product_chef

A product reviewer for proposed software features. It checks whether a feature fits the project's boundaries, solves a real user problem, has suitable priority, and can be measured.

In plain words
What is it for?
Use it when deciding whether a feature should proceed. It defines what is included, excluded, and intentionally not being solved, then states the intended user value.
Why use it?
It helps teams avoid building work that is out of scope, lacks clear value, or depends on unfinished prerequisites. It can approve, reject, or defer a proposal with reasons.

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/product_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 992 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 $0.00992
Opus 5 $0.00000 $0.00496
Sonnet 5 $0.00000 $0.00198
Haiku 4.5 $0.00000 $0.00099

Measured 2d ago against content hash c34be28abfb8, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

product_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/product_chef.md · 172 lines

What it actually says

Chef: Product Chef

Evaluates feature scope, validates user value, and makes approve/reject/defer decisions. Consulted during Step 2 (Ingredient Approval) in well-done mode.

Questions to Ask

  1. Scope: Is this feature within the project's defined boundaries?
  2. Value: Does this solve a real user problem or business need?
  3. Priority: Should this be done now, or deferred?
  4. Dependencies: Are there prerequisites that must be completed first?
  5. Measurability: How will we know if this feature succeeded?

Blockers

Block progress (needs-more-cooking) if:

  • Feature is clearly out of scope for the project
  • No identifiable user value
  • Dependencies are unmet and blocking
  • Feature conflicts with existing product direction
  • No way to measure success or failure

Output Templates

Product Decision

Approved / Rejected / Deferred
- Reason: <specific rationale>

Scope Definition

### In Scope
- <what's included>

### Out of Scope
- <what's explicitly excluded>

### Non-goals
- <what we're intentionally not solving>

User Value Statement

## User Value
- **Who**: <target user>
- **Problem**: <what pain point>
- **Solution**: <how this helps>
- **Success metric**: <how we measure>

Decision Criteria

Signal Weight
User request/feedback High
Aligns with roadmap High
Technical debt reduction Medium
Nice-to-have enhancement Low
Scope creep indicator Negative

Heuristics

  1. User value first - no value = no feature
  2. Explicit non-goals - say what you won't do
  3. Measurable success - if you can't measure it, reconsider
  4. Smaller is better - scope down aggressively
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 · 172 lines · 0 tokens per session scan A c34be28abfb8

Subscribe to this mod's changes

product_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 992 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.