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/inspectgit 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 | $0.00013 | $0.04683 |
| Opus 5 | $0.00006 | $0.02341 |
| Sonnet 5 | $0.00003 | $0.00937 |
| Haiku 4.5 | $0.00001 | $0.00468 |
Grade A, and why
inspect 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 yesterday.
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 — 621 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/inspect Command
Sanitation Inspector - post-implementation CODE REVIEW that verifies actual git diffs match the cook artifact plan.
What This Command Does
┌─────────────────────────────────────────────────────────────────┐
│ /juni:inspect │
│ │
│ 1. Find artifact (plan) cook/feature.cook.md │
│ ↓ │
│ 2. Find related commits git log, git show │
│ ↓ │
│ 3. Get actual diff git show <sha> -p │
│ ↓ │
│ 4. CODE REVIEW Compare PLAN vs DIFF │
│ • Recipe Compliance (planned files vs changed) │
│ • Hygiene (error handling, edge cases) │
│ • Safety (security issues in diff) │
│ ↓ │
│ 5. Generate report Append to artifact │
└─────────────────────────────────────────────────────────────────┘
THIS IS NOT: A review of the artifact document itself. THIS IS: A code review of git commits against the artifact plan.
Agent assumptions (applies to all agents and subagents):
- All tools are functional. Do not test tools or make exploratory calls.
- Only call a tool if required to complete the task.
- This is a CODE REVIEW - you MUST run
git showorgit diffto get actual code changes. - Never review just the artifact markdown - always review the git diff.
Syntax
/juni:inspect Inspect most recent well-done artifact
/juni:inspect <artifact> Inspect specific artifact
/juni:inspect <artifact> --commit <sha> Inspect specific commit against artifact
/juni:inspect --commit <sha> Pure code review (no artifact, just diff review)
/juni:inspect --surprise Surprise inspection (stricter, more thorough)
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.
- yesterday First seen · 621 lines · 13 tokens per session scan A 69aac56d1e12
inspect is a command published in the GitHub repository PJuniszewski/cook (13 stars, last pushed 6mo ago), licensed MIT. It adds 13 tokens to every session and 4,683 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.
review
Conduct a five-axis code review — correctness, readability, architecture, security, performance.
plan
Break work into small verifiable tasks with acceptance criteria and dependency ordering.