Getting it into your agent
This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.
/plugin marketplace add tomascupr/sous-chef/plugin install 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/mise)<a href="https://agentmods.dev/skills/tomascupr/sous-chef/mise"><img src="https://agentmods.dev/badge/skills/tomascupr/sous-chef/mise/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.
<a href="https://agentmods.dev/skills/tomascupr/sous-chef/mise"><img src="https://agentmods.dev/badge/skills/tomascupr/sous-chef/mise.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00079 | $0.02779 |
| Opus 5 | $0.00039 | $0.01389 |
| Sonnet 5 | $0.00016 | $0.00556 |
| Haiku 4.5 | $0.00008 | $0.00278 |
Grade D, and why
mise scanned grade D with 3 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 9d 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.
Downloads and executes remote codehighSupply chain
curl | sh runs whatever the server returns today, which is not necessarily what it returned when this was reviewed.
(`curl -fsSL https://x.ai/cli/install.sh | bash`). When present, check auth Reads agent configuration directoriesmediumAgent snooping
.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.
model and reasoning effort fall through to the user's `~/.codex/config.toml`, which Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
(`curl -fsSL https://x.ai/cli/install.sh | bash`). When present, check auth How it starts
The opening of the file, as written. The whole thing — 177 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Mise en place - set up the kitchen before service
Every other skill assumes a chain: CLI → auth → profile → repo standards → routing policy, proven by a smoke test. Mise walks that chain and makes each link true. Open with the plan so the user knows the shape: "Four checks, at most a couple of questions, one ~30s smoke test." Report each check as pass/fixed/needs-user, batch any questions into a single AskUserQuestion call rather than interrogating one at a time, and never overwrite an existing file without asking.
1. Codex CLI present and current
codex --version
- Missing → offer to install it for the user (
npm i -g @openai/codexorbrew install codex); if they decline or it fails, stop here and tell them to re-run/sous-chef:miseafter installing. - Version below 0.134.0 → warn: this plugin uses file-per-profile config
(
~/.codex/sous-chef.config.toml). Older Codex only reads[profiles.*]tables from config.toml, which 0.134+ silently ignores - ask the user to upgrade rather than shipping a config that does nothing.
2. Auth
codex login status
- Not logged in (exit 1) → tell the user to run
codex loginin a separate terminal (it's an interactive browser flow), then re-run/sous-chef:mise. Stop here - the remaining steps end in a smoke test that would fail confusingly without auth. - Logged in with ChatGPT (the normal, recommended setup - no API key needed): all good; delegated runs bill the subscription and tokens auto-refresh, even mid-run.
- Logged in with an API key instead: warn that usage bills at per-token API rates and some models available on ChatGPT plans (GPT-5.5 included) may not be available at all under API-key auth.
- Check
[ -n "$CODEX_API_KEY" ] || [ -n "$CODEX_ACCESS_TOKEN" ]: these two env vars override the login incodex exec, which is why sous-chef invocations unset them - mention it if either is set. (OPENAI_API_KEYis harmless; current Codex doesn't read it for auth.)
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.
- 9d ago First seen · 177 lines · 79 tokens per session scan D 3de768ed3490
mise is a skill published in the GitHub repository tomascupr/sous-chef (76 stars, last pushed 1mo ago), licensed MIT. It adds 79 tokens to every session and 2,779 once invoked, about $0.0004 per session on Opus 5. A static security scan graded it D with 3 findings (downloads and executes remote code, reads agent configuration directories, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
b3os-report
A team reporting skill that turns approved markdown and HTML reports into entries in an internal reports portal. HTML becomes the main view when available, while markdown remains the source and download version.
b3os-ai-code-safety
As code and logic grow, the cost is not the happy path — it is coupling: a change ripples into places you did not touch, and a "small fix" breaks something unrelated. This skill is a code-structure and refactoring guide: structure well from the initial design so a change stays local, apply operational safety where…
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.
b3os-team-inbox
A team message-bus client for sending, receiving, and recalling messages between AI teammates. It also supports replying to a specific message thread and sending final reports to the team lead.
b3os
An onboarding workflow for b3os, a local system for creating and managing a team of AI agents.
b3os-bwf
A basic workflow for carrying a team task from planning through completion. BWF means b3os workflow; it is the overall process, not a harness, which is a method for splitting work among helper agents.