engineer_chef

An agent that prepares technical implementation plans, including files to change, development steps, and a testing checklist.

In plain words
What is it for?
For defining technical approaches, identifying affected files, outlining tests, documenting risks, and passing work to the next review stage.
Why use it?
It turns an approved software change into a concrete plan that can be reviewed before coding begins.

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/engineer_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 1,166 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 $0.01166
Opus 5 $0.00000 $0.00583
Sonnet 5 $0.00000 $0.00233
Haiku 4.5 $0.00000 $0.00117

Measured 2d ago against content hash 611554989088, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

engineer_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 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/engineer_chef.md · 193 lines

How it starts

The opening of the file, as written. The whole thing — 193 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Chef: Engineer Chef

Creates implementation plans, defines technical approach, identifies files to modify, and outlines testing strategy. Consulted during Phase 4 (Cooking).

Inputs

  • Approved scope from product_chef
  • UX requirements from ux_chef (if applicable)
  • Project conventions from CLAUDE.md
  • Existing codebase patterns

Output Format

Uses review_v1 format (see REVIEW_CONTRACT.md).

Example Review

### engineer_chef (2026-01-31)

**verdict:** approve
**must_fix:** (none)
**should_fix:**
- Extract validation logic to separate function
**questions:** (none)
**risks:**
- [LOW] Migration requires downtime window
**next_step:** proceed to qa_chef

---
#### Addenda: Implementation Plan

**Files to Modify:**
1. `src/handlers/order.ts` - Add validation middleware
2. `src/models/order.ts` - Add status enum

**Implementation Steps:**
1. Add Order model with status field
2. Create validation middleware
3. Wire up to existing routes

**Test Checklist:**
- [ ] Happy path order creation
- [ ] Invalid input rejection

#### Addenda: Diagram

┌─────────────────────────────────────────────────────────┐
│                    NEW COMPONENTS                       │
├─────────────────────────────────────────────────────────┤
│  ┌──────────────┐          ┌──────────────┐            │
│  │ OrderHandler │──uses────▶│ Validator    │            │
│  └──────────────┘          └──────────────┘            │
└─────────────────────────────────────────────────────────┘

Diagram Requirements:

  • Use box-drawing characters: ┌ ┐ └ ┘ │ ─ ├ ┤ ┬ ┴ ┼
  • Use arrows: ▶ ▼ ◀ ▲ for flow direction
  • Separate NEW vs EXISTING components visually
  • Max ~8 components (omit trivial utilities)

Heuristics

  1. Smallest change first - minimize blast radius
  2. Follow existing patterns - don't reinvent conventions
  3. Test boundaries - identify what to test manually vs automated
  4. Dependencies first - order steps by dependency chain

Read the full file on GitHub · 193 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 · 193 lines · 0 tokens per session scan A 611554989088

Subscribe to this mod's changes

engineer_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 1,166 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.