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.
npx skills add JuliusBrussee/cavekit --skill 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/skills/juliusbrussee/cavekit/review)<a href="https://agentmods.dev/skills/juliusbrussee/cavekit/review"><img src="https://agentmods.dev/badge/skills/juliusbrussee/cavekit/review/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/skills/juliusbrussee/cavekit/review"><img src="https://agentmods.dev/badge/skills/juliusbrussee/cavekit/review.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- Socket pass
- Snyk pass
- NVIDIA SkillSpector pass
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 | $0.00139 | $0.01032 |
| Opus 5.5 | $0.00056 | $0.00413 |
| Sonnet 5.5 | $0.00028 | $0.00206 |
| Haiku 4.5 | $0.00014 | $0.00103 |
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 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.
How it starts
The opening of the file, as written. The whole thing — 86 lines — stays where its author put it; the contents beside it link to each section on GitHub.
review — refute the spec before build
Every finding cites evidence — file:line or a source. No evidence → flag [unverified]. Default to refuted: a flaw you cannot prove is a flaw you note, not one you wave through.
An LLM cannot self-correct on its own judgment — left alone it drifts or degrades. Review fixes that the only way that works: a separate skeptic anchored to an external oracle — the code, §R, the test suite, the docs. "Looks good" is not a review. A refutation attempt is.
WHEN TO REVIEW
- Before
/buildon a high-blast-radius change (shared module, auth, data, money, public API). - Spec touched §I or §V that other code depends on.
- Right-sizing says the cost of a wrong build > the cost of one review pass.
Skip for a trivial, reversible, well-understood change. Adversarial review on a typo hallucinates flaws & wastes the budget — the self-critique paradox is real.
PHASE 0 — CAPTURE
Read the spec: §G §C §I §R §V §T. Hold the whole thing. You review the spec, not your memory of the conversation.
PHASE 1 — CONSTRUCT THE SENIOR
Build a reviewer with real authority, not a generic critic:
- Codebase — grep/read the modules this spec touches. What patterns, what invariants already hold?
- §R — what did research establish? A spec decision that contradicts §R is a finding.
- Live — for any best-practice claim you are unsure of, fetch it. An out-of-date assumption is a flaw.
A reviewer with no evidence is just an opinion. Earn the authority first.
PHASE 2 — REFUTE
Attack the spec on these axes. For each, try to find the case where it breaks:
- Goal vs reality — does §G solve the actual problem, or a proxy?
- Missing invariant — what can go wrong that no §V catches? (most findings live here)
- Interface drift — does §I match what callers already expect? (cite the caller, file:line)
- Constraint conflict — do two §C bullets contradict? does one fight §R?
- Unowned edge — the input, ordering, failure, or concurrency case no §T covers.
- Altitude — §T too vague to act on, or so granular it is just typing?
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 · 86 lines · 139 tokens per session scan A 15dff7dab0a7
review is a skill published in the GitHub repository JuliusBrussee/cavekit (1,157 stars, last pushed 2mo ago), licensed MIT. It adds 139 tokens to every session and 1,032 once invoked, about $0.0006 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 skills, from other repositories
code-reviewer
Review completed implementation batches for spec compliance and code quality. Invoke after execution batches complete, before merging, or when a review gate is reached in the workflow.
review
Uses a fresh agent to review an implementation change without editing it. Checks behavior, security, regressions, complexity, tests, docs, and missing proof. Use for code, PR, diff, security, second-opinion, or pre-merge reviews.
architecture-review
Reviews a technical proposal before implementation. Use for system architectures, feature specs, RFCs, ADRs, and issues that define how a system change should work. Finds material ambiguity and flaws in correctness, scalability, performance, security, operations, and proof.
task-to-pr
Delivers specs or decided tasks as tested, independently reviewed pull requests. Runs the CI and review repair loop, then leaves passing pull requests open unless merging was explicitly authorized.
improve
Makes existing code easier to understand without changing behavior. Use to simplify structure, remove duplication or dead code, improve names, or remove unnecessary abstractions.
speq-code-review
Code review tag taxonomy and findings format for the code-reviewer agent during /speq-implement. Not for general code review.