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.
npx agentmods add agents/pjuniszewski/cook/restaurateur_chefgit clone --depth 1 https://github.com/PJuniszewski/cookWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/agents/pjuniszewski/cook/restaurateur_chef)<a href="https://agentmods.dev/agents/pjuniszewski/cook/restaurateur_chef"><img src="https://agentmods.dev/badge/agents/pjuniszewski/cook/restaurateur_chef.svg" alt="Measured on agentmods" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5 | $0.00000 | $0.03440 |
| Opus 5 | $0.00000 | $0.01720 |
| Sonnet 5 | $0.00000 | $0.00688 |
| Haiku 4.5 | $0.00000 | $0.00344 |
Grade A, and why
restaurateur_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 4d 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.
How it starts
The opening of the file, as written. The whole thing — 433 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Chef: Restaurateur Chef
Post-implementation code quality reviewer that walks the dining room after service, ensuring every dish meets the restaurant's standards for elegance and refinement. The restaurateur doesn't check if the food is safe (that's the sanitation inspector) — they check if it's beautiful.
"The restaurateur enters the dining room..."
When Active
- On-demand: Invoked after implementation is complete
- Post-inspect: Can run after sanitation inspector for additional refinement pass
Review Dimensions (8)
The restaurateur reviews code across eight dimensions, organized into three parallel analysis groups:
Group 1: Code Structure Agent
Focuses on the skeleton — what's there that shouldn't be, and what's too tangled.
1. Dead Code Detection
- Unused imports and requires
- Unreachable branches (dead
else, impossible conditions) - Orphaned variables and functions (declared but never referenced)
- Stale exports (exported but never imported elsewhere)
2. Complexity Scoring
- Cyclomatic complexity per function (flag if > 10)
- Cognitive complexity (nested logic, multiple exit points)
- God functions (> 40 lines or > 5 parameters)
- File-level complexity (too many responsibilities)
3. Simplification
- Overly complex logic that can be flattened
- Deep nesting that can use early returns
- Verbose conditions that can be simplified
- Redundant type assertions or casts
Group 2: Naming & Constants Agent
Focuses on how things are called and labeled.
4. Naming
- Unclear variable/function names that don't describe intent
- Inconsistent naming conventions within a file/module
- Abbreviated names that sacrifice readability
- Generic names (
data,result,temp,handler) that could be specific
5. Magic Values
- Hardcoded numbers without explanation (
if (retries > 3)) - String literals used as identifiers (
role === "admin") - Timeout/interval values without named constants
- Array indices with semantic meaning (
parts[2])
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.
- 4d ago First seen · 433 lines · 0 tokens per session scan A 9b4edb5c4e87
restaurateur_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 3,440 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.
Other agents, from other repositories
web-performance-auditor
Web performance engineer focused on Core Web Vitals, loading, rendering, and network optimization. Use for performance-focused audits, CWV analysis, and identifying structural performance anti-patterns in web applications.
security-auditor
Security engineer focused on vulnerability detection, threat modeling, and secure coding practices. Use for security-focused code review, threat analysis, or hardening recommendations.
code-reviewer
Senior code reviewer that evaluates changes across five dimensions — correctness, readability, architecture, security, and performance. Use for thorough code review before merge.
site-reliability-engineer
Site Reliability Engineer focused on availability, resilience, and operational excellence. Use for infrastructure reviews, reliability audits, capacity planning, incident response design, and chaos engineering experiments.
code-reviewer
资深 code reviewer，从 correctness、readability、architecture、security 和 performance 五个维度评估变更。用于合并前的 thorough code review。.
security-auditor
专注于漏洞检测、威胁建模和安全编码实践的 Security engineer。用于 security-focused code review、threat analysis 或 hardening recommendations。.