# omniconductor - 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 omniconductor. 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_0002` supported 0.86

## What It Can Do

- **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_0001` supported 0.86

## How to Start

- `git clone https://github.com/lee77840/omniconductor ~/conductor` Evidence: `README.md` Claim: `clm_0003` supported 0.86
- `npx omniconductor init --target=claude ~/your-project --recipes=coding-conventions,tdd` Evidence: `README.md` Claim: `clm_0004` supported 0.86
- `npx omniconductor list                                # list the 6 adapters` Evidence: `README.md` Claim: `clm_0005` supported 0.86
- `npx omniconductor models show .                       # inspect saved Tier mappings` Evidence: `README.md` Claim: `clm_0006` supported 0.86
- `npx omniconductor models configure --target=all .     # change mappings` Evidence: `README.md` Claim: `clm_0007` supported 0.86
- `npx omniconductor init --target=claude . --dry-run --no-prompt   # preview, writes nothing` Evidence: `README.md` Claim: `clm_0008` supported 0.86
- `npx omniconductor init --target=all . --no-prompt --accept-model-defaults  # explicit noninteractive setup` Evidence: `README.md` Claim: `clm_0009` supported 0.86
- `npx omniconductor init --target=claude . --uninstall             # revert` Evidence: `README.md` Claim: `clm_0010` supported 0.86
- `git clone https://github.com/lee77840/omniconductor /c/conductor` Evidence: `README.md` Claim: `clm_0011` supported 0.86

## Continue-or-Stop Decision Card

- **Current recommendation**: Trial role matching first
- **Why**: This project is more of a role library; the core risk is picking the wrong role or treating role copy as execution capability. Trial role matching with Prompt Preview first, then decide whether to sandbox-import it.

### 30-Second Read

- **What to do now**: Trial role matching first
- **Minimum safe next step**: Trial role matching with Prompt Preview first; import in isolation only once satisfied
- **Do not trust yet**: Role quality and task fit cannot be trusted directly.
- **Continuing will touch**: Role selection bias, 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_0002` 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_0001` 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_0003` supported 0.86

### What You Cannot Trust Yet

- **Role quality and task fit cannot be trusted directly.** (unverified): A role library proves there are many roles; it does not prove each one fits your specific task or that a role produces high-quality results.
- **Do not treat role copy as real execution capability.** (unverified): Before install you can only judge whether the role description and task profile match; you cannot prove it can complete the task inside the host AI.
- **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`
- **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

- **Role selection bias**: The user's judgment about which expert role should handle the task. Why: Picking the wrong role makes the AI answer from the wrong expert perspective, wasting time or misleading decisions.
- **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`
- **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 an interactive trial to verify the task profile and role match first; do not import the whole role library up front. (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.
- **Keep a record of the original role selection**: If output goes off-topic, you can return to the task-profiling stage and reselect a role instead of pushing on with the wrong one.
- **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_0012` inferred 0.45
- **Command execution will modify the local environment**: Install commands may write to the user's home directory, the host plugin directory, or project configuration. Mitigation: Run in an isolated environment or a test account first. Evidence: `README.md` Claim: `clm_0013` supported 0.86
- **To confirm**: After a real install, is it compatible with the user's current host AI version?. Why: Compatibility can only be verified in the actual host environment.
- **To confirm**: Does the project's output quality meet the user's specific task?. Why: The pre-install preview can only show flow and boundaries; it cannot replace real evaluation.
- **To confirm**: Do the install commands require network access, permissions, or global writes?. Why: This affects install risk in both enterprise and personal environments.

## Pre-Work Working Context

### Loading Order

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

### Task Routes

- **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_0001` supported 0.86

### Context Scale

- Total files: 226
- Important-file coverage: 40/226
- Evidence index entries: 80
- Role / Skill entries: 62

### 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 omniconductor, 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 omniconductor 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 omniconductor, 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 62 role / Skill / project-doc entries.

- **CONDUCTOR** (project_doc): One workflow framework, every coding agent. Activation hint: Reference this when the user needs to understand the project's structure, install path, or boundaries. Evidence: `README.md`
- **adapters/ — Layer 2, per-tool transformers** (project_doc): adapters/ — Layer 2, per-tool transformers Activation hint: Reference this when the user needs to understand the project's structure, install path, or boundaries. Evidence: `adapters/README.md`
- **core/ — Layer 1, Universal source-of-truth** (project_doc): core/ — Layer 1, Universal source-of-truth Activation hint: Reference this when the user needs to understand the project's structure, install path, or boundaries. Evidence: `core/README.md`
- **examples/** (project_doc): Worked example installs that show what CONDUCTOR actually writes into a project . Activation hint: Reference this when the user needs to understand the project's structure, install path, or boundaries. Evidence: `examples/README.md`
- **Adapter — Claude Code T1, full support** (project_doc): Adapter — Claude Code T1, full support Activation hint: Reference this when the user needs to understand the project's structure, install path, or boundaries. Evidence: `adapters/claude/README.md`
- **Hookify Rule Templates Claude Code adapter** (project_doc): Hookify Rule Templates Claude Code adapter Activation hint: Reference this when the user needs to understand the project's structure, install path, or boundaries. Evidence: `adapters/claude/hookify-templates/README.md`
- **Adapter — Codex T2** (project_doc): OpenAI Codex the modern shell-driven agent — not the deprecated original Codex API is a T2 target because: Activation hint: Reference this when the user needs to understand the project's structure, install path, or boundaries. Evidence: `adapters/codex/README.md`
- **Adapter — GitHub Copilot T2** (project_doc): GitHub Copilot is a T2 target because: Activation hint: Reference this when the user needs to understand the project's structure, install path, or boundaries. Evidence: `adapters/copilot/README.md`
- **Adapter — Cursor T1** (project_doc): Cursor is a strong CONDUCTOR target because: Activation hint: Reference this when the user needs to understand the project's structure, install path, or boundaries. Evidence: `adapters/cursor/README.md`
- **Adapter — Gemini CLI T2** (project_doc): - It supports a single always-loaded rule file GEMINI.md . - It supports a coding-style guide convention .gemini/styleguide.md . - It excels at large-context exploration — the always-loaded rule bundle fits its strengths. Activation hint: Reference this when the user needs to understand the project's structure, install path, or boundaries. Evidence: `adapters/gemini/README.md`
- **Adapter — Windsurf T3** (project_doc): Windsurf the AI-IDE is a T3 target because: Activation hint: Reference this when the user needs to understand the project's structure, install path, or boundaries. Evidence: `adapters/windsurf/README.md`
- **core/anti-patterns/ — Token-economy anti-pattern catalog** (project_doc): Token-economy anti-pattern catalog — diagnostic reference for adopters losing cache hit rate, paying for tool spam, or carrying bloated prefixes. Activation hint: Reference this when the user needs to understand the project's structure, install path, or boundaries. Evidence: `core/anti-patterns/README.md`
- **core/docs-templates/ — Universal doc template skeletons** (project_doc): core/docs-templates/ — Universal doc template skeletons Activation hint: Reference this when the user needs to understand the project's structure, install path, or boundaries. Evidence: `core/docs-templates/README.md`
- **core/hooks/ — Universal hook templates** (project_doc): core/hooks/ — Universal hook templates Activation hint: Reference this when the user needs to understand the project's structure, install path, or boundaries. Evidence: `core/hooks/README.md`
- **core/memory-pattern/ — 4-type memory pattern universal** (project_doc): core/memory-pattern/ — 4-type memory pattern universal Activation hint: Reference this when the user needs to understand the project's structure, install path, or boundaries. Evidence: `core/memory-pattern/README.md`
- **core/recipes/ — Project-specific opt-in patterns** (project_doc): core/recipes/ — Project-specific opt-in patterns Activation hint: Reference this when the user needs to understand the project's structure, install path, or boundaries. Evidence: `core/recipes/README.md`
- **core/roles/ — 8 universal roles + 1 opt-in reflector** (project_doc): core/roles/ — 8 universal roles + 1 opt-in reflector Activation hint: Reference this when the user needs to understand the project's structure, install path, or boundaries. Evidence: `core/roles/README.md`
- **core/universal-rules/ — The 5 universal rules** (project_doc): core/universal-rules/ — The 5 universal rules Activation hint: Reference this when the user needs to understand the project's structure, install path, or boundaries. Evidence: `core/universal-rules/README.md`
- **core/workflow/ — Universal workflow definition** (project_doc): core/workflow/ — Universal workflow definition Activation hint: Reference this when the user needs to understand the project's structure, install path, or boundaries. Evidence: `core/workflow/README.md`
- **Conductor — VSCode extension** (project_doc): Thin wrapper around the Conductor https://github.com/lee77840/conductor lfamily bash adapters. Install Claude Code, Cursor, or GitHub Copilot rules into the current workspace from the Command Palette. Activation hint: Reference this when the user needs to understand the project's structure, install path, or boundaries. Evidence: `phase-2/vscode-extension/README.md`
- **CONTRIBUTING — CONDUCTOR** (project_doc): How to add a new tool adapter, fix a bug, or improve a universal rule. Activation hint: Reference this when the user needs to understand the project's structure, install path, or boundaries. Evidence: `docs/CONTRIBUTING.md`
- **CONDUCTOR repository instructions** (project_doc): This repository is maintained with the same rules in every supported coding tool. Read CURRENT WORK.md , SESSION HANDOFF.md , and the relevant files under docs/ before changing implementation. Activation hint: Reference this when the user needs to understand the project's structure, install path, or boundaries. Evidence: `AGENTS.md`
- **ARCHITECTURE — CONDUCTOR** (project_doc): CONDUCTOR is a 3-layer system. Each layer has a single, sharp responsibility. Activation hint: Reference this when the user needs to understand the project's structure, install path, or boundaries. Evidence: `docs/ARCHITECTURE.md`
- **One-time, vendor-neutral model routing** (project_doc): One-time, vendor-neutral model routing Activation hint: Reference this when the user needs to understand the project's structure, install path, or boundaries. Evidence: `docs/MODEL-ROUTING.md`
- **PHILOSOPHY — CONDUCTOR** (project_doc): The beliefs CONDUCTOR is built on. If you disagree with any of these, you will fight the framework. Activation hint: Reference this when the user needs to understand the project's structure, install path, or boundaries. Evidence: `docs/PHILOSOPHY.md`
- **Project Orchestrator Manual installed by CONDUCTOR** (project_doc): Project Orchestrator Manual installed by CONDUCTOR Activation hint: Reference this when the user needs to understand the project's structure, install path, or boundaries. Evidence: `examples/sample-claude-project/CLAUDE.md`
- **Changelog** (project_doc): All notable changes to CONDUCTOR are documented here. Format follows Keep a Changelog https://keepachangelog.com/ ; versioning is SemVer https://semver.org/ . Activation hint: Reference this when the user needs to understand the project's structure, install path, or boundaries. Evidence: `CHANGELOG.md`
- **ROADMAP — CONDUCTOR** (project_doc): Last updated: 2026-07-09. Estimated dates assume CONDUCTOR work resumes at ~50% of weekly capacity the reference project retains priority through its 2026 launch . Activation hint: Reference this when the user needs to understand the project's structure, install path, or boundaries. Evidence: `ROADMAP.md`
- **VISION — CONDUCTOR** (project_doc): 한글: AI 코딩 도구가 우후죽순 늘어났습니다. 2026년의 개발자 한 명이 Claude Code 깊은 리팩터 , Cursor IDE 내 페어 프로그래밍 , GitHub Copilot 인라인 자동완성 + PR 리뷰 , Gemini CLI 저렴한 대용량 컨텍스트 탐색 , Codex 셸 기반 작업 , Windsurf 를 동시에 쓸 수 있습니다. 그런데 도구마다 룰·컨텍스트 포맷이 제각각입니다. 도구를 바꾸는 순간 그동안 쌓은 규율이 사라집니다. Claude 용으로 쓴 룰은 Cursor 에서 자동 로드되지 않고, 스스로 훈련해 온 Plan → Architecture → Tasks 워크플로는 다른 에이전트를 여는 순간 증발합니다. 6개월간 다듬은 취향이 통째로 날아갑니다. 이것이 CONDUCTOR 가 푸는 문제입니다. Activation hint: Reference this when the user needs to understand the project's structure, install path, or boundaries. Evidence: `VISION.md`
- **Adapter Live-Verification Guide** (project_doc): What the automated checks DO and DON'T cover, and a manual checklist to close the gap. Activation hint: Reference this when the user needs to understand the project's structure, install path, or boundaries. Evidence: `docs/ADAPTER-LIVE-VERIFICATION.md`
- **COMPARISON — CONDUCTOR vs other tools** (project_doc): COMPARISON — CONDUCTOR vs other tools Activation hint: Reference this when the user needs to understand the project's structure, install path, or boundaries. Evidence: `docs/COMPARISON.md`
- **COMPATIBILITY MATRIX — CONDUCTOR per tool** (project_doc): COMPATIBILITY MATRIX — CONDUCTOR per tool Activation hint: Reference this when the user needs to understand the project's structure, install path, or boundaries. Evidence: `docs/COMPATIBILITY-MATRIX.md`
- **Context Editing Guide Claude / Anthropic SDK** (project_doc): Context Editing Guide Claude / Anthropic SDK Activation hint: Reference this when the user needs to understand the project's structure, install path, or boundaries. Evidence: `docs/CONTEXT-EDITING-GUIDE.md`
- **DESIGN DECISIONS — CONDUCTOR** (project_doc): ADR-style decision records. Each entry: Status / Context / Decision / Consequences / Alternatives considered. Activation hint: Reference this when the user needs to understand the project's structure, install path, or boundaries. Evidence: `docs/DESIGN-DECISIONS.md`
- **HOW IT WORKS PER TOOL — CONDUCTOR** (project_doc): For each of the 6 supported tools: what gets installed, where, what works, and what is lost compared to Claude Code the reference implementation . Activation hint: Reference this when the user needs to understand the project's structure, install path, or boundaries. Evidence: `docs/HOW-IT-WORKS-PER-TOOL.md`
- **IDE Compatibility Notes — known quirks per consumer** (project_doc): IDE Compatibility Notes — known quirks per consumer Activation hint: Reference this when the user needs to understand the project's structure, install path, or boundaries. Evidence: `docs/IDE-COMPATIBILITY-NOTES.md`
- **IDE Smoke Testing — Conductor adapter outputs** (project_doc): IDE Smoke Testing — Conductor adapter outputs Activation hint: Reference this when the user needs to understand the project's structure, install path, or boundaries. Evidence: `docs/IDE-SMOKE-TESTING.md`
- **CONDUCTOR — Document Index** (project_doc): Single catalog of every asset in this repo. Updated when new documents land. Activation hint: Reference this when the user needs to understand the project's structure, install path, or boundaries. Evidence: `docs/INDEX.md`
- **MANUAL INSTALL — CONDUCTOR** (project_doc): Companion to README.md . Step-by-step manual install for every supported tool, on Mac and Windows. Activation hint: Reference this when the user needs to understand the project's structure, install path, or boundaries. Evidence: `docs/MANUAL-INSTALL.md`
- **MIGRATION — switching tools mid-project** (project_doc): MIGRATION — switching tools mid-project Activation hint: Reference this when the user needs to understand the project's structure, install path, or boundaries. Evidence: `docs/MIGRATION.md`
- **Prompt Caching Guide Claude / Anthropic SDK** (project_doc): Prompt Caching Guide Claude / Anthropic SDK Activation hint: Reference this when the user needs to understand the project's structure, install path, or boundaries. Evidence: `docs/PROMPT-CACHING-GUIDE.md`
- **Publication Policy — private source, public distribution** (project_doc): Publication Policy — private source, public distribution Activation hint: Reference this when the user needs to understand the project's structure, install path, or boundaries. Evidence: `docs/PUBLICATION-POLICY.md`
- **Conductor — Marketplace Publish Guide** (project_doc): Conductor — Marketplace Publish Guide Activation hint: Reference this when the user needs to understand the project's structure, install path, or boundaries. Evidence: `docs/PUBLISH-GUIDE.md`
- **Claude Code — supported features** (project_doc): Detailed matrix of which CONDUCTOR features Claude Code supports natively. Activation hint: Reference this when the user needs to understand the project's structure, install path, or boundaries. Evidence: `adapters/claude/SUPPORTED-FEATURES.md`
- **Claude Code adapter — transform.sh specification** (project_doc): Claude Code adapter — transform.sh specification Activation hint: Reference this when the user needs to understand the project's structure, install path, or boundaries. Evidence: `adapters/claude/transform-spec.md`
- **Codex — supported features** (project_doc): Detailed matrix of which CONDUCTOR features Codex supports. Activation hint: Reference this when the user needs to understand the project's structure, install path, or boundaries. Evidence: `adapters/codex/SUPPORTED-FEATURES.md`
- **Codex adapter — transform.sh specification** (project_doc): Codex adapter — transform.sh specification Activation hint: Reference this when the user needs to understand the project's structure, install path, or boundaries. Evidence: `adapters/codex/transform-spec.md`
- **GitHub Copilot — supported features** (project_doc): GitHub Copilot — supported features Activation hint: Reference this when the user needs to understand the project's structure, install path, or boundaries. Evidence: `adapters/copilot/SUPPORTED-FEATURES.md`
- **GitHub Copilot adapter — transform.sh specification** (project_doc): GitHub Copilot adapter — transform.sh specification Activation hint: Reference this when the user needs to understand the project's structure, install path, or boundaries. Evidence: `adapters/copilot/transform-spec.md`
- **Cursor — supported features** (project_doc): Detailed matrix of which CONDUCTOR features Cursor supports natively. Activation hint: Reference this when the user needs to understand the project's structure, install path, or boundaries. Evidence: `adapters/cursor/SUPPORTED-FEATURES.md`
- **Cursor adapter — transform.sh specification** (project_doc): Cursor adapter — transform.sh specification Activation hint: Reference this when the user needs to understand the project's structure, install path, or boundaries. Evidence: `adapters/cursor/transform-spec.md`
- **Gemini CLI — supported features** (project_doc): Detailed matrix of which CONDUCTOR features Gemini CLI supports. Activation hint: Reference this when the user needs to understand the project's structure, install path, or boundaries. Evidence: `adapters/gemini/SUPPORTED-FEATURES.md`
- **Gemini CLI adapter — transform.sh specification** (project_doc): Gemini CLI adapter — transform.sh specification Activation hint: Reference this when the user needs to understand the project's structure, install path, or boundaries. Evidence: `adapters/gemini/transform-spec.md`
- **Windsurf — supported features** (project_doc): Detailed matrix of which CONDUCTOR features Windsurf supports. Activation hint: Reference this when the user needs to understand the project's structure, install path, or boundaries. Evidence: `adapters/windsurf/SUPPORTED-FEATURES.md`
- **Windsurf adapter — transform.sh specification** (project_doc): Windsurf adapter — transform.sh specification Activation hint: Reference this when the user needs to understand the project's structure, install path, or boundaries. Evidence: `adapters/windsurf/transform-spec.md`
- **CURRENT WORK —** (project_doc): What this is : session continuity log. Updated EVERY session. Read FIRST every session start. Lean ~150 lines . When it grows past, archive older sessions to docs/sessions/ .md . Activation hint: Reference this when the user needs to understand the project's structure, install path, or boundaries. Evidence: `examples/sample-claude-project/docs/CURRENT_WORK.md`
- **INDEX — document map** (project_doc): What this is : a single page that points to every other doc in docs/ . Update when you add a doc. Activation hint: Reference this when the user needs to understand the project's structure, install path, or boundaries. Evidence: `examples/sample-claude-project/docs/INDEX.md`
- **PLANS —** (project_doc): What this is : long-term phase roadmap. Strategic — what major work remains and in what order. Updated infrequently per quarter / major milestone . Activation hint: Reference this when the user needs to understand the project's structure, install path, or boundaries. Evidence: `examples/sample-claude-project/docs/PLANS.md`
- **REMAINING TASKS —** (project_doc): What this is : open scope dashboard. Things that need to ship before launch / before next milestone. Updated when scope changes. NOT a daily task tracker that's TASKS.md . Activation hint: Reference this when the user needs to understand the project's structure, install path, or boundaries. Evidence: `examples/sample-claude-project/docs/REMAINING_TASKS.md`
- **TASKS —** (project_doc): What this is : phase completion tracker. Per-phase task list with concrete work items. Updated as tasks complete. Activation hint: Reference this when the user needs to understand the project's structure, install path, or boundaries. Evidence: `examples/sample-claude-project/docs/TASKS.md`
- **Spec — PLACEHOLDER — copy + rename per area** (project_doc): Spec — PLACEHOLDER — copy + rename per area Activation hint: Reference this when the user needs to understand the project's structure, install path, or boundaries. Evidence: `examples/sample-claude-project/docs/specs/_example.md`
- **Changelog — Conductor VSCode extension** (project_doc): Changelog — Conductor VSCode extension Activation hint: Reference this when the user needs to understand the project's structure, install path, or boundaries. Evidence: `phase-2/vscode-extension/CHANGELOG.md`

## Evidence Index

- Indexed 80 evidence entries.

- **CONDUCTOR** (documentation): One workflow framework, every coding agent. Evidence: `README.md`
- **adapters/ — Layer 2, per-tool transformers** (documentation): adapters/ — Layer 2, per-tool transformers Evidence: `adapters/README.md`
- **core/ — Layer 1, Universal source-of-truth** (documentation): core/ — Layer 1, Universal source-of-truth Evidence: `core/README.md`
- **examples/** (documentation): Worked example installs that show what CONDUCTOR actually writes into a project . Evidence: `examples/README.md`
- **Adapter — Claude Code T1, full support** (documentation): Adapter — Claude Code T1, full support Evidence: `adapters/claude/README.md`
- **Hookify Rule Templates Claude Code adapter** (documentation): Hookify Rule Templates Claude Code adapter Evidence: `adapters/claude/hookify-templates/README.md`
- **Adapter — Codex T2** (documentation): OpenAI Codex the modern shell-driven agent — not the deprecated original Codex API is a T2 target because: Evidence: `adapters/codex/README.md`
- **Adapter — GitHub Copilot T2** (documentation): GitHub Copilot is a T2 target because: Evidence: `adapters/copilot/README.md`
- **Adapter — Cursor T1** (documentation): Cursor is a strong CONDUCTOR target because: Evidence: `adapters/cursor/README.md`
- **Adapter — Gemini CLI T2** (documentation): - It supports a single always-loaded rule file GEMINI.md . - It supports a coding-style guide convention .gemini/styleguide.md . - It excels at large-context exploration — the always-loaded rule bundle fits its strengths. Evidence: `adapters/gemini/README.md`
- **Adapter — Windsurf T3** (documentation): Windsurf the AI-IDE is a T3 target because: Evidence: `adapters/windsurf/README.md`
- **core/anti-patterns/ — Token-economy anti-pattern catalog** (documentation): core/anti-patterns/ — Token-economy anti-pattern catalog Evidence: `core/anti-patterns/README.md`
- **core/docs-templates/ — Universal doc template skeletons** (documentation): core/docs-templates/ — Universal doc template skeletons Evidence: `core/docs-templates/README.md`
- **core/hooks/ — Universal hook templates** (documentation): core/hooks/ — Universal hook templates Evidence: `core/hooks/README.md`
- **core/memory-pattern/ — 4-type memory pattern universal** (documentation): core/memory-pattern/ — 4-type memory pattern universal Evidence: `core/memory-pattern/README.md`
- **core/recipes/ — Project-specific opt-in patterns** (documentation): core/recipes/ — Project-specific opt-in patterns Evidence: `core/recipes/README.md`
- **core/roles/ — 8 universal roles + 1 opt-in reflector** (documentation): core/roles/ — 8 universal roles + 1 opt-in reflector Evidence: `core/roles/README.md`
- **core/universal-rules/ — The 5 universal rules** (documentation): core/universal-rules/ — The 5 universal rules Evidence: `core/universal-rules/README.md`
- **core/workflow/ — Universal workflow definition** (documentation): core/workflow/ — Universal workflow definition Evidence: `core/workflow/README.md`
- **Conductor — VSCode extension** (documentation): Thin wrapper around the Conductor https://github.com/lee77840/conductor lfamily bash adapters. Install Claude Code, Cursor, or GitHub Copilot rules into the current workspace from the Command Palette. Evidence: `phase-2/vscode-extension/README.md`
- **Package** (package_manifest): { "name": "omniconductor", "version": "1.1.2", "description": "Multi-coding-agent workflow framework. Write your project's rules, workflow, and discipline ONCE — install into Claude Code, Cursor, GitHub Copilot, Gemini CLI, Codex, or Windsurf. Encodes the discipline developers most often skip — spec-before-code, review gates, session continuity — so your AI agents catch what's easy to miss.", "license": "Apache-2.0", "author": "LFamily Labs LLC", "repository": { "type": "git", "url": "git+https://github.com/lee77840/omniconductor.git" }, "homepage": "https://github.com/lee77840/omniconductor readme", "bugs": { "url": "https://github.com/lee77840/omniconductor/issues" }, "engines": { "node":… Evidence: `package.json`
- **CONTRIBUTING — CONDUCTOR** (documentation): How to add a new tool adapter, fix a bug, or improve a universal rule. Evidence: `docs/CONTRIBUTING.md`
- **Package** (package_manifest): { "name": "conductor", "displayName": "Conductor — Production-grade workflow framework", "description": "Install Conductor rules, hooks, and recipes for Claude Code, Cursor, or GitHub Copilot from your editor. Thin wrapper around the validated bash adapters.", "publisher": "lfamily-labs", "version": "0.3.0", "license": "Apache-2.0", "icon": "images/icon.png", "engines": { "vscode": "^1.85.0" }, "categories": "AI", "Other" , "keywords": "claude", "claude-code", "cursor", "copilot", "rules", "workflow", "tdd", "ai", "agent", "framework" , "repository": { "type": "git", "url": "https://github.com/lee77840/conductor lfamily.git" }, "homepage": "https://github.com/lee77840/conductor lfamily read… Evidence: `phase-2/vscode-extension/package.json`
- **CONDUCTOR repository instructions** (documentation): This repository is maintained with the same rules in every supported coding tool. Read CURRENT WORK.md , SESSION HANDOFF.md , and the relevant files under docs/ before changing implementation. Evidence: `AGENTS.md`
- **ARCHITECTURE — CONDUCTOR** (documentation): CONDUCTOR is a 3-layer system. Each layer has a single, sharp responsibility. Evidence: `docs/ARCHITECTURE.md`
- **One-time, vendor-neutral model routing** (documentation): One-time, vendor-neutral model routing Evidence: `docs/MODEL-ROUTING.md`
- **PHILOSOPHY — CONDUCTOR** (documentation): The beliefs CONDUCTOR is built on. If you disagree with any of these, you will fight the framework. Evidence: `docs/PHILOSOPHY.md`
- **Project Orchestrator Manual installed by CONDUCTOR** (documentation): Project Orchestrator Manual installed by CONDUCTOR Evidence: `examples/sample-claude-project/CLAUDE.md`
- **License** (source_file): Apache License Version 2.0, January 2004 http://www.apache.org/licenses/ Evidence: `LICENSE`
- **License** (source_file): Apache License Version 2.0, January 2004 http://www.apache.org/licenses/ Evidence: `phase-2/vscode-extension/LICENSE`
- **Changelog** (documentation): All notable changes to CONDUCTOR are documented here. Format follows Keep a Changelog https://keepachangelog.com/ ; versioning is SemVer https://semver.org/ . Evidence: `CHANGELOG.md`
- **ROADMAP — CONDUCTOR** (documentation): Last updated: 2026-07-09. Estimated dates assume CONDUCTOR work resumes at ~50% of weekly capacity the reference project retains priority through its 2026 launch . Evidence: `ROADMAP.md`
- **VISION — CONDUCTOR** (documentation): 한글: AI 코딩 도구가 우후죽순 늘어났습니다. 2026년의 개발자 한 명이 Claude Code 깊은 리팩터 , Cursor IDE 내 페어 프로그래밍 , GitHub Copilot 인라인 자동완성 + PR 리뷰 , Gemini CLI 저렴한 대용량 컨텍스트 탐색 , Codex 셸 기반 작업 , Windsurf 를 동시에 쓸 수 있습니다. 그런데 도구마다 룰·컨텍스트 포맷이 제각각입니다. 도구를 바꾸는 순간 그동안 쌓은 규율이 사라집니다. Claude 용으로 쓴 룰은 Cursor 에서 자동 로드되지 않고, 스스로 훈련해 온 Plan → Architecture → Tasks 워크플로는 다른 에이전트를 여는 순간 증발합니다. 6개월간 다듬은 취향이 통째로 날아갑니다. 이것이 CONDUCTOR 가 푸는 문제입니다. Evidence: `VISION.md`
- **Adapter Live-Verification Guide** (documentation): What the automated checks DO and DON'T cover, and a manual checklist to close the gap. Evidence: `docs/ADAPTER-LIVE-VERIFICATION.md`
- **COMPARISON — CONDUCTOR vs other tools** (documentation): COMPARISON — CONDUCTOR vs other tools Evidence: `docs/COMPARISON.md`
- **COMPATIBILITY MATRIX — CONDUCTOR per tool** (documentation): COMPATIBILITY MATRIX — CONDUCTOR per tool Evidence: `docs/COMPATIBILITY-MATRIX.md`
- **Context Editing Guide Claude / Anthropic SDK** (documentation): Context Editing Guide Claude / Anthropic SDK Evidence: `docs/CONTEXT-EDITING-GUIDE.md`
- **DESIGN DECISIONS — CONDUCTOR** (documentation): ADR-style decision records. Each entry: Status / Context / Decision / Consequences / Alternatives considered. Evidence: `docs/DESIGN-DECISIONS.md`
- **HOW IT WORKS PER TOOL — CONDUCTOR** (documentation): For each of the 6 supported tools: what gets installed, where, what works, and what is lost compared to Claude Code the reference implementation . Evidence: `docs/HOW-IT-WORKS-PER-TOOL.md`
- **IDE Compatibility Notes — known quirks per consumer** (documentation): IDE Compatibility Notes — known quirks per consumer Evidence: `docs/IDE-COMPATIBILITY-NOTES.md`
- **IDE Smoke Testing — Conductor adapter outputs** (documentation): IDE Smoke Testing — Conductor adapter outputs Evidence: `docs/IDE-SMOKE-TESTING.md`
- **CONDUCTOR — Document Index** (documentation): Single catalog of every asset in this repo. Updated when new documents land. Evidence: `docs/INDEX.md`
- **MANUAL INSTALL — CONDUCTOR** (documentation): Companion to README.md . Step-by-step manual install for every supported tool, on Mac and Windows. Evidence: `docs/MANUAL-INSTALL.md`
- **MIGRATION — switching tools mid-project** (documentation): MIGRATION — switching tools mid-project Evidence: `docs/MIGRATION.md`
- **Prompt Caching Guide Claude / Anthropic SDK** (documentation): Prompt Caching Guide Claude / Anthropic SDK Evidence: `docs/PROMPT-CACHING-GUIDE.md`
- **Publication Policy — private source, public distribution** (documentation): Publication Policy — private source, public distribution Evidence: `docs/PUBLICATION-POLICY.md`
- **Conductor — Marketplace Publish Guide** (documentation): Conductor — Marketplace Publish Guide Evidence: `docs/PUBLISH-GUIDE.md`
- **Claude Code — supported features** (documentation): Detailed matrix of which CONDUCTOR features Claude Code supports natively. Evidence: `adapters/claude/SUPPORTED-FEATURES.md`
- **Claude Code adapter — transform.sh specification** (documentation): Claude Code adapter — transform.sh specification Evidence: `adapters/claude/transform-spec.md`
- **Codex — supported features** (documentation): Detailed matrix of which CONDUCTOR features Codex supports. Evidence: `adapters/codex/SUPPORTED-FEATURES.md`
- **Codex adapter — transform.sh specification** (documentation): Codex adapter — transform.sh specification Evidence: `adapters/codex/transform-spec.md`
- **GitHub Copilot — supported features** (documentation): GitHub Copilot — supported features Evidence: `adapters/copilot/SUPPORTED-FEATURES.md`
- **GitHub Copilot adapter — transform.sh specification** (documentation): GitHub Copilot adapter — transform.sh specification Evidence: `adapters/copilot/transform-spec.md`
- **Cursor — supported features** (documentation): Detailed matrix of which CONDUCTOR features Cursor supports natively. Evidence: `adapters/cursor/SUPPORTED-FEATURES.md`
- **Cursor adapter — transform.sh specification** (documentation): Cursor adapter — transform.sh specification Evidence: `adapters/cursor/transform-spec.md`
- **Gemini CLI — supported features** (documentation): Detailed matrix of which CONDUCTOR features Gemini CLI supports. Evidence: `adapters/gemini/SUPPORTED-FEATURES.md`
- **Gemini CLI adapter — transform.sh specification** (documentation): Gemini CLI adapter — transform.sh specification Evidence: `adapters/gemini/transform-spec.md`
- **Windsurf — supported features** (documentation): Detailed matrix of which CONDUCTOR features Windsurf supports. Evidence: `adapters/windsurf/SUPPORTED-FEATURES.md`
- **Windsurf adapter — transform.sh specification** (documentation): Windsurf adapter — transform.sh specification Evidence: `adapters/windsurf/transform-spec.md`
- **CURRENT WORK —** (documentation): What this is : session continuity log. Updated EVERY session. Read FIRST every session start. Lean ~150 lines . When it grows past, archive older sessions to docs/sessions/ .md . Evidence: `examples/sample-claude-project/docs/CURRENT_WORK.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: `README.md`, `adapters/README.md`, `core/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`, `adapters/README.md`, `core/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.

- **Project Overview & Three-Layer Architecture**: importance `high`
  - source_paths: README.md, VISION.md, ROADMAP.md, CHANGELOG.md, docs/ARCHITECTURE.md
- **Adapter System & Per-Tool Coverage Matrix**: importance `high`
  - source_paths: adapters/README.md, adapters/claude/transform.sh, adapters/claude/transform-spec.md, adapters/claude/metadata.json, adapters/claude/SUPPORTED-FEATURES.md
- **CLI Commands, Install Modes, Model Routing & Doctor**: importance `high`
  - source_paths: bin/omniconductor.js, bin/model-routing.js, bin/doctor.js, bin/claude-hookify.js, bin/path-safety.js
- **Recipes, Hooks, Reflector & Anti-Drift Tooling**: importance `high`
  - source_paths: core/recipes/README.md, core/universal-rules/README.md, core/hooks/README.md, core/reflector/README.md, core/anti-patterns/README.md

## Repo Inspection Evidence

- repo_clone_verified: true
- repo_inspection_verified: true
- repo_commit: `5f558c8c97d98fbf8b516f9306f0b4abf658ee5d`
- inspected_files: `README.md`, `package.json`, `docs/ADAPTER-LIVE-VERIFICATION.md`, `docs/ARCHITECTURE.md`, `docs/COMPARISON.md`, `docs/COMPATIBILITY-MATRIX.md`, `docs/CONTEXT-EDITING-GUIDE.md`, `docs/CONTRIBUTING.md`, `docs/DESIGN-DECISIONS.md`, `docs/HOW-IT-WORKS-PER-TOOL.md`, `docs/IDE-COMPATIBILITY-NOTES.md`, `docs/IDE-SMOKE-TESTING.md`, `docs/INDEX.md`, `docs/MANUAL-INSTALL.md`, `docs/MIGRATION.md`, `docs/MODEL-ROUTING.md`, `docs/PHILOSOPHY.md`, `docs/PROMPT-CACHING-GUIDE.md`, `docs/PUBLICATION-POLICY.md`, `docs/PUBLISH-GUIDE.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/lee77840/omniconductor
- 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/lee77840/omniconductor
- 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/lee77840/omniconductor
- 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/lee77840/omniconductor
- 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/lee77840/omniconductor
- Hard boundary: Do not present this pitfall as solved, verified, or ignorable unless later evidence explicitly closes it.