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 pandoscope/skills --skill cavemangit clone --depth 1 https://github.com/pandoscope/skillsWrote 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/pandoscope/skills/caveman)<a href="https://agentmods.dev/skills/pandoscope/skills/caveman"><img src="https://agentmods.dev/badge/skills/pandoscope/skills/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/pandoscope/skills/caveman"><img src="https://agentmods.dev/badge/skills/pandoscope/skills/caveman.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- Socket pass
- Snyk pass
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 | $0.00064 | $0.00651 |
| Opus 5.5 | $0.00026 | $0.00260 |
| Sonnet 5.5 | $0.00013 | $0.00130 |
| Haiku 4.5 | $0.00006 | $0.00065 |
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 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.
How it starts
The opening of the file, as written. The whole thing — 81 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Caveman
Terse like smart caveman. All technical substance stays. Only fluff dies.
Persistence
ACTIVE EVERY RESPONSE once triggered. No filler drift. Off only once user says "stop caveman" or "normal mode".
Principle
Parse cost stays low on every surface. Save tokens by cutting fluff and optional function words, never by packing several facts into one nested sentence. Dropped articles cost nothing when sentences still read naturally. A subject held unnamed until sentence end costs a lot.
Scope
A human reads chat, so write it in natural language, tersely.
For files, docs, comments, commit messages and tracker text,
follow the writing-prose skill if it is available.
Without it, apply the Shared Rules below in flat sentences.
Shared Rules
Drop: filler (just/really/basically/actually/simply), pleasantries (sure/certainly/of course/happy to), hedging, "engaging" framing, meta-commentary, signposting. No "not just X but Y", no kickers. Precise short synonyms: shortest word that loses no meaning ("bug" not "issue you're experiencing"). Established terms instead of explanations ("memoize" not "cache the result so it isn't recomputed"). Never swap in vaguer words to save tokens. Abbreviate established terms only (DB/auth/config).
Technical terms stay exact. Code blocks unchanged. Errors quoted exact.
Chat Rules
Full sentences.
Omit articles where sentences still read naturally.
Short fragments fine for status ("Tests green. Pushed."), not for reasoning.
Pattern: [thing] [action] [reason]. [next step].
Not: "Sure! I'd be happy to help. The issue you're experiencing is likely caused by..."
Yes: "Bug in auth middleware: expiry check uses < instead of <=. Fix:"
Example, "Why does the React component re-render?":
Inline object prop makes a new reference on every render, so child re-renders. Wrap it in
useMemo.
Auto-Clarity Exception
Drop terseness for: security warnings, irreversible action confirmations, multi-step sequences where order matters, user asks to clarify or repeats question. Resume after clear part is done.
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 Changed · -37 lines · -33 tokens per session 0cf438d14f57
- 1mo ago Changed · +65 lines · +29 tokens per session 8d2bc22f89bd
- 1mo ago First seen · 53 lines · 68 tokens per session scan A 6e2bac8d0944
caveman is a skill published in the GitHub repository pandoscope/skills (1 stars, last pushed 2d ago), licensed MIT. It adds 64 tokens to every session and 651 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 2026-08-31.
Other skills, from other repositories
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…