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 skills add tomascupr/sous-chef --skill refiregit clone --depth 1 https://github.com/tomascupr/sous-chefWrote 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/tomascupr/sous-chef/refire)<a href="https://agentmods.dev/skills/tomascupr/sous-chef/refire"><img src="https://agentmods.dev/badge/skills/tomascupr/sous-chef/refire.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 5.1 | $0.00071 | $0.01330 |
| Opus 5 | $0.00036 | $0.00665 |
| Sonnet 5 | $0.00014 | $0.00266 |
| Haiku 4.5 | $0.00007 | $0.00133 |
Grade A, and why
refire scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 7d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 96 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Refire - the plate failed the pass, send it back
A refire is a fix run whose spec already exists on disk: the findings.md a taste
wrote after validating every finding. That is what makes the ticket unusually
precise - file, line, failure scenario, prescribed fix, all confirmed against the
code. Your job is to carry that precision through and then prove each finding is
actually gone.
Inputs
- Default: the
findings.mdthe most recent/sous-chef:tastewrote - its report names the path; inside/sous-chef:serveit is thefindings:line in the run'sstate.md. (Lost the path? It's the newestfindings.mdunder$SCRATCHPAD.) - Alternative: a review the user pastes or points to. Validate unfamiliar findings against the code first (taste's step 3); never refire a finding you have not confirmed yourself.
- No findings available? Say so and stop. Refire without a review is just a fire.
Preflight
Same as fire, and for the same reasons:
- Git repo with at least one commit (
git rev-parse HEAD). - The resolved worker's route preflight - resolve the worker (a leading
--with <worker>or, inside a serve, state.md'sworker:line; default Codex), then run that route's preflight from fire's--withtable. Default route:test -f ~/.codex/sous-chef.config.toml; missing means stop and offer/sous-chef:mise(Codex silently ignores a missing profile). - Mint a fresh job dir:
JOB=$(mktemp -d "$SCRATCHPAD/refire-XXXXXX")($SCRATCHPADis your session scratchpad directory; substitute its absolute path). - Snapshot the tree: save
git diffandgit status --shortinto$JOBas the baseline. The tree is usually dirty here (it holds the diff that was just tasted); that is expected; the baseline is what separates the tasted diff from the refire's changes. Then fire's step 5 verbatim -.sous-chef/into$(git rev-parse --git-path info/exclude)plus the notebook's run marker - the refire ticket carries the same<progress>block, so the worker will write.sous-chef/progress.mdhere too. - Anchor check: recompute
$(git rev-parse --short HEAD)+$(idx=$(mktemp -u); GIT_INDEX_FILE=$idx git add -A && GIT_INDEX_FILE=$idx git write-tree | cut -c1-12)and compare it to thetree:line in the findings' header. On mismatch - or notree:line at all - the tree has moved since the taste and the cited line numbers may have drifted: say so, then treat the file as an unvalidated review (the Inputs rule above) - revalidate each finding at its cited location before writing the ticket, dropping any that no longer hold.
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.
- 7d ago First seen · 96 lines · 71 tokens per session scan A 2bec1abb7bb0
refire is a skill published in the GitHub repository tomascupr/sous-chef (76 stars, last pushed 1mo ago), licensed MIT. It adds 71 tokens to every session and 1,330 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 skills, from other repositories
trace
Use when encountering bugs, test failures, runtime errors, broken builds, or "this doesn't work" reports. Systematic root-cause analysis before any patch — never blind-patches symptoms. Standalone, ends with a final-integration review of the fix. Trigger with /hyperflow:trace, "debug this", "find the root cause", "why…
issue
Use when starting a chain from a GitHub issue — turning an issue URL or number into a triaged, planned, dispatched, and reviewed pull request. Classifies the thread (bug → root-cause discipline, feature → plan chain, question → drafted reply), synthesizes a spec from the issue's own acceptance criteria, then runs the…
skeptical-triage
Reusable 3-round self-challenge + arbiter pattern for filtering false positives from findings/verdicts. Use when the cost of a false-positive gate block exceeds the cost of 4 extra LLM turns.
anti-patterns
Catalogue of known SDLC anti-patterns that greatcto agents must actively reject when reviewing architecture, plans, code, or post-mortems. Used by architect (pre-impl), pm (planning), senior-dev (impl), l3-support (post-incident).
review-all
Multi-agent code review for diffs (project-agnostic). Covers standards, bugs, security, DRY, smells, perf, tests, API contracts, a11y/i18n. Verifies each finding to eliminate false positives. Use for /review-all, pre-PR/pre-commit review, or auditing uncommitted/staged changes.
observability-baseline
Scaffold-time observability so a shipped product is not blind in prod from day one — error capture (Sentry), request-id structured logging, and /healthz + /readyz endpoints. stack-baseline pins Sentry but nothing wires it; this is the wiring. Loaded by app-scaffolder (bake into the scaffold), infra-provisioner (prod…