packages/claude/plugins/live-canvas-marketplace/plugins/live-canvas-channel/README.md` Claim: `clm_0009` supported 0.86 - `curl -X POST http://localhost:8788/feedback \` Evidence: `packages/claude/plugins/live-canvas-marketplace/plugins/live-canvas-channel/README.md` Claim: `clm_0010` supported 0.86 ## Continue-or-Stop Decision Card - **Current recommendation**: Sandbox-trial the workflow first - **Why**: This project changes the host AI's development workflow and rules. It is worth trying, but do not install it straight into your primary Claude/Cursor/Codex; verify it first with a temporary host or an isolated directory. ### 30-Second Read - **What to do now**: Sandbox-trial the workflow first - **Minimum safe next step**: Feel the workflow constraints with Prompt Preview first; trial in a temporary host only once satisfied - **Do not trust yet**: Whether this workflow fits your way of working cannot be trusted directly. - **Continuing will touch**: Host behavior change, Command execution, Host AI configuration ### 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: `packages/claude/skills/brainstorming/SKILL.md`, `packages/claude/skills/debug-method/SKILL.md`, `packages/claude/skills/docs-builder/SKILL.md`, `packages/claude/skills/live-canvas/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: `packages/claude/skills/brainstorming/SKILL.md`, `packages/claude/skills/debug-method/SKILL.md`, `packages/claude/skills/docs-builder/SKILL.md`, `packages/claude/skills/live-canvas/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/ampcode/commands/live-canvas/README.md`, `packages/claude/plugins/live-canvas-marketplace/plugins/live-canvas-channel/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 - **Whether this workflow fits your way of working cannot be trusted directly.** (unverified): Workflow-style Skills can strongly constrain AI behavior; they can improve discipline but may also slow your current task pace. Evidence: `CLAUDE.md`, `packages/claude/plugins/live-canvas-marketplace/plugins/live-canvas-channel/README.md`, `packages/claude/skills/brainstorming/SKILL.md`, `packages/claude/skills/debug-method/SKILL.md` et al. - **That it will not conflict with your existing Claude/Cursor/Codex rules cannot be trusted directly.** (inferred): A dev-workflow Skill changes default behaviors like clarifying, planning, testing, and verifying, so it must be tried in a temporary host. Evidence: `CLAUDE.md`, `packages/claude/plugins/live-canvas-marketplace/plugins/live-canvas-channel/README.md`, `packages/claude/skills/brainstorming/SKILL.md`, `packages/claude/skills/debug-method/SKILL.md` et al. - **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: `CLAUDE.md`, `packages/claude/plugins/live-canvas-marketplace/plugins/live-canvas-channel/README.md`, `packages/claude/skills/brainstorming/SKILL.md`, `packages/claude/skills/debug-method/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. ### What Continuing Will Touch - **Host behavior change**: The default development rhythm of clarifying, planning, TDD, verifying, and wrapping up. Why: This kind of Skill draws both its value and its risk from strongly constraining the workflow; confirm first that you are willing to have it change how you work. Evidence: `CLAUDE.md`, `packages/claude/plugins/live-canvas-marketplace/plugins/live-canvas-channel/README.md`, `packages/claude/skills/brainstorming/SKILL.md`, `packages/claude/skills/debug-method/SKILL.md` et al. - **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/ampcode/commands/live-canvas/README.md`, `packages/claude/plugins/live-canvas-marketplace/plugins/live-canvas-channel/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: `CLAUDE.md`, `packages/claude/plugins/live-canvas-marketplace/plugins/live-canvas-channel/README.md`, `packages/claude/skills/brainstorming/SKILL.md`, `packages/claude/skills/debug-method/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/ampcode/commands/live-canvas/README.md`, `packages/claude/plugins/live-canvas-marketplace/plugins/live-canvas-channel/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**: Feel how it changes the AI's development rhythm first, then decide whether to let it into a real host. (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_0011` 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/ampcode/commands/live-canvas/README.md`, `packages/claude/plugins/live-canvas-marketplace/plugins/live-canvas-channel/README.md` Claim: `clm_0012` 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: `packages/claude/skills/brainstorming/SKILL.md`, `packages/claude/skills/debug-method/SKILL.md`, `packages/claude/skills/docs-builder/SKILL.md`, `packages/claude/skills/live-canvas/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/ampcode/commands/live-canvas/README.md`, `packages/claude/plugins/live-canvas-marketplace/plugins/live-canvas-channel/README.md` Claim: `clm_0002` supported 0.86 ### Context Scale - Total files: 220 - Important-file coverage: 40/220 - Evidence index entries: 78 - Role / Skill entries: 9 ### 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 liteagents-skill-installer, 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 liteagents-skill-installer 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 liteagents-skill-installer, 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 9 role / Skill / project-doc entries. - **brainstorming** (skill): Use when creating or developing, before writing code or implementation plans - refines rough ideas into fully-formed designs through collaborative questioning, alternative exploration, and incremental validation. Don't use during clear 'mechanical' processes Activation hint: When the user's task is highly relevant to the workflow described by “brainstorming”, use it for a pre-install experience first, then decide whether to install. Evidence: `packages/claude/skills/brainstorming/SKILL.md` - **debug-method** (skill): Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes - four-phase framework root cause investigation, pattern analysis, hypothesis testing, implementation that ensures understanding before attempting solutions Activation hint: When the user's task is highly relevant to the workflow described by “debug-method”, use it for a pre-install experience first, then decide whether to install. Evidence: `packages/claude/skills/debug-method/SKILL.md` - **docs-builder** (skill): Create or reorganize project documentation with structured /docs hierarchy Activation hint: When the user's task is highly relevant to the workflow described by “docs-builder”, use it for a pre-install experience first, then decide whether to install. Evidence: `packages/claude/skills/docs-builder/SKILL.md` - **live-canvas** (skill): Conduct design interviews, generate UI variations, and collect live click-to-annotate feedback that streams into the session so edits land without leaving the browser. Use when the user wants rapid iterative UI refinement, not just batched feedback. Activation hint: When the user's task is highly relevant to the workflow described by “live-canvas”, use it for a pre-install experience first, then decide whether to install. Evidence: `packages/claude/skills/live-canvas/SKILL.md` - **skill-creator** (skill): Guide for creating effective skills. This skill should be used when users want to create a new skill or update an existing skill that extends Claude's capabilities with specialized knowledge, workflows, or tool integrations. Activation hint: When the user's task is highly relevant to the workflow described by “skill-creator”, use it for a pre-install experience first, then decide whether to install. Evidence: `packages/claude/skills/skill-creator/SKILL.md` - **tdd-flow** (skill): Use when implementing any feature or bugfix, before writing implementation code - write the test first, watch it fail, write minimal code to pass; ensures tests actually verify behavior by requiring failure first Activation hint: When the user's task is highly relevant to the workflow described by “tdd-flow”, use it for a pre-install experience first, then decide whether to install. Evidence: `packages/claude/skills/tdd-flow/SKILL.md` - **test-traps** (skill): Use when writing or changing tests, adding mocks, or tempted to add test-only methods to production code - prevents testing mock behavior, production pollution with test-only methods, and mocking without understanding dependencies Activation hint: When the user's task is highly relevant to the workflow described by “test-traps”, use it for a pre-install experience first, then decide whether to install. Evidence: `packages/claude/skills/test-traps/SKILL.md` - **trace-back** (skill): Use when errors occur deep in execution and you need to trace back to find the original trigger - systematically traces bugs backward through call stack, adding instrumentation when needed, to identify source of invalid data or incorrect behavior Activation hint: When the user's task is highly relevant to the workflow described by “trace-back”, use it for a pre-install experience first, then decide whether to install. Evidence: `packages/claude/skills/trace-back/SKILL.md` - **verify-done** (skill): Use when about to claim work is complete, fixed, or passing, before committing or creating PRs - requires running verification commands and confirming output before making any success claims; evidence before assertions always Activation hint: When the user's task is highly relevant to the workflow described by “verify-done”, use it for a pre-install experience first, then decide whether to install. Evidence: `packages/claude/skills/verify-done/SKILL.md` ## Evidence Index - Indexed 78 evidence entries. - **Quick Start** (documentation): AI development toolkit with 11 specialized agents and 18 commands per tool Evidence: `README.md` - **Live Canvas** (documentation): Click-to-annotate UI design tool for Claude Code. Renders N variants of a component or page in your browser, you click an element and type what to change, and Claude edits the variant file while you watch in the browser. No window switching, no pasted JSON. Evidence: `packages/ampcode/commands/live-canvas/README.md` - **live-canvas-channel** (documentation): Claude Code channel plugin that bridges the Live Canvas browser overlay to a running Claude session. Each Save in the overlay becomes a notifications/claude/channel event — Claude reacts immediately without the user leaving the browser. Evidence: `packages/claude/plugins/live-canvas-marketplace/plugins/live-canvas-channel/README.md` - **Live Canvas** (documentation): Click-to-annotate UI design tool for Claude Code. Renders N variants of a component or page in your browser, you click an element and type what to change, and Claude edits the variant file while you watch in the browser. No window switching, no pasted JSON. Evidence: `packages/claude/skills/live-canvas/README.md` - **Live Canvas** (documentation): Click-to-annotate UI design tool for Claude Code. Renders N variants of a component or page in your browser, you click an element and type what to change, and Claude edits the variant file while you watch in the browser. No window switching, no pasted JSON. Evidence: `packages/droid/commands/live-canvas/README.md` - **Live Canvas** (documentation): Click-to-annotate UI design tool for Claude Code. Renders N variants of a component or page in your browser, you click an element and type what to change, and Claude edits the variant file while you watch in the browser. No window switching, no pasted JSON. Evidence: `packages/opencode/command/live-canvas/README.md` - **Package** (package_manifest): { "name": "liteagents", "version": "2.15.0", "description": "AI development toolkit with 11 specialized agents and 17 commands including live-canvas UI design with click-to-annotate feedback. Simple one-question installer for Claude, Opencode, Ampcode, and Droid.", "main": "index.js", "bin": { "liteagents": "./installer/cli.js", "liteag": "./cli.js" }, "scripts": { "test": "node tests/run-all-tests.js", "test-installer": "node tests/installer/integration.test.js", "install-interactive": "node installer/cli.js", "uninstall-tool": "node installer/cli.js --uninstall", "clean": "rm -rf tests/tmp/ && echo 'Cleaned test artifacts'", "clean:git": "git clean -fdx tests/tmp/", "validate": "node ./sc… Evidence: `package.json` - **Package** (package_manifest): { "name": "live-canvas-channel", "version": "0.5.0", "description": "MCP channel server: bridges Live Canvas HTTP overlay events into the Claude Code session.", "main": "server.js", "type": "commonjs", "engines": { "node": " =18" }, "scripts": { "start": "node server.js" }, "dependencies": { "@modelcontextprotocol/sdk": "^1.0.0" }, "license": "MIT" } Evidence: `packages/claude/plugins/live-canvas-marketplace/plugins/live-canvas-channel/package.json` - **Brainstorming Ideas Into Designs** (skill_instruction): Help turn ideas into fully formed designs and specs through natural collaborative dialogue. Evidence: `packages/claude/skills/brainstorming/SKILL.md` - **Debug Method** (skill_instruction): Random fixes waste time and create new bugs. Quick patches mask underlying issues. Evidence: `packages/claude/skills/debug-method/SKILL.md` - **Documentation Architecture Skill** (skill_instruction): Create or reorganize /docs following a 5-tier hierarchy: Evidence: `packages/claude/skills/docs-builder/SKILL.md` - **Live Canvas Skill** (skill_instruction): This skill implements a complete design exploration workflow: interview, generate variations, collect feedback, refine, preview, and finalize. Evidence: `packages/claude/skills/live-canvas/SKILL.md` - **Skill Creator** (skill_instruction): This skill provides guidance for creating effective skills. Evidence: `packages/claude/skills/skill-creator/SKILL.md` - **TDD Flow** (skill_instruction): APPLIES WHEN: - About to write new production code function, method, class - Implementing any feature or bug fix - Modifying behavior of existing code - Task metadata includes tdd: yes - User requests feature implementation Evidence: `packages/claude/skills/tdd-flow/SKILL.md` - **Trace Back** (skill_instruction): Bugs often manifest deep in the call stack git init in wrong directory, file created in wrong location, database opened with wrong path . Your instinct is to fix where the error appears, but that's treating a symptom. Evidence: `packages/claude/skills/trace-back/SKILL.md` - **Verify Done** (skill_instruction): APPLIES WHEN: - About to say: done, fixed, complete, passing, success - About to commit, push, create PR - About to mark task x Evidence: `packages/claude/skills/verify-done/SKILL.md` - **Test Traps** (skill_instruction): Tests must verify real behavior, not mock behavior. Mocks are a means to isolate, not the thing being tested. Evidence: `packages/claude/skills/test-traps/SKILL.md` - **liteagents** (documentation): AI development toolkit with 11 specialized agents and 20 commands per tool. Supports Claude, Opencode, Ampcode, and Droid. Evidence: `CLAUDE.md` - **liteagents Installer Guide** (documentation): Version : 2.8.1 Last Updated : 2026-05-24 Evidence: `docs/INSTALLER_GUIDE.md` - **antigen gate "sleep" — PRD** (documentation): Validation-gated hot memory for the liteagents /stash → /remember pipeline. No rule reaches always-loaded memory except through measured consequences — similarity/reflection proposes, consequence disposes. This is SkillOpt's validation-gate idea arXiv/microsoft SkillOpt, 2026 ported to the one domain where the reward cannot be replayed offline: the user's own future sessions. Governing rules: AGENT RULES.md POC-first, vanilla → stdlib → external, simple clever, surgical changes . friction's own doctrine applies throughout: precision over recall — a false hot rule loaded into every future session costs more than a missed faint one. Status legend: DECIDED settled · POC-GATED build only after… Evidence: `docs/antigen-gate-prd.md` - **Hot Memory — the stash → remember pipeline** (documentation): Hot Memory — the stash → remember pipeline Evidence: `docs/remember-README.md` - **Global Claude Code CLI** (documentation): Claude Code is a lightweight CLI tool that provides workflow automation commands. Evidence: `packages/claude/CLAUDE.md` - **Global Droid CLI** (documentation): Droid is a lightweight CLI tool that provides workflow automation commands. Evidence: `packages/droid/AGENTS.md` - **Global Opencode CLI** (documentation): Opencode is a lightweight CLI tool that provides workflow automation commands. Evidence: `packages/opencode/AGENTS.md` - **License** (source_file): Apache License Version 2.0, January 2004 http://www.apache.org/licenses/ Evidence: `LICENSE` - **Subagentic Manual** (documentation): Production-ready AI agent framework providing specialized subagents, workflow commands, and development skills for Claude Code , OpenCode , Ampcode , and Droid . Deploy expert AI personas instantly with zero configuration. Evidence: `packages/subagentic-manual.md` - **Workflow** (documentation): You are an expert Product Manager creating clear, actionable PRDs for junior developers. Evidence: `packages/ampcode/agents/1-create-prd.md` - **Session Start** (documentation): You are a router. You don't do work—you match intent to agents/workflows, spawn with minimal context, and track state. Evidence: `packages/ampcode/agents/orchestrator.md` - **── Add your own global sessions root at the TOP so it is checked first ──** (documentation): Run friction analysis, then consolidate session stashes + friction antigens into a single project-local MEMORY.md, and inject into AGENT.md. Friction runs automatically best-effort — there is no separate /friction command. Evidence: `packages/ampcode/commands/remember.md` - **Workflow** (documentation): You are an expert Product Manager creating clear, actionable PRDs for junior developers. Evidence: `packages/claude/agents/1-create-prd.md` - **Session Start** (documentation): You are a router. You don't do work—you match intent to agents/workflows, spawn with minimal context, and track state. Evidence: `packages/claude/agents/orchestrator.md` - **── Add your own global sessions root at the TOP so it is checked first ──** (documentation): Run friction analysis, then consolidate session stashes + friction antigens into a single project-local MEMORY.md, and inject into CLAUDE.md. Friction runs automatically best-effort — there is no separate /friction command. Evidence: `packages/claude/commands/remember.md` - **── Add your own global sessions root at the TOP so it is checked first ──** (documentation): Run friction analysis, then consolidate session stashes + friction antigens into a single project-local MEMORY.md, and inject into AGENTS.md. Friction runs automatically best-effort — there is no separate /friction command. Evidence: `packages/droid/commands/remember.md` - **Workflow** (documentation): You are an expert Product Manager creating clear, actionable PRDs for junior developers. Evidence: `packages/droid/droids/1-create-prd.md` - **Session Start** (documentation): You are a router. You don't do work—you match intent to agents/workflows, spawn with minimal context, and track state. Evidence: `packages/droid/droids/orchestrator.md` - **Workflow** (documentation): You are an expert Product Manager creating clear, actionable PRDs for junior developers. Evidence: `packages/opencode/agent/1-create-prd.md` - **Session Start** (documentation): You are a router. You don't do work—you match intent to agents/workflows, spawn with minimal context, and track state. Evidence: `packages/opencode/agent/orchestrator.md` - **── Add your own global sessions root at the TOP so it is checked first ──** (documentation): Run friction analysis, then consolidate session stashes + friction antigens into a single project-local MEMORY.md, and inject into AGENTS.md. Friction runs automatically best-effort — there is no separate /friction command. Evidence: `packages/opencode/command/remember.md` - **Cli** (source_file): class InteractiveInstaller ⋮---- async askInstallOrUninstall ⋮---- async run ⋮---- async runUninstall ⋮---- const rimraf = dir = ⋮---- findBackups targetPath ⋮---- async selectToolsCheckbox tools ⋮---- const renderList = = ⋮---- console.log '' ; // Empty line at bottom ⋮---- // Initial render ⋮---- const onKeypress = key = ⋮---- async handleFatalError error ⋮---- console.log '' ; // Add spacing ⋮---- // Categorize the error and provide appropriate guidance ⋮---- // Exit with error code ⋮---- / Categorize errors and provide actionable advice @param {Error} error - The error to categorize @returns {object} Object with type, advice array, and technical details / categorizeError error ⋮---- //… Evidence: `installer/cli.js` - **Installation Engine** (source_file): class InstallationEngine ⋮---- async installMultipleTools variant, tools, paths, progressCallback = null, resume = false ⋮---- async installPackage toolId, variant, targetPath, progressCallback = null ⋮---- async copySelectedFiles sourceBase, targetPath, packageContents, progressCallback = null ⋮---- const getFileSize = async filePath = ⋮---- const collectDirectoryFiles = async dirPath, relativePath = '', skipNodeModules = false = ⋮---- async copyDirectory source, target ⋮---- async generateManifest toolId, variant, targetPath ⋮---- const extractAgentName = fullPath = ⋮---- const extractSkillName = fullPath = ⋮---- async createBackup targetPath ⋮---- async rollbackInstallation toolId, targe… Evidence: `installer/installation-engine.js` - **Package Manager** (source_file): class PackageManager ⋮---- async loadVariantConfig toolId ⋮---- async getVariantMetadata toolId, variant ⋮---- async selectVariantContent toolId, variant, availableContent ⋮---- const selectItems = category, variantSelection, availableItems, skipMissing = false = ⋮---- getAvailableVariants toolId ⋮---- async getPackageContents toolId, variant ⋮---- async getAvailableContent packageDir ⋮---- const getItemsInDir = async dir, isAgentDir = false = ⋮---- async countFiles dir ⋮---- async function traverse currentDir ⋮---- async getPackageSize toolId, variant ⋮---- const calculatePathSize = async itemPath = ⋮---- formatBytes bytes ⋮---- async validatePackage toolId, variant ⋮---- const checkConten… Evidence: `installer/package-manager.js` - **Path Manager** (source_file): class PathManager ⋮---- expandPath pathStr ⋮---- sanitizePath pathStr ⋮---- async validatePath pathStr ⋮---- async getDiskSpace pathStr ⋮---- async checkExistingInstallation pathStr ⋮---- getDefaultPath toolId ⋮---- normalizePathForDisplay pathStr Evidence: `installer/path-manager.js` - **Report Template** (source_file): class ReportTemplate ⋮---- generateReport installationData ⋮---- // Header ⋮---- // Summary Section ⋮---- // Tool Details Section ⋮---- // System Information Section ⋮---- // Errors Section if any ⋮---- // Warnings Section if any ⋮---- // Footer ⋮---- / Save report to file @param {string} reportContent - Generated report content @returns {Promise } Path where report was saved / async saveReport reportContent ⋮---- async createAndSaveReport installationData ⋮---- getReportPath ⋮---- generateHeader ⋮---- generateSummary summary ⋮---- generateToolDetails tools ⋮---- generateSystemInfo ⋮---- generateErrorsSection errors ⋮---- generateWarningsSection warnings ⋮---- generateFooter ⋮---- formatDur… Evidence: `installer/report-template.js` - **Verification System** (source_file): class VerificationSystem ⋮---- async verifyInstallation toolId, variant, targetPath ⋮---- async verifyManifest targetPath ⋮---- async verifyDirectoryStructure targetPath ⋮---- async verifyFileIntegrity toolId, variant, targetPath ⋮---- async verifyPermissions targetPath ⋮---- async verifyToolCompatibility toolId, targetPath ⋮---- async countFilesInDirectory dir ⋮---- async function traverse currentDir ⋮---- generateReport ⋮---- clearResults Evidence: `installer/verification-system.js` - **Validate All Packages** (source_file): async function getDirectorySize dirPath ⋮---- function calculateSize currentPath ⋮---- function formatBytes bytes ⋮---- async function countFiles dirPath ⋮---- function countRecursive currentPath ⋮---- async function validateAllPackages Evidence: `scripts/validate-all-packages.js` - **Friction** (source_file): function loadConfig ⋮---- function parseJsonl raw, source ⋮---- function parseISODate s ⋮---- function formatDuration minutes ⋮---- function globFiles dir, pattern, recursive ⋮---- function listDirs dir ⋮---- // ============================================================================= // FRICTION ANALYZE - derive session name // ============================================================================= ⋮---- function deriveSessionName sessionFile, metadata ⋮---- function extractToolNameFromResult result ⋮---- function looksLikeTerminalPaste text ⋮---- function extractSignals sessionFile ⋮---- content = text; // Fall through to user message handling below ⋮---- // Handle single dict t… Evidence: `packages/ampcode/commands/remember/friction.js` - **Friction** (source_file): function loadConfig ⋮---- function parseJsonl raw, source ⋮---- function parseISODate s ⋮---- function formatDuration minutes ⋮---- function globFiles dir, pattern, recursive ⋮---- function listDirs dir ⋮---- // ============================================================================= // FRICTION ANALYZE - derive session name // ============================================================================= ⋮---- function deriveSessionName sessionFile, metadata ⋮---- function extractToolNameFromResult result ⋮---- function looksLikeTerminalPaste text ⋮---- function extractSignals sessionFile ⋮---- content = text; // Fall through to user message handling below ⋮---- // Handle single dict t… Evidence: `packages/claude/commands/remember/friction.js` - **Friction** (source_file): function loadConfig ⋮---- function parseJsonl raw, source ⋮---- function parseISODate s ⋮---- function formatDuration minutes ⋮---- function globFiles dir, pattern, recursive ⋮---- function listDirs dir ⋮---- // ============================================================================= // FRICTION ANALYZE - derive session name // ============================================================================= ⋮---- function deriveSessionName sessionFile, metadata ⋮---- function extractToolNameFromResult result ⋮---- function looksLikeTerminalPaste text ⋮---- function extractSignals sessionFile ⋮---- content = text; // Fall through to user message handling below ⋮---- // Handle single dict t… Evidence: `packages/droid/commands/remember/friction.js` - **Friction** (source_file): function loadConfig ⋮---- function parseJsonl raw, source ⋮---- function parseISODate s ⋮---- function formatDuration minutes ⋮---- function globFiles dir, pattern, recursive ⋮---- function listDirs dir ⋮---- // ============================================================================= // FRICTION ANALYZE - derive session name // ============================================================================= ⋮---- function deriveSessionName sessionFile, metadata ⋮---- function extractToolNameFromResult result ⋮---- function looksLikeTerminalPaste text ⋮---- function extractSignals sessionFile ⋮---- content = text; // Fall through to user message handling below ⋮---- // Handle single dict t… Evidence: `packages/opencode/command/remember/friction.js` - **Changelog** (documentation): All notable changes to liteagents will be documented in this file. Evidence: `CHANGELOG.md` - **Global Ampcode CLI** (documentation): Ampcode is a lightweight CLI tool that provides workflow automation commands. Evidence: `packages/ampcode/AGENT.md` - **CRITICAL BEHAVIOR** (documentation): You are an expert Technical Program Manager translating PRDs into precise, actionable task lists for non-technical users, accounting for existing codebase patterns. Evidence: `packages/ampcode/agents/2-generate-tasks.md` - **RULES** (documentation): You are an implementation agent executing tasks from a provided task list. Evidence: `packages/ampcode/agents/3-process-task-list.md` - **Invocation Modes** (documentation): You are an Expert Senior Software Engineer & Implementation Specialist. Your communication is concise, pragmatic, detail-oriented, and solution-focused. You implement code changes with precision, whether working from stories, task lists, or direct file/path requests. Evidence: `packages/ampcode/agents/code-developer.md` - **Invocation Modes** (documentation): You are a Context Initialization Specialist. Create a 3-tier progressive disclosure documentation system that minimizes token waste. Evidence: `packages/ampcode/agents/context-builder.md` - **Session Start** (documentation): You are an elite Product Manager—an Investigative Product Strategist. You specialize in epics, user stories, prioritization, and backlog management with validation-first thinking. Evidence: `packages/ampcode/agents/feature-planner.md` - **Session Start** (documentation): You are an elite Business Analyst and Strategic Research Partner. Deep, evidence-based research through iterative dialogue. Evidence: `packages/ampcode/agents/market-researcher.md` - **Session Start** (documentation): You are a QA Engineer and Test Architect. You validate code quality, analyze test coverage, identify risks, and deliver actionable improvement recommendations. Evidence: `packages/ampcode/agents/quality-assurance.md` - **On First Interaction** (documentation): You are a Senior System Architect who designs simple, pragmatic architectures focused on delivering MVP. You validate requirements, select appropriate tech stacks, and produce high-level architecture HLA and detailed design HLD documents. Start with questions, recommend the simplest viable solution, and challenge over-engineering. Evidence: `packages/ampcode/agents/system-architect.md` - **On First Interaction** (documentation): You are a Senior UI Designer who favors lightweight, functional, pragmatic designs. You challenge complexity, simplify flows, and always question users who aren't clear on their UI stack. You think in steps-to-goal and minimize them. Evidence: `packages/ampcode/agents/ui-designer.md` - The remaining 18 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: `README.md`, `packages/ampcode/commands/live-canvas/README.md`, `packages/claude/plugins/live-canvas-marketplace/plugins/live-canvas-channel/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: `README.md`, `packages/ampcode/commands/live-canvas/README.md`, `packages/claude/plugins/live-canvas-marketplace/plugins/live-canvas-channel/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. - **Overview & Installation**: importance `high` - source_paths: README.md, package.json, cli.js, postinstall.js, docs/INSTALLER_GUIDE.md - **Multi-Package Architecture**: importance `medium` - source_paths: installer/installation-engine.js, installer/package-manager.js, installer/path-manager.js, installer/verification-system.js, installer/report-template.js - **Hot Memory Pipeline (/stash → /friction → /remember)**: importance `high` - source_paths: docs/remember-README.md, docs/antigen-gate-prd.md, packages/claude/commands/remember.md, packages/claude/commands/remember/friction.js, packages/opencode/command/remember.md - **Agents, Commands, Skills & Workflows**: importance `high` - source_paths: packages/subagentic-manual.md, packages/claude/skills/tdd-flow/SKILL.md, packages/claude/skills/test-traps/SKILL.md, packages/claude/skills/verify-done/SKILL.md, packages/claude/agents/orchestrator.md ## Repo Inspection Evidence - repo_clone_verified: true - repo_inspection_verified: true - repo_commit: `88f67a4067a5b64c831bb7ae336e0f9fc9aed4bc` - inspected_files: `README.md`, `package.json`, `docs/INSTALLER_GUIDE.md`, `docs/antigen-gate-prd.md`, `docs/remember-README.md`, `packages/ampcode/AGENT.md`, `packages/ampcode/agents/1-create-prd.md`, `packages/ampcode/agents/2-generate-tasks.md`, `packages/ampcode/agents/3-process-task-list.md`, `packages/ampcode/agents/code-developer.md`, `packages/ampcode/agents/context-builder.md`, `packages/ampcode/agents/feature-planner.md`, `packages/ampcode/agents/market-researcher.md`, `packages/ampcode/agents/orchestrator.md`, `packages/ampcode/agents/quality-assurance.md`, `packages/ampcode/agents/system-architect.md`, `packages/ampcode/agents/ui-designer.md`, `packages/ampcode/commands/brainstorming.md`, `packages/ampcode/commands/debug-method.md`, `packages/ampcode/commands/diff-review.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/hamr0/liteagents - 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/hamr0/liteagents - 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/hamr0/liteagents - 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/hamr0/liteagents - 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/hamr0/liteagents - Hard boundary: Do not present this pitfall as solved, verified, or ignorable unless later evidence explicitly closes it.