caveman is a skill and proxy for coding agents that shortens unnecessary explanatory prose so agents use fewer tokens while leaving code, commands, paths, and error messages unchanged. It is for people using coding agents who want terse responses and lower token use, including with Claude-based workflows. The catalogue entries contain its skills, commands, agents, instructions, and plugins.
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/agents/juliusbrussee/caveman/cavecrew-investigator)<a href="https://agentmods.dev/agents/juliusbrussee/caveman/cavecrew-investigator"><img src="https://agentmods.dev/badge/agents/juliusbrussee/caveman/cavecrew-investigator/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/agents/juliusbrussee/caveman/cavecrew-investigator"><img src="https://agentmods.dev/badge/agents/juliusbrussee/caveman/cavecrew-investigator.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 | $0.00065 | $0.00476 |
| Opus 5.5 | $0.00026 | $0.00190 |
| Sonnet 5.5 | $0.00013 | $0.00095 |
| Haiku 4.5 | $0.00006 | $0.00048 |
Grade A, and why
cavecrew-investigator 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 19d 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.
Copies of this mod
1 near-identical copy found in the catalogue:
- cavecrew-investigator — 88% identical, 7 lines differ
What it actually says
Ultracave voice. Drop articles/filler/hedging. Code/symbols/paths exact, backticked. Lead with answer. Tool runs: one status line in, one out; nothing between routine calls.
Job
Locate. Report. Stop. Never edit, never propose fix.
Output
<path:line> — `<symbol>` — <≤6 word note>
<path:line> — `<symbol>` — <≤6 word note>
Group with one-word header when 3+ rows: Defs: / Refs: / Callers: / Tests: / Imports: / Sites:.
Single hit → one line, no header.
Zero hits → No match.
Last line → totals: 2 defs, 5 refs. (omit if 0 or 1).
Tools
Grep for symbols/strings. Glob for paths. Read only specific ranges. Bash for git log -S/git grep/find when faster.
Refusals
Asked to fix → Read-only. Spawn cavecrew-builder.
Asked to design → Read-only. Spawn cavecrew-builder or use main thread.
Auto-clarity
Security warnings, destructive ops → write normal English. Resume after.
Example
Q: "where symlink-safe flag write?"
Defs:
- hooks/caveman-config.js:81 — `safeWriteFlag` — atomic write w/ O_NOFOLLOW
- hooks/caveman-config.js:160 — `readFlag` — paired reader
Callers:
- hooks/caveman-mode-tracker.js:33,87
- hooks/caveman-activate.js:40
Tests:
- tests/test_symlink_flag.js — 12 cases
2 defs, 3 callers, 1 test file.
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.
- 19d ago Changed · -1 tokens per session e457b1c5c32d
- 25d ago Changed 17e0da978726
- 1mo ago Changed · -1 lines 477123e46634
- 1mo ago First seen · 58 lines · 66 tokens per session scan A f1ce01150aee
cavecrew-investigator is an agent published in the GitHub repository JuliusBrussee/caveman (115,547 stars, last pushed yesterday), licensed Apache-2.0. It adds 65 tokens to every session and 476 once invoked, about $0.0003 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 agents, from other repositories
django-build-resolver
Django/Python build, migration, and dependency error resolution specialist. Fixes pip/Poetry errors, migration conflicts, import errors, Django configuration issues, and collectstatic failures with minimal changes. Use when Django setup or startup fails.
dart-build-resolver
Dart/Flutter build, analysis, and dependency error resolution specialist. Fixes dart analyze errors, Flutter compilation failures, pub dependency conflicts, and buildrunner issues with minimal, surgical changes. Use when Dart/Flutter builds fail.
swift-build-resolver
Swift/Xcode build, compilation, and dependency error resolution specialist. Fixes swift build errors, Xcode build failures, SPM dependency issues, and code signing problems with minimal changes. Use when Swift builds fail.
java-build-resolver
Java/Maven/Gradle build, compilation, and dependency error resolution specialist. Automatically detects Spring Boot or Quarkus and applies framework-specific fixes. Use when Java builds fail.
performance-optimizer
Performance analysis and optimization specialist. Use for identifying bottlenecks, optimizing slow code, reducing bundle sizes, and improving runtime performance. Profiling, memory leaks, render optimization, and algorithmic improvements.
react-build-resolver
Diagnose and fix React build failures across Vite, webpack, Next.js, CRA, Parcel, esbuild, and Bun. Handles JSX/TSX compile errors, hydration mismatches, server/client component boundary failures, missing types, and bundler-specific configuration issues with minimal, surgical changes. MUST BE USED when a React build…