README

A reference guide describing specialized reviewers, called agents or chefs, used in a feature-development workflow. Each reviewer covers an area such as product scope, architecture, testing, security, documentation, or release work.

In plain words
What is it for?
Use it when configuring or understanding the workflow's review agents. It helps map development phases to reviewers and explains their expected review format.
Why use it?
It clarifies which reviewer handles each development stage and what structured output they should provide. This makes reviews more consistent across a project.

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/readme
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 763 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 $0.00763
Opus 5 $0.00000 $0.00381
Sonnet 5 $0.00000 $0.00153
Haiku 4.5 $0.00000 $0.00076

Measured 2d ago against content hash ad10e34b3a4a, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

README 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 2d 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.

.claude/agents/README.md · 110 lines

How it starts

The opening of the file, as written. The whole thing — 110 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Agents (Chefs)

Agents are specialized reviewers that evaluate different aspects of a feature during the /juni:cook workflow. Each agent (or "chef") has a specific role and provides structured output using the review_v1 format.

How Agents Work

During cooking, Claude Code consults different agents based on their phase_affinity:

Phase Agent Purpose
scope product_chef Validates feature scope and value
ux ux_chef Reviews user experience impact
plan architect_chef Evaluates alternatives and trade-offs
plan engineer_chef Creates implementation plan
test qa_chef Defines test strategy
security security_chef Audits security implications
docs docs_chef Identifies documentation updates
release release_chef Manages versioning and changelog
inspect sanitation_inspector_chef Post-implementation review
refine restaurateur_chef Code refinement, optimization, naming, dead code, complexity
monitor sous_chef Background monitoring

Output Contract

All agents output reviews in review_v1 format (see REVIEW_CONTRACT.md):

output_contract:
  format: review_v1
  required_sections:
    - verdict
    - must_fix
    - should_fix
    - questions
    - risks
    - next_step

Agent Resolution Order

  1. Project-specific agents in <project>/.claude/agents/
  2. System-wide agents in ~/.claude/agents/

Project agents override system defaults, allowing you to customize reviews for your specific codebase.

Creating Custom Agents

Create a new .md file in .claude/agents/ with YAML frontmatter:

---
chef_id: my_chef
version: 1.0.0

phase_affinity:
  - <phase>

output_contract:
  format: review_v1
  required_sections:
    - verdict
    - must_fix
    - should_fix
    - questions
    - risks
    - next_step

traits:
  risk_posture: balanced | conservative
  quality_bar: standard | high
  speed_vs_correctness: balanced | correctness-first
  verbosity: minimal | concise | explicit

non_negotiables:
  - <rule 1>
  - <rule 2>

# ... other fields
---

# Chef: My Chef

<Description and when it's consulted>

## Output Format

Uses `review_v1` format (see REVIEW_CONTRACT.md).

## Heuristics

1. <guideline 1>
2. <guideline 2>

Read the full file on GitHub · 110 lines

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. 2d ago First seen · 110 lines · 0 tokens per session scan A ad10e34b3a4a

Subscribe to this mod's changes

README 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 763 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.