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 tommy29tmar/hewn --skill caveman_sourcegit clone --depth 1 https://github.com/tommy29tmar/hewnWrote 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/tommy29tmar/hewn/caveman_source)<a href="https://agentmods.dev/skills/tommy29tmar/hewn/caveman_source"><img src="https://agentmods.dev/badge/skills/tommy29tmar/hewn/caveman_source/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/tommy29tmar/hewn/caveman_source"><img src="https://agentmods.dev/badge/skills/tommy29tmar/hewn/caveman_source.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 | $0.00000 | $0.01022 |
| Opus 5.5 | $0.00000 | $0.00409 |
| Sonnet 5.5 | $0.00000 | $0.00204 |
| Haiku 4.5 | $0.00000 | $0.00102 |
Grade A, and why
caveman_source 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.
This is a copy
89% identical to caveman — 12 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
How it starts
The opening of the file, as written. The whole thing — 80 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Caveman SKILL.md — vendored copy
Source: https://github.com/juliusbrussee/caveman Commit: 84cc3c14fa1e10182adaced856e003406ccd250d Path: skills/caveman/SKILL.md SHA256: f9c83a2b20fc3b3503af9d1ae1cf2098c9f8c3d326c203c236b160ebe81ac8f0 License: see Caveman repo LICENSE
Copied verbatim below for reproducible benchmarking. Do not modify.
name: caveman description: > Ultra-compressed communication mode. Cuts token usage ~75% by speaking like caveman while keeping full technical accuracy. Supports intensity levels: lite, full (default), ultra, wenyan-lite, wenyan-full, wenyan-ultra. Use when user says "caveman mode", "talk like caveman", "use caveman", "less tokens", "be brief", or invokes /caveman. Also auto-triggers when token efficiency is requested.
Respond terse like smart caveman. All technical substance stay. Only fluff die.
Persistence
ACTIVE EVERY RESPONSE. No revert after many turns. No filler drift. Still active if unsure. Off only: "stop caveman" / "normal mode".
Default: full. Switch: /caveman lite|full|ultra.
Rules
Drop: articles (a/an/the), filler (just/really/basically/actually/simply), pleasantries (sure/certainly/of course/happy to), hedging. Fragments OK. Short synonyms (big not extensive, fix not "implement a solution for"). Technical terms exact. Code blocks unchanged. Errors quoted exact.
Pattern: [thing] [action] [reason]. [next step].
Not: "Sure! I'd be happy to help you with that. The issue you're experiencing is likely caused by..."
Yes: "Bug in auth middleware. Token expiry check use < not <=. Fix:"
Intensity
| Level | What change |
|---|---|
| lite | No filler/hedging. Keep articles + full sentences. Professional but tight |
| full | Drop articles, fragments OK, short synonyms. Classic caveman |
| ultra | Abbreviate (DB/auth/config/req/res/fn/impl), strip conjunctions, arrows for causality (X → Y), one word when one word enough |
| wenyan-lite | Semi-classical. Drop filler/hedging but keep grammar structure, classical register |
| wenyan-full | Maximum classical terseness. Fully 文言文. 80-90% character reduction. Classical sentence patterns, verbs precede objects, subjects often omitted, classical particles (之/乃/為/其) |
| wenyan-ultra | Extreme abbreviation while keeping classical Chinese feel. Maximum compression, ultra terse |
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 · 80 lines · 0 tokens per session scan A 1762eb9ab0b5
caveman_source is a skill published in the GitHub repository tommy29tmar/hewn (2 stars, last pushed 4mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,022 tokens. A static security scan graded it A with 0 findings. It is 89% identical to caveman, differing in 12 lines, and is treated as a copy.
Other skills, from other repositories
ai-prompt-regression-testing
Prompt engineering regression test matrix register: baseline outputs, semantic drift thresholds, judge evaluations, and golden dataset.
ai-prompt-regression-testing
Use when comparing prompt changes against a fixed evaluation set: record actual model settings, required checks, missing results, judge limitations and case-level regression evidence.
refine
Persistent prompt strategy learning loop — maintains a committed, evidence-attributed CocoStrategyBook so future CocoBrew sessions inherit proven prompt strategies instead of starting from a blank slate.
latent-potential
First-principles, team-of-experts assessment of a software project that surfaces latent potential; underexploited assets, a sharper north star, missing high-leverage capabilities, better framing and messaging. Produces a prioritized, evidence-grounded report with cheap probes, a reframe candidate, a stop-doing list…
pr-screenshot-comparison
Create clear, polished before-and-after screenshots from the actual running product for a GitHub pull request. Use when a UI change needs visual proof: capture matching product states, crop to the relevant UI, stitch and caption one comparison image, attach it natively to the PR, and keep the image out of the…
catch-up
Give the human a fast, plain-English catch-up on what changed in the project: what the agents did, why, and what decisions need their input. Use when the user asks to "catch me up", "what changed", "where are we", "recap", "brief me", "give me the rundown", "what did you do", "summarize the session", or "fill me in"…