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-installnpx skills add thaitype/chief --skill chief-installgit clone --depth 1 https://github.com/thaitype/chiefWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/thaitype/chief/chief-install)<a href="https://agentmods.dev/skills/thaitype/chief/chief-install"><img src="https://agentmods.dev/badge/skills/thaitype/chief/chief-install.svg" alt="Measured on agentmods" height="20"></a>What 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 | $0.00061 | $0.02080 |
| Opus 5 | $0.00030 | $0.01040 |
| Sonnet 5 | $0.00012 | $0.00416 |
| Haiku 4.5 | $0.00006 | $0.00208 |
Grade C, and why
chief-install scanned grade C with 1 finding 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 4d 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.
Recursive force deletehighDestructive command
rm -rf with a variable or a broad path is one typo away from removing the wrong tree.
If the setup script **fails completely** (non-zero exit code or crashes), skip to step 3b for full manual install. Do NOT run `rm -rf .chief-agent-tmp` yet — it's needed for manual steps. How it starts
The opening of the file, as written. The whole thing — 196 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Install the Chief framework into the current project.
This is a lazy install: only subagents and AGENTS.md are placed at install time. .chief/ (project.md, milestones, rules) is created on demand by chief-agent — run /chief-init to bootstrap project context, or just start with /chief-plan.
Arguments
The first argument is the target version (branch or tag). Optional.
- No argument → install the latest stable release (highest semver tag). Find it by running
git ls-remote --tags https://github.com/thaitype/chief.git, striprefs/tags/, ignore^{}entries, and pick the highest semver version. canary→ latest canary branch (active development, unreleased)v1.0.0,v2.0.0, etc. → specific tagged version
Steps
1. Check for existing installation
Check if the Chief is already installed by looking for these signals:
.agents/agents/chief-agent.mdexistsAGENTS.mdat root contains the keyword "Chief" or "chief-agent" (check file content, not just existence — these files may exist from other setups)
If any of these match → the framework is likely already installed. Warn the user and suggest upgrading instead. Show them:
npx skills@latest add thaitype/chief --skill chief-upgrade
/chief-upgrade
Do NOT proceed unless the user explicitly confirms they want a fresh install.
If none match → proceed.
2. Ask coding agent and install mode
Ask the user:
- Which coding agent? — Supported agents:
claude-code,opencode,codex,cursor,copilot,gemini-cli,amp,windsurf,kiro,aider - Install mode? (relevant for
claude-codeandcopilot)- link (recommended) — symlinks from agent-specific directory to
.agents/ - copy — copies files instead of symlinking
- On Windows, link mode requires Developer Mode enabled and
git config --global core.symlinks true. If unavailable, suggest copy mode. - For all other agents, mode does not affect behavior since they read
AGENTS.mdand.agents/directly
- link (recommended) — symlinks from agent-specific directory to
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.
- 4d ago First seen · 196 lines · 61 tokens per session scan C 88b6a89b9c2b
chief-install is a skill published in the GitHub repository thaitype/chief (56 stars, last pushed yesterday), licensed MIT. It adds 61 tokens to every session and 2,080 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it C with 1 finding (recursive force delete). 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…