cavekit is a Claude Code plugin that organizes software changes through a compact, spec-driven workflow stored in a SPEC.md file. It is for developers who want to plan, research, review, and build changes while preserving project context across sessions; the catalogue entries are its skills, commands, plugin configuration, and workflow rules.
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.
git 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/check)<a href="https://agentmods.dev/commands/juliusbrussee/cavekit/check"><img src="https://agentmods.dev/badge/commands/juliusbrussee/cavekit/check/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/commands/juliusbrussee/cavekit/check"><img src="https://agentmods.dev/badge/commands/juliusbrussee/cavekit/check.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.00016 | $0.00134 |
| Opus 5.5 | $0.00006 | $0.00054 |
| Sonnet 5.5 | $0.00003 | $0.00027 |
| Haiku 4.5 | $0.00002 | $0.00013 |
Grade A, and why
check 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 1mo 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 check skill (skills/check/SKILL.md). Treat $ARGUMENTS as the
scope (§V default, §I, §T, or --all). Read-only — classify each item
HOLD/VIOLATE/UNVERIFIABLE (or MATCH/DRIFT/MISSING/EXTRA for §I), cite file:line
evidence, end with remedy hints. Writes nothing. Run it after each build.
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.
- 1mo ago First seen · 10 lines · 16 tokens per session scan A a35de7f82b25
check is a command published in the GitHub repository JuliusBrussee/cavekit (1,156 stars, last pushed 2mo ago), licensed MIT. It adds 16 tokens to every session and 134 once invoked, about $0.0001 per session on Opus 5.5. 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
cc-review
(Conductor) Review code changes against spec and standards.
cc-debug
(Conductor) Systematically diagnose and fix a bug.
verify
Perform a systematic second-pass verification of code changes to catch errors before commit.
review-hard
Review the current task changes for correctness, safety, and maintainability risks before slice closure or PR prep, and recommend the smallest safe next step. Use when a slice or task-level implementation was completed, the user wants a focused engineering risk review before closure or PR prep, or meaningful issues…
triage
Triage a bug report (PDF / markdown / text) — extract the issues, prioritize, then run the fix pipeline per issue.
fix
Diagnose and fix a bug — reproduce → locate → root-cause → fix → test.