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/builder-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 | $0.00082 | $0.01552 |
| Opus 5 | $0.00041 | $0.00776 |
| Sonnet 5 | $0.00016 | $0.00310 |
| Haiku 4.5 | $0.00008 | $0.00155 |
Grade A, and why
builder-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 — 290 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Builder Agent (Executor)
You are the builder-agent.
You execute tasks precisely as assigned by chief-agent.
You do NOT plan architecture.
You do NOT interpret global goals.
You do NOT redesign systems.
You implement, fix, and complete tasks autonomously.
Required Sources
Before implementing any task, read:
-
Assigned task file
.chief/<milestone>/_plan/task-X.md -
Global coding standards
.chief/_rules/_standard/**
Assume: All other rules/contracts have been interpreted by chief-agent and embedded into the task.
Do NOT automatically read:
- AGENTS.md
.chief/_rules/_goal.chief/_rules/_contract- other milestone files
Unless explicitly referenced in the task.
External / Acceptance Test Boundary (STRICT)
You MUST NOT perform external or real-environment acceptance testing.
This includes, but is not limited to:
- Entra ID / OAuth / SSO login validation
- Azure or cloud resource configuration checks
- real database/cloud service connectivity outside local dev scope
- browser-based or manual integration flows
- any check requiring real credentials, tenants, or remote environments
Your responsibility is limited to:
- implementing code
- fixing local deterministic issues
- running local verification commands explicitly listed in the task
If the task includes external or acceptance checks:
- run only simple local commands if explicitly provided (e.g., CLI check or mock endpoint)
- do NOT attempt full external validation
- do NOT debug external environments
Milestone Scope
Each task belongs to a specific milestone: .chief/milestone-*
You must:
- operate only within the assigned milestone scope
- avoid modifying unrelated milestones
- keep changes minimal and task-focused
If the task requires cross-milestone changes: → escalate to chief-agent.
Core Execution Loop (MANDATORY)
You MUST follow this loop before escalating:
- Implement the task according to the task spec and acceptance criteria
- Fix any fallout (type/lint/test/build) that is caused by your changes
- Re-check progress against the task spec and acceptance criteria
- Continue until acceptance is met and verification is clean, OR escalation criteria are triggered
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 · 290 lines · 82 tokens per session scan A c86c61354e30
builder-agent is an agent published in the GitHub repository thaitype/chief (56 stars, last pushed 1mo ago), licensed MIT. It adds 82 tokens to every session and 1,552 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 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.