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 martineserios/thebrana --skill cavemangit clone --depth 1 https://github.com/martineserios/thebranaWrote 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/martineserios/thebrana/caveman)<a href="https://agentmods.dev/skills/martineserios/thebrana/caveman"><img src="https://agentmods.dev/badge/skills/martineserios/thebrana/caveman/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/martineserios/thebrana/caveman"><img src="https://agentmods.dev/badge/skills/martineserios/thebrana/caveman.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 | $0.00041 | $0.00379 |
| Opus 5 | $0.00020 | $0.00189 |
| Sonnet 5 | $0.00008 | $0.00076 |
| Haiku 4.5 | $0.00004 | $0.00038 |
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 9d 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
Caveman Mode
Ultra-compressed communication reducing token usage ~65-75% while maintaining technical accuracy.
Activation
Triggered by: /caveman, "caveman mode", "talk like caveman", "less tokens", "less tokens please".
Once activated, stays ACTIVE EVERY RESPONSE until explicitly stopped with "stop caveman" or "normal mode".
Behavior
- Remove articles, filler words, hedging language, pleasantries
- Maintain exact technical terminology and code blocks unchanged
- Use fragments and short synonyms: "[thing] [action] [reason]. [next step]."
- Code, commits, and PRs written normally — no compression
Intensity Levels
lite— tight but professionalfull— default, classic caveman styleultra— abbreviated terms
Critical Exceptions (auto-switch to normal language)
- Security warnings
- Irreversible action confirmations
- Complex multi-step sequences where fragment order could cause misunderstanding
Examples
Normal: "Sure, I'd be happy to help! The reason this is happening is because the config file is missing the API key." Caveman: "Config missing API key. Add to .env. Restart server."
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.
- 9d ago First seen · 49 lines · 41 tokens per session scan A 7123be6fa26c
caveman is a skill published in the GitHub repository martineserios/thebrana (3 stars, last pushed yesterday), licensed MIT. It adds 41 tokens to every session and 379 once invoked, about $0.0002 per session on Opus 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 2026-08-31.
Other skills, from other repositories
log
A phase-log command that records completed work in Markdown files, a human-readable text format, and updates an index of phases.
i-have-adhd
Shape output for a reader with ADHD: lead with the next action, number multi-step work, restate state across turns, suppress tangents, give specific time estimates, make wins visible. Invoke with /i-have-adhd; stays on until "stop adhd mode".
txt-copy
Copy generated text content to clipboard. Use when user asks to "copy this", "copy to clipboard", "save to clipboard", or after creating emails, messages, letters, or other text content that needs to be shared.
docs
Use when documentation generally needs to catch up with a branch before pushing or merging, covering internal developer docs, external customer-facing docs, and release notes together — "update the docs", "do a docs pass before I merge", "make sure everything's documented". Prefer this when no single documentation…
joycraft-bugfix
Structured bug fix workflow — triage, diagnose, discuss with user, write a focused spec, hand off for implementation.
sitrep-panel
Keep a live local HTML report updated as you work on a task — a status board, a running "what's happening now" narrative, screenshots, and a newest-first log — served on localhost so the user can watch progress in a browser tab instead of reading the transcript. Use when the user invokes /sitrep-panel, asks for a…