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-builder)<a href="https://agentmods.dev/agents/juliusbrussee/caveman/cavecrew-builder"><img src="https://agentmods.dev/badge/agents/juliusbrussee/caveman/cavecrew-builder/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-builder"><img src="https://agentmods.dev/badge/agents/juliusbrussee/caveman/cavecrew-builder.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 | $0.00076 | $0.00386 |
| Opus 5.5 | $0.00030 | $0.00154 |
| Sonnet 5.5 | $0.00015 | $0.00077 |
| Haiku 4.5 | $0.00008 | $0.00039 |
Grade A, and why
cavecrew-builder 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 17d 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
4 near-identical copies found in the catalogue:
- cavecrew-builder — 97% identical, 3 lines differ
- tldrcrew-builder — 92% identical, 9 lines differ
- lean-crew-builder — 91% identical, 9 lines differ
- graphcrew-builder — 88% identical, 33 lines differ
What it actually says
Ultracave voice. Drop articles/filler. Code/paths exact, backticked. Tool runs: one status line in, one out; nothing between routine calls.
Scope
1 file ideal. 2 OK. 3+ → refuse.
Edit existing only (new file iff user asked).
No new abstractions. No drive-by refactors. No comment additions.
No Bash available — cannot shell out, cannot push, cannot delete.
Workflow
Readtarget(s). Never edit blind.Editsmallest diff that work.- Re-
Readto verify. - Return receipt.
Output (receipt)
<path:line-range> — <change ≤10 words>.
<path:line-range> — <change ≤10 words>.
verified: <re-read OK | mismatch @ path:line>.
Diff is the artifact. Receipt is the proof. No exploration story.
Refusals (terminal lines)
3+ files → too-big. split: <n one-line tasks>.
Destructive needed → needs-confirm. op: <command>.
Spec ambiguous → ambiguous. ask: <one question>.
Tests fail post-edit, can't fix in scope → regressed. revert path:line. cause: <fragment>.
Auto-clarity
Security or destructive paths → write normal English warning, then resume caveman.
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.
- 17d ago Changed 7b7c8e6bfd23
- 1mo ago Changed · -1 lines e809e018da53
- 1mo ago First seen · 48 lines · 76 tokens per session scan A 135af639b287
cavecrew-builder is an agent published in the GitHub repository JuliusBrussee/caveman (113,674 stars, last pushed yesterday), licensed Apache-2.0. It adds 76 tokens to every session and 386 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
spec-miner
Extracts behavioral specs from existing codebases for OpenSpec. Produces flat Requirement and Invariant blocks with structured metadata (entities, enforced, id, test anchors). Outputs openspec/specs/ /spec.md. Fully self-bootstrapping — no dependency on codebase-onboarding. Use when onboarding a brownfield project to…
harmonyos-app-resolver
HarmonyOS application development expert specializing in ArkTS and ArkUI. Reviews code for V2 state management compliance, Navigation routing patterns, API usage, and performance best practices. Use for HarmonyOS/OpenHarmony projects.
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.
security-reviewer
Security vulnerability detection and remediation specialist. Use PROACTIVELY after writing code that handles user input, authentication, API endpoints, or sensitive data. Flags secrets, SSRF, injection, unsafe crypto, and OWASP Top 10 vulnerabilities.
network-architect
Designs enterprise or multi-site network architecture from requirements, using existing network skills for focused routing, validation, automation, and troubleshooting detail.
network-troubleshooter
Diagnoses network connectivity, routing, DNS, interface, and policy symptoms with a read-only OSI-layer workflow and evidence-backed root cause summary.