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/himraven/codex-chief-engineer/chief-engineernpx skills add himraven/codex-chief-engineer --skill chief-engineergit clone --depth 1 https://github.com/himraven/codex-chief-engineerWrote 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/himraven/codex-chief-engineer/chief-engineer)<a href="https://agentmods.dev/skills/himraven/codex-chief-engineer/chief-engineer"><img src="https://agentmods.dev/badge/skills/himraven/codex-chief-engineer/chief-engineer.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 | $0.00100 | $0.02756 |
| Opus 5 | $0.00050 | $0.01378 |
| Sonnet 5 | $0.00020 | $0.00551 |
| Haiku 4.5 | $0.00010 | $0.00276 |
Grade A, and why
chief-engineer 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 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.
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 — 247 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Chief Engineer
Manifesto
Sol is the architect, not the execution pool. Its output is design, decomposition, routing, and convergence—not every line of execution.
- Do not spend chief context on routine execution.
- Do not outsource architecture, contracts, red-line judgment, or acceptance.
- Cut cost through less context replication and right-sized executors, never a weaker correctness gate.
- Treat worker output as untrusted until its evidence is reproduced.
- Never dispatch Sol as a worker. Use same-model children only for justified isolation or latency.
Sol holds decisions, not history. Persist decisions, contracts, and evidence before a phase expires.
1. Establish reality and design
- Inspect actual files, Git state, logs, runtime behavior, and current documentation before accepting the premise.
- Select the specialist skill before selecting the executor.
- If the task is linear, do not invent phases or persistent workstreams.
- Keep framing, architecture, contracts, ownership, state transitions, risk, topology, and acceptance criteria in the chief phase.
- Use read-only scouts for bounded evidence gathering. Never delegate the decision that the evidence must support.
2. Model the lifecycle
Use three levels:
- Objective — one durable outcome and one existing, user-approved
chief-statefor decisions, contracts, phase status, evidence, and next actions. Do not create a new state system. - Phase — one active chief decision context. Persist a handoff before replacement.
- Workstream — one bounded ownership lane. Keep it persistent only for repeated exchanges or long-running state; otherwise use an ephemeral worker.
Use one chief context for small work, one or two sequential phases for medium work, and two to four for genuinely large work. Treat these as ranges.
Roll over at a natural research→implementation, implementation→integration, or module boundary. Elsewhere require lost facts, contradictory decisions, or repeated rereading. Compaction and high context are telemetry, not sufficient rollover reasons.
What ships with it
7 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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 · 247 lines · 100 tokens per session scan A 9390ebe56906
chief-engineer is a skill published in the GitHub repository himraven/codex-chief-engineer (5 stars, last pushed 1mo ago), licensed MIT. It adds 100 tokens to every session and 2,756 once invoked, about $0.0005 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 2026-08-31.
Other skills, from other repositories
feishu
Work with Feishu or Lark bots, docs, sheets, bitables, approval flows, and OpenAPI/MCP setup without hardcoding credentials.
interview
Ask one useful structured question at a time only when material product/implementation choices are genuinely missing; remember answers and produce a brief/spec. Discoverable facts should be investigated instead of asked.
local-frontend-check
Smoke-test or verify UI behaviour on the local Jarvis Registry frontend running at http://localhost/gateway. Use for manual regression checks, bug-fix verification, and end-to-end confirmation of specific flows without running the automated test suite.
ppt-review
Read this skill only after current officereview structural output and relevant rendered images exist. Do not use source code, a tool success flag, or the first-slide preview as a substitute for deck evidence.
agy-delegate
Delegate a coding task to the Google Antigravity CLI (agy) as a background implementer, then review its diff and land it yourself. Use this whenever the user wants to hand implementation work to Antigravity or agy - phrasings like "have Antigravity do X", "delegate this to agy", "run it through agy", or "use…
helmor-debug-operate
Operate, reproduce, and debug a running local Helmor desktop development build through the Tauri MCP bridge. Use when the user asks to use Tauri MCP, towery MCP, the local dev build, the Tauri webview, visual end-to-end validation, UI automation, screenshots, DOM/accessibility snapshots, IPC or log tracing…