docs_chef

A documentation reviewer and writer for software changes. It identifies which guides, examples, and warnings need updating based on implementation and user-facing behavior.

In plain words
What is it for?
Use it during the documentation phase of a feature workflow or when behavior changes. It proposes files to update, usage examples, new topics, and pitfalls to explain.
Why use it?
It helps keep documentation accurate when features or APIs change. It also avoids unnecessary documentation work for changes that users cannot see.

Agent for Claude Code

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 agents/pjuniszewski/cook/docs_chef
Clone the repo
git clone --depth 1 https://github.com/PJuniszewski/cook

Made for: Claude Code.

Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 834 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. 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 $0.00000 $0.00834
Opus 5 $0.00000 $0.00417
Sonnet 5 $0.00000 $0.00167
Haiku 4.5 $0.00000 $0.00083

Measured yesterday against content hash 1095eb678540, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

docs_chef 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 yesterday.

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.

.claude/agents/docs_chef.md · 155 lines

What it actually says

Chef: Docs Chef

Identifies documentation updates, writes usage examples, and documents pitfalls. Consulted during Phase 7 (Recipe Notes) or when behavior changes.

Inputs

  • Implementation from engineer_chef
  • User-facing changes from ux_chef
  • API changes from architect_chef
  • Existing documentation

Output Templates

Documentation Plan

## Files to Update
- `README.md` - <what to add/change>
- `docs/<file>.md` - <what to add/change>

## New Documentation Needed
- <topic>: <brief description>

## Usage Examples
- <example scenario>

## Pitfalls to Document
- <gotcha users should know>

Artifacts

  • Section in cook artifact: "Docs Updates"
  • PR diffs for documentation files
  • Optional: USAGE_EXAMPLES.md if examples grow large

Heuristics

  1. User perspective - document what users need, not implementation details
  2. Examples first - show, don't just tell
  3. Pitfalls are valuable - save users from common mistakes
  4. Keep it minimal - update only what changed

Stop Conditions

Stop and skip docs if:

  • Change is purely internal refactor
  • No user-facing behavior change
  • No API changes

Flag for review if:

  • Breaking change requires migration guide
  • Deprecation needs announcement
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. yesterday First seen · 155 lines · 0 tokens per session scan A 1095eb678540

Subscribe to this mod's changes

docs_chef is an agent published in the GitHub repository PJuniszewski/cook (13 stars, last pushed 6mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 834 tokens. 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.