Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx agentmods add skills/thaitype/chief/chief-initnpx skills add thaitype/chief --skill chief-initgit clone --depth 1 https://github.com/thaitype/chiefWhat it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5 | $0.00081 | $0.00890 |
| Opus 5 | $0.00041 | $0.00445 |
| Sonnet 5 | $0.00016 | $0.00178 |
| Haiku 4.5 | $0.00008 | $0.00089 |
Grade A, and why
chief-init scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 83 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are bootstrapping the project's .chief/project.md. This is the only thing this skill creates. Milestones, rules, and other .chief/ content are created later by chief-agent on first need.
Steps
1. Pre-flight checks
- Verify the framework is installed:
.agents/agents/chief-agent.mdmust exist. If missing, tell the user to run/chief-installfirst and stop. - Check if
.chief/project.mdalready exists.- If yes → ask the user: "
.chief/project.mdalready exists. Update it / overwrite / cancel?" - If overwrite, back up the current file to
.chief/project.md.bakbefore proceeding. - If update, read the current content first and treat the interview as a refinement pass.
- If cancel, stop.
- If yes → ask the user: "
- Create
.chief/if it does not exist.
2. Interview the user
Walk through these topics, one short question at a time. Keep questions focused. Wait for the answer before moving on. Skip a topic if the user says "skip" or "n/a".
- Project name and one-line summary.
- Tech stack — primary languages, frameworks, runtimes, databases, key libraries.
- Dev commands — how to install deps, run dev, run tests, lint, typecheck, build.
- Architecture overview — main patterns (e.g. Repository Pattern, Service Layer, hexagonal, monorepo, etc.).
- Directory structure — top-level folders and what they hold.
- Important development rules — conventions developers must follow (commit style, branch policy, formatting, testing requirements, etc.).
If the user is unsure about a topic, suggest reasonable defaults derived from files you can see in the repo (package.json, pyproject.toml, Cargo.toml, Makefile, README.md, etc.) and confirm.
3. Show a draft and confirm
Print the proposed .chief/project.md content as formatted markdown. Then ask once: "Write this to .chief/project.md?"
If the user requests changes, apply them and re-confirm. Do not loop more than three rounds — if alignment is hard, write the current draft and tell the user they can edit manually.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 2d ago First seen · 83 lines · 81 tokens per session scan A 869657783031
chief-init is a skill published in the GitHub repository thaitype/chief (56 stars, last pushed 1mo ago), licensed MIT. It adds 81 tokens to every session and 890 once invoked, about $0.0004 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
brainstorming
You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.
auto-perf-optimize
Run agent-driven VS Code performance or memory investigations. Use when asked to launch Code OSS, automate a VS Code scenario, run the Chat memory smoke runner, capture renderer heap snapshots, take workflow screenshots, compare run summaries, or drive a repeatable scenario before heap-snapshot analysis.
chat-perf
Run chat perf benchmarks and memory leak checks against the local dev build or any published VS Code version. Use when investigating chat rendering regressions, validating perf-sensitive changes to chat UI, or checking for memory leaks in the chat response pipeline.
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…