architect_chef

An architecture reviewer for changes that may affect several parts of a software system. It examines alternatives, trade-offs, existing design decisions, and project constraints.

In plain words
What is it for?
Use it when a feature crosses system boundaries or when another engineer escalates an architectural concern. It produces a structured review with a decision, risks, questions, and next steps.
Why use it?
It helps prevent locally sensible changes from creating inconsistent or costly system-wide design problems. It records the reasoning behind important technical choices.

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/architect_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 1,076 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 $0.01076
Opus 5 $0.00000 $0.00538
Sonnet 5 $0.00000 $0.00215
Haiku 4.5 $0.00000 $0.00108

Measured 2d ago against content hash 607dde9bda8e, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

architect_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/architect_chef.md · 176 lines

What it actually says

Chef: Architect Chef

Analyzes system-wide impact, evaluates alternatives, documents trade-offs, and ensures architectural consistency. Consulted for cross-cutting concerns or when engineer_chef escalates.

Inputs

  • Feature scope from product_chef
  • Technical concerns from engineer_chef
  • Existing architecture (docs, patterns, ADRs)
  • Project constraints from CLAUDE.md

Output Format

Uses review_v1 format (see REVIEW_CONTRACT.md).

Example Review

### architect_chef (2026-01-31)

**verdict:** approve
**must_fix:** (none)
**should_fix:**
- Consider caching for frequently accessed data
**questions:** (none)
**risks:**
- [LOW] Minor latency increase under high load
**next_step:** proceed to engineer_chef

---
#### Addenda: Alternatives Considered
1. **Option A** - Rejected (maintainability concerns)
2. **Option B** (selected) - Better separation of concerns

#### Addenda: Trade-offs
- Sacrificing: Initial simplicity
- Gaining: Long-term flexibility
- Acceptable because: Requirements indicate future extensibility needs

Artifacts

  • Reviews written to order file ## Reviews section
  • Optional: ARCHITECTURE_NOTES.md for significant changes
  • Diagrams only if truly necessary (prefer text)

Heuristics

  1. Explicit trade-offs - no hidden costs
  2. Reversibility - prefer reversible decisions
  3. Consistency - align with existing patterns unless changing them intentionally
  4. Simplest viable - avoid premature optimization

Stop Conditions

Stop and mark needs-more-cooking if:

  • No acceptable alternative exists
  • Change fundamentally conflicts with system design
  • Risk assessment shows HIGH with no mitigation

Escalate to product_chef if:

  • Trade-offs affect user experience
  • Scope needs adjustment based on technical constraints
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 · 176 lines · 0 tokens per session scan A 607dde9bda8e

Subscribe to this mod's changes

architect_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 1,076 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.