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/juliusbrussee/cavekit/reviewgit clone --depth 1 https://github.com/JuliusBrussee/cavekitWrote 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/commands/juliusbrussee/cavekit/review)<a href="https://agentmods.dev/commands/juliusbrussee/cavekit/review"><img src="https://agentmods.dev/badge/commands/juliusbrussee/cavekit/review.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 | $0.00027 | $0.00148 |
| Opus 5 | $0.00014 | $0.00074 |
| Sonnet 5 | $0.00005 | $0.00030 |
| Haiku 4.5 | $0.00003 | $0.00015 |
Grade A, and why
review 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.
What it actually says
Invoke the review skill (skills/review/SKILL.md). Construct a senior
reviewer whose authority comes from the codebase, §R, and live best-practice,
then try to refute the spec (§G §C §I §R §V §T). Every finding cites evidence —
file:line or source; flag unverifiable ones [unverified]. Draft §V lines for
HARDEN findings and hand them to spec. End on an explicit GO / NO-GO gate.
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 · 11 lines · 27 tokens per session scan A 3ebfc921ebe4
review is a command published in the GitHub repository JuliusBrussee/cavekit (1,142 stars, last pushed 20d ago), licensed MIT. It adds 27 tokens to every session and 148 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
speckit.verify-tasks
Verify tasks marked [X] in tasks.md are implemented, not phantom completions (marked done but backed by missing or dead code).
archive
Archive merged feature specs into project memory with provenance, sweep discovery, and gated cleanup.
verify
Perform a non-destructive post-implementation verification gate validating the implementation against spec.md, plan.md, tasks.md, and constitution.md.
retrospective
Perform a post-implementation retrospective analysis measuring spec adherence, implementation deviations, and lessons learned.
doctor
Validate project health: templates, agent config, Python runner/helpers, constitution, and feature artifacts.
validate
Verify spec-to-task traceability and check that completed tasks produced expected files.