fire

fire is a skill for Claude Code, Codex from tomascupr/sous-chef. It costs 89 tokens per session (3,705 once invoked), scanned B, original, MIT.

A delegation workflow that gives a clearly specified coding task to Codex CLI or another supported coding model.

In plain words
What is it for?
Handing off multi-file features, refactors, migrations, boilerplate, or test scaffolding when the desired result is already clear.
Why use it?
It separates the task instructions from the conversation so another worker can implement the requested changes against checkable criteria.

Skill for Claude CodeCodex

Written for Claude Code and Codex: shipped in a Claude Code plugin, but also runs codex exec. Also seen: mentions CLAUDE.md; mentions Claude Code; mentions AGENTS.md.

Part of the sous-chef plugin — 7 skills shipped together

Install

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.

agentmods
npx agentmods add skills/tomascupr/sous-chef/fire
Any agent
npx skills add tomascupr/sous-chef --skill fire
Clone the repo
git clone --depth 1 https://github.com/tomascupr/sous-chef

Made for: Claude Code, Codex.

Or install sous-chef, the plugin that ships this one along with the rest of its 7 skills.

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 fire

README.md
[![agentmods](https://agentmods.dev/badge/skills/tomascupr/sous-chef/fire.svg)](https://agentmods.dev/skills/tomascupr/sous-chef/fire)
Your own site
<a href="https://agentmods.dev/skills/tomascupr/sous-chef/fire"><img src="https://agentmods.dev/badge/skills/tomascupr/sous-chef/fire.svg" alt="Measured on agentmods" height="20"></a>
Per session 89 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 3,705 The whole file, excluding the scripts and references it only reads on demand.
Security scan B 1 finding. Scan, not verified.
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 $0.00089 $0.03705
Opus 5 $0.00044 $0.01852
Sonnet 5 $0.00018 $0.00741
Haiku 4.5 $0.00009 $0.00370

Measured 6d ago against content hash f6ffd198b588, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade B, and why

fire scanned grade B 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 6d 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.

Reads agent configuration directoriesmediumAgent snooping

.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.

- `--profile sous-chef` loads `~/.codex/sous-chef.config.toml` (workspace-write sandbox, approvals never - it never pauses for input that will never arrive). Model and reasoning effort deliberately fall through to the us
skills/fire/SKILL.md · 138 lines

How it starts

The opening of the file, as written. The whole thing — 138 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Fire - hand the ticket to the sous-chef

You are the head chef. Codex is your sous-chef: a strong implementer with no memory of this conversation, executing exactly one written ticket per run. Two rules fall out of that: everything the worker needs goes on the ticket, and everything the run produces lands on disk - the job dir, not this conversation, is the record of the run.

When to fire vs. cook it yourself

Fire when ALL of these hold:

  • The task is implementation, not design - you already know what the end state looks like.
  • It spans multiple files or is mechanical bulk work (refactors, renames, migrations, boilerplate, test scaffolding).
  • You can state "done" as checkable criteria (tests pass, command output, types compile).

Cook it yourself when ANY of these hold:

  • One-file or few-line surgical fix - the delegation round trip costs more than doing it.
  • The approach is still ambiguous - resolve design questions first, then fire.
  • The task depends on conversation context that can't be written into a ticket.

Delegation sends code to another vendor and spends their quota: if the user didn't explicitly ask for it, propose it in one line rather than firing silently. Exception - an autonomous routing policy in the user's CLAUDE.md pre-authorizes the delegation; the one-line announcement then replaces the proposal: announce and fire.

Preflight (all deterministic, run before writing the ticket)

  1. Git repo with at least one commit - git rev-parse HEAD succeeds. Codex refuses non-repos by default, and diff review needs a baseline. If not: tell the user to git init / make an initial commit first.
  2. Profile exists - test -f ~/.codex/sous-chef.config.toml. This check is load-bearing: Codex silently ignores a missing profile (exit 0, runs under the user's own defaults - possibly no sandbox at all). If missing: stop and offer /sous-chef:mise.
  3. Job directory - mint one per fire: JOB=$(mktemp -d "$SCRATCHPAD/fire-XXXXXX") ($SCRATCHPAD = your session scratchpad directory; substitute its absolute path). Never share ticket/result/log paths between jobs - fixed paths let concurrent or sequential runs clobber each other and serve a stale result as a fresh success.
  4. Snapshot the tree - if git status --porcelain is non-empty, warn the user their uncommitted changes will share the tree with Codex's edits (suggest committing/stashing first), and either way save the baseline: git diff > "$JOB/pre-fire.patch"; git status --short > "$JOB/pre-fire.status". At plating you review Codex's delta against this baseline, not the raw diff. One honest limit: the patch carries no contents for untracked files - the status file records their paths, so if untracked WIP shared the tree, content changes inside those paths cannot be attributed patch-style; say so at plating rather than guessing.
  5. Exclude and mark the notebook - add .sous-chef/ to $(git rev-parse --git-path info/exclude) if it isn't there (the ticket tells the worker to keep a milestone notebook at .sous-chef/progress.md; unexcluded, it would pollute the diff and trip the concurrent-edit check), then append a run marker to the notebook: ## fire <UTC ISO-8601> <$JOB basename>. Ticks read only below this marker - without it, a previous run's milestones would masquerade as this one's.

Read the full file on GitHub · 138 lines

Files

What ships with it

2 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.

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. 6d ago First seen · 138 lines · 89 tokens per session scan B f6ffd198b588

Subscribe to this mod's changes

fire is a skill published in the GitHub repository tomascupr/sous-chef (76 stars, last pushed 1mo ago), licensed MIT. It adds 89 tokens to every session and 3,705 once invoked, about $0.0004 per session on Opus 5. A static security scan graded it B with 1 finding (reads agent configuration directories). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Related

Other skills, from other repositories

b3os-report

세 스킬이 보고서 작업에 붙는다. 셋 다 이 저장소에 없는 외부 스킬이고 install.sh 가 설치하지도 않는다. 설치돼 있으면 아래 자리에서 쓰고, 없으면 보고서를 쓰는 팀원이 그 자리에서 같은 일을 직접 한다 — 스킬은 절차를 묶어 둔 것이지 그 스킬만 할 수 있는 일이 아니다. 아래 "무엇을 한다" 칸이 그 절차다.

b3rys/b3rys-team-os · 100 tokens

b3os-team-inbox

Skill "b3os-team-inbox" from b3rys/b3rys-team-os, covering b3os-team-inbox, 언제 쓰는가, 자기 id 자동 감지, 사용 예 and inbox 확인.

b3rys/b3rys-team-os · 152 tokens

b3os-team-member-lifecycle

Use when adding, testing, disabling, offboarding, or archiving a b3rys team member across Claude Code channel, OpenClaw, Hermes Agent, or future runtimes.

b3rys/b3rys-team-os · 45 tokens

b3os-bwf

BWF(b3os workflow)는 harness가 아니다. b3rys 팀이 과제를 받아 끝까지 수행하는 기본 흐름이다. harness·multi-ai review·judge panel·적대적 리뷰는 이 흐름의 한 단계에서 고르는 품질방법일 뿐이다. (이 구분을 먼저 박는다 — 과거 "BWF=harness" 오해 방지.).

b3rys/b3rys-team-os · 193 tokens

b3os-scheduler

팀원이 세션과 무관하게(durable) 시각에 맞춰 발화하는 반복/예약 잡을 등록하는 절차 스킬이다. 런타임별 세션 cron(claude CronCreate, openclaw/hermes 자체 예약)은 그 세션이 죽으면 유실된다. 팀 정본 반복작업(야간 사이클·주기 리마인드·정기 점검)은 이 스케줄러에 등록해 team.db에 durable 저장하고, b3os 서버 안의 워커가 발화한다.

b3rys/b3rys-team-os · 128 tokens

b3os-task-loop

Skill "b3os-task-loop" from b3rys/b3rys-team-os, covering b3os-task-loop — 과제 완료까지 끊기지 않게 도는 작업 루프, source of truth, 핵심 원칙, 언제 쓰나 and wait/review loop — 멈춤 방지 프로토콜.

b3rys/b3rys-team-os · 0 tokens