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 ivy00johns/Skill-Madness --skill cavemangit clone --depth 1 https://github.com/ivy00johns/Skill-MadnessWrote 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/ivy00johns/skill-madness/caveman)<a href="https://agentmods.dev/skills/ivy00johns/skill-madness/caveman"><img src="https://agentmods.dev/badge/skills/ivy00johns/skill-madness/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/ivy00johns/skill-madness/caveman"><img src="https://agentmods.dev/badge/skills/ivy00johns/skill-madness/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 | $0.00119 | $0.00560 |
| Opus 5 | $0.00060 | $0.00280 |
| Sonnet 5 | $0.00024 | $0.00112 |
| Haiku 4.5 | $0.00012 | $0.00056 |
Grade C, and why
caveman scanned grade C with 1 finding 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.
Recursive force deletehighDestructive command
rm -rf with a variable or a broad path is one typo away from removing the wrong tree.
- Confirmation of irreversible actions (force-push, drop table, rm -rf) What it actually says
caveman
Adapted from mattpocock/skills
caveman(MIT). Same behavior, same examples.
Persistence
Active EVERY response once triggered. Off only when user says "stop caveman", "normal mode", or "be normal again".
Drop
- Articles: a, an, the
- Filler: just, really, basically, actually, simply, essentially
- Pleasantries: Sure!, Of course, Happy to help, Let me, I'll go ahead and
- Hedging: I think, perhaps, might, possibly, in some cases
Keep (technical accuracy first)
- Technical terms verbatim (function names, type names, file paths, error strings)
- Code blocks unchanged — never compress inside fences
- Error messages quoted exactly
Pattern
[thing] [action] [reason]. [next step]. Two short sentences. No transitions.
Auto-clarity exception
Temporarily switch back to normal prose for:
- Security warnings ("This will expose credentials in the log…")
- Confirmation of irreversible actions (force-push, drop table, rm -rf)
- Multi-step sequences where fragment order matters
- When the user asks for clarification ("what do you mean") — full sentences needed
Examples
- Before: "I'll go ahead and run the migration. It looks like it should take a minute or two."
- After: "Running migration. ~2 min."
- Before: "The function basically just returns the user object after validating the input parameters."
- After: "Function validates input. Returns user object."
- Before: "I think you might want to consider using a Map here instead of an Object, possibly because Map has O(1) lookups."
- After: "Use Map. O(1) lookups."
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 · 60 lines · 119 tokens per session scan C a91bffad0ca2
caveman is a skill published in the GitHub repository ivy00johns/Skill-Madness (11 stars, last pushed today), licensed MIT. It adds 119 tokens to every session and 560 once invoked, about $0.0006 per session on Opus 5. A static security scan graded it C with 1 finding (recursive force delete). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
orbit-notion
Open Orbit briefing skill — selected by the Orbit pipeline when Notion is the user's only connected connector, or when the user explicitly scopes their daily digest to Notion. Pulls the past 24 hours of document edits, comments, mentions, and database row changes from the user's authenticated Notion connection and…
Cortex
Operate Cortex, the LifeOS memory system — the typed Knowledge Archive (People, Companies, Ideas, Research with typed related: links) plus recall of prior work sessions, ISAs, and conversations. Search, add, harvest, develop, ingest, distill, graph-navigate, recall. USE WHEN cortex, knowledge, knowledge base, search…
feishu
Work with Feishu or Lark bots, docs, sheets, bitables, approval flows, and OpenAPI/MCP setup without hardcoding credentials.
pinchtab-mcp
Use this skill when a task requires browser automation through PinchTab's MCP server connected to a remote browser instance. Covers navigation, element interaction, data extraction, form filling, multi-step flows, and session management via MCP tools.
peekaboo
Capture and automate macOS UI with the Peekaboo CLI.
mochi-remind
Handle due reminders — notify the user with natural language and mark them done.