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/deepen)<a href="https://agentmods.dev/commands/juliusbrussee/cavekit/deepen"><img src="https://agentmods.dev/badge/commands/juliusbrussee/cavekit/deepen/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/deepen"><img src="https://agentmods.dev/badge/commands/juliusbrussee/cavekit/deepen.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 | $0.00024 | $0.00136 |
| Opus 5.5 | $0.00010 | $0.00054 |
| Sonnet 5.5 | $0.00005 | $0.00027 |
| Haiku 4.5 | $0.00002 | $0.00014 |
Grade A, and why
deepen 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 deepen skill (skills/deepen/SKILL.md). Pick the single shallowest
module the spec touches, diagnose the design defect at file:line, research a
deeper shape (hand the external case to research → §R), and propose §I/§V/§T edits
to spec. Behavior is sacred — full suite green before AND after. Run only when the
build is green and there is token budget to drain.
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 · 11 lines · 24 tokens per session scan A 865fc93a8096
deepen is a command published in the GitHub repository JuliusBrussee/cavekit (1,156 stars, last pushed 2mo ago), licensed MIT. It adds 24 tokens to every session and 136 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.
speckit.analyze
Perform a non-destructive cross-artifact consistency and quality analysis across spec.md, plan.md, and tasks.md after task generation. (project).
critique
Design lens critique covering visual hierarchy, clarity, and anti-slop patterns — produces a findings table, no code edits unless asked. Use when the user wants a design review, says "what's wrong with this UI", or needs a second opinion before a handoff or presentation.
devkit.github.review-pr
Provides comprehensive GitHub pull request review with code quality, security, and best practices analysis. Use when reviewing a PR before merging.
devkit.react.code-review
Provides comprehensive React 19 + Tailwind CSS code review focusing on modern patterns, hooks, Server Components, Actions, performance, accessibility, and Tailwind best practices. Use when reviewing React code changes or before merging pull requests.
devkit.typescript.code-review
Provides comprehensive TypeScript monorepo code review for Nx workspaces including NestJS backend, React web, and React Native mobile apps. Use when reviewing architecture, boundaries, security, performance, CI/CD and Nx-specific practices.