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/cavemanWrote 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/plugins/juliusbrussee/caveman/gemini-extension)<a href="https://agentmods.dev/plugins/juliusbrussee/caveman/gemini-extension"><img src="https://agentmods.dev/badge/plugins/juliusbrussee/caveman/gemini-extension/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/plugins/juliusbrussee/caveman/gemini-extension"><img src="https://agentmods.dev/badge/plugins/juliusbrussee/caveman/gemini-extension.svg" alt="Reviewed on agentmods" width="80" height="20"></a>Grade A, and why
caveman 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 3d 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.
The source is not reproduced here
A licence we could not identify
The repository carries a LICENSE file, but it is custom or dual enough that GitHub cannot name it and neither can this catalogue. Unknown terms are not permission, so the body is not copied here. Read the licence at the source and decide for yourself.
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.
- 3d ago First seen · 7 lines scan A 5c46a9e23622
caveman is a plugin published in the GitHub repository JuliusBrussee/caveman (104,422 stars, last pushed yesterday), with no licence file. Its token cost is not measured: this kind of file is read by the harness, not the model. 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 2026-09-07.
Other plugins, from other repositories
claw-mo
Manage mo markdown viewer sessions: autosync new Claude-written .md via PostToolUse hook, group-based organization, restart-on-up for fsnotify-miss recovery, file deep-linking, stdin pipe support, cmux browser integration, per-project watch patterns, port isolation.
claude-eco
Eco mode for Claude Code: minimize token consumption with critical findings intact. Ships /eco and /eco-max (frugality rules, with a low reasoning-effort override), an Eco output style, /eco audit and /eco report, opt-in enforcement hooks, and a benchmark harness. Measured -35% to -57% output tokens on the same task…
skill-conductor
Create, edit, evaluate, and package Claude Code agent skills — full draft→test→review→improve lifecycle.
diretto
Forces the agent to answer in numbered steps you can execute: a one-sentence verdict, the exact commands, and a separate list of what is missing.
neurodock
Local-first cognitive substrate for neurodivergent professionals. Bundles the five NeuroDock MCP servers and a set of ND-aware skills for communication decoding, task decomposition, working-memory recall, and clinical guardrails.
evernote
Evernote integration - notes, notebooks, and research management.