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 commands/pjuniszewski/cook/cook-statsgit clone --depth 1 https://github.com/PJuniszewski/cookWhat 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 | $0.00015 | $0.00937 |
| Opus 5 | $0.00008 | $0.00468 |
| Sonnet 5 | $0.00003 | $0.00187 |
| Haiku 4.5 | $0.00002 | $0.00094 |
Grade A, and why
cook-stats 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.
How it starts
The opening of the file, as written. The whole thing — 168 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/cook-stats Command Specification
Purpose
/cook-stats provides analytics and insights about your cook artifacts.
It helps you:
- Track cooking velocity and completion rates
- Identify frequently touched files (hot spots)
- Find similar past artifacts for pattern reuse
- Understand blocker patterns
Syntax
/cook-stats Show overall statistics
/cook-stats --since 2026-01-01 Filter by date range
/cook-stats search <query> Search artifacts by keyword
/cook-stats similar <file1> <file2> Find artifacts touching similar files
/cook-stats timeline Show recent activity
Options
| Option | Description |
|---|---|
--since DATE |
Only include artifacts from this date (YYYY-MM-DD) |
--until DATE |
Only include artifacts until this date |
--json |
Output as JSON format |
--rebuild |
Force rebuild the index |
--verbose |
Show detailed output |
--limit N |
Limit results (default: 10) |
Commands
stats (default)
Show overall statistics for all cook artifacts.
/cook-stats
/cook-stats --since 2026-01-01
Output includes:
- Total cooks (well-done vs microwave breakdown)
- Status breakdown (well-done, cooking, blocked, etc.)
- Completion rate and block rate
- Most common blockers by chef
- Hot files (most frequently touched)
- Pre-mortem statistics
search
Search artifacts by keyword.
/cook-stats search "authentication"
/cook-stats search "api" --limit 5
Searches:
- Artifact titles
- Slugs
- Files touched
- Decisions made
similar
Find artifacts that touched similar files.
/cook-stats similar src/auth.ts src/login.ts
Use this to:
- Find related past work
- Reuse patterns from similar features
- Recall decisions made for related changes
timeline
Show recent activity across all artifacts.
/cook-stats timeline
/cook-stats timeline --limit 30
Shows:
- Artifact creation dates
- Key decisions made
Example Output
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.
- 2d ago First seen · 168 lines · 0 tokens per session scan A 3d6417ef0a2a
cook-stats is a command published in the GitHub repository PJuniszewski/cook (13 stars, last pushed 6mo ago), licensed MIT. It adds 15 tokens to every session and 937 once invoked, about $0.0001 per session on Opus 5. 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 commands, from other repositories
ship
Run the pre-launch checklist via parallel fan-out to specialist personas, then synthesize a go/no-go decision.
build
Implement tasks incrementally — build, test, verify, commit. Add "auto" to run the whole plan in one approved pass.
constraints
Define and enforce this project's quality bar — interview, sane defaults, CONSTRAINTS.md.
webperf
Run a web performance audit via the web-performance-auditor persona.
plan
Break work into small verifiable tasks with acceptance criteria and dependency ordering.
review
Conduct a five-axis code review — correctness, readability, architecture, security, performance.