ontology-atlas: Agent for Claude Code

.agents/agents/chief.md

chief is an agent for Claude Code from wlsdks/ontology-atlas. It costs 29 tokens per session (790 once invoked), scanned A, original, MIT.

A coordinating role that decides whether a product or design review is needed, chooses the relevant reviewers, manages their order, and records the decision.

In plain words
What is it for?
Use it to convene product or design reviews, select the appropriate seats, apply conflict rules, stop work after a rejected product decision, and append decisions to the project record.
Why use it?
It prevents unnecessary review meetings and separates deciding what is worth building from deciding whether it is ready to ship. It also keeps disagreements and the conditions that could disprove a decision visible to future contributors.

Agent for Claude Code

Written for Claude Code: a Claude Code subagent (agents/*.md). Also seen: model in frontmatter; installed under .agents/ (shared by several agents).

This is wlsdks/ontology-atlas's own configuration. It tells Claude Code how to work on ontology-atlas itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything ontology-atlas configures →

Reuse

Borrowing it

Nothing to install: this file belongs to wlsdks/ontology-atlas. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/wlsdks/ontology-atlas/main/.agents/agents/chief.md
Clone the repo
git clone --depth 1 https://github.com/wlsdks/ontology-atlas

Made for: Claude Code.

Wrote 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.

agentmods badge for chief

README.md
[![agentmods](https://agentmods.dev/badge/agents/wlsdks/ontology-atlas/chief/github.svg)](https://agentmods.dev/agents/wlsdks/ontology-atlas/chief)
Your own site
<a href="https://agentmods.dev/agents/wlsdks/ontology-atlas/chief"><img src="https://agentmods.dev/badge/agents/wlsdks/ontology-atlas/chief/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for chief

Your own site · 80×15
<a href="https://agentmods.dev/agents/wlsdks/ontology-atlas/chief"><img src="https://agentmods.dev/badge/agents/wlsdks/ontology-atlas/chief.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 29 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 790 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00029 $0.00790
Opus 5 $0.00015 $0.00395
Sonnet 5 $0.00006 $0.00158
Haiku 4.5 $0.00003 $0.00079

Measured 3d ago against content hash 16f58ebe42c3, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

chief 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 3d 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.

.agents/agents/chief.md · 88 lines

How it starts

The opening of the file, as written. The whole thing — 88 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Chief

Coordinate the Atlas product route and eight design seats; do not become another reviewer and do not edit code. Product and design both derive review from observable change facts.

Route first

Run pnpm po:route from the evidence state, one Atlas outcome, inspectable change signals, and all four boundary assessments. Never accept a builder-supplied door or risk; the router derives both and records its reasons.

Route Action
skip technical checks only
solo one accountable Atlas product pass
review Evidence plus the one specialist returned by the router
explicit owner exception record the extra reviewer and why the default pair was insufficient

Visual craft and journeys use their dedicated design and walkthrough gates. po-craft is an owner-requested proof audit, not a standing vote.

Run pnpm design:route for rendered product work. Use exactly its directions, selected seats, proof scopes, and sequence. A council is not the default design route; the baseline/checkpoint/final Computer Use render loop is mandatory for every rendered class, and a real macOS recording is mandatory for motion.

Coordinate selected review

  1. Read only the relevant prior decision and its falsifier.
  2. Record the pre-review decision, lost human ability, and recovery proof before convening.
  3. Give selected reviewers the same literal brief and primary evidence.
  4. Preserve independent first positions.
  5. Run one rebuttal only for material conflict or a fact-changing bounded query.
  6. Choose one recommendation or something smaller, never a union.
  7. Present the result to the human owner, who accepts or overturns it.
  8. Record the decision delta, dissent, falsifier, review footprint, unique contributor, and pilot rows. Run pnpm po:pilot to expose unresolved proof, clarity, or boundary state.

The chief adds at most two turns: the route/convening decision and the final record. Reviewer turns belong to their selected seats.

Read the full file on GitHub · 88 lines

Changes

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.

  1. 3d ago Changed · +1 lines 16f58ebe42c3
  2. 5d ago Changed · -12 lines · -9 tokens per session 45365ce042b6
  3. 9d ago First seen · 99 lines · 38 tokens per session scan A 9b95c2e8d705

Subscribe to this mod's changes

chief is an agent published in the GitHub repository wlsdks/ontology-atlas (100 stars, last pushed today), licensed MIT. It adds 29 tokens to every session and 790 once invoked, about $0.0001 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.