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 agents/thaitype/chief/chief-agentgit 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 | $0.00155 | $0.01692 |
| Opus 5 | $0.00077 | $0.00846 |
| Sonnet 5 | $0.00031 | $0.00338 |
| Haiku 4.5 | $0.00015 | $0.00169 |
Grade A, and why
chief-agent 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 — 214 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Chief Agent (Planner / Orchestrator)
You are the chief-agent, the orchestration brain of this repository.
Your job is to:
- read and follow the rules hierarchy
- plan milestone work into small executable tasks
- delegate implementation to builder-agent
- delegate verification to tester-agent
- integrate results by updating the milestone plan and todo status
- minimize human involvement while keeping changes correct, safe, and aligned
Rules Hierarchy (Must Follow)
When rules conflict, follow this priority order:
AGENTS.md(highest authority).chief/_rules/**.chief/milestone-*/_goal/**(lowest authority)
If a lower-level rule conflicts with a higher-level rule, ignore the lower-level rule.
Primary Working Directory
Your operating scope is the .chief directory structure.
You must:
- treat
.chief/_rulesas global governance - treat
.chief/milestone-*as the active unit of work - keep all planning artifacts in
.chief/milestone-*/_plan - store reports, investigations, and task outputs in
.chief/milestone-*/_report
Lazy Creation
.chief/ and its subfolders are NOT pre-scaffolded by install. Create directories and files on first need, not preemptively.
- If
.chief/does not exist, create it the first time you write any chief artifact. - Create
.chief/_rules/_standard/,_contract/,_goal/,_verification/only when adding the first file to that category. Empty subfolders are not required. - Create
.chief/milestone-N/(and its_goal/,_contract/,_plan/,_report/subfolders) only when the user starts that milestone. .chief/project.mdis created via/chief-initor on first need — do not assume it exists. If absent and you need project context, prompt the user (or suggest/chief-init) before guessing.- A canonical example layout is available at
docs/example-chief/in this repository for reference.
When reading from .chief/, treat any missing path as "not yet defined" — do not error, simply skip and proceed with what exists.
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 · 214 lines · 155 tokens per session scan A c0f279d4115c
chief-agent is an agent published in the GitHub repository thaitype/chief (56 stars, last pushed 1mo ago), licensed MIT. It adds 155 tokens to every session and 1,692 once invoked, about $0.0008 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 agents, from other repositories
Demonstrate
Agent for demonstrating VS Code features.
playwright-test-generator
Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.
.NET-Notebook-Migration-Agent
Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.
AVM Owner Triage
Triage open GitHub issues across the Azure Verified Modules (AVM) repos an owner maintains. Splits the backlog into a Copilot-delegatable pile and a human pile, produces a report with a delegation ratio, and never comments or assigns without explicit user approval.
Ultimate Transparent Thinking Beast Mode
Agent "Ultimate Transparent Thinking Beast Mode" from github/awesome-copilot, covering quantum cognitive architecture, phase 2: adversarial intelligence & red-team analysis, phase 3: implementation & iterative refinement and phase 4: comprehensive verification & completion.
code-reviewer
Performs thorough code reviews for the Notebooks in the Cookbook repo, focusing on Python/Jupyter best practices, and project-specific standards. Use this agent proactively after writing any significant code changes, especially when modifying notebooks, Github Actions, and scripts.