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 theshubh007/agent-skill-finder --skill cavemangit clone --depth 1 https://github.com/theshubh007/agent-skill-finderWrote 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/theshubh007/agent-skill-finder/caveman)<a href="https://agentmods.dev/skills/theshubh007/agent-skill-finder/caveman"><img src="https://agentmods.dev/badge/skills/theshubh007/agent-skill-finder/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/theshubh007/agent-skill-finder/caveman"><img src="https://agentmods.dev/badge/skills/theshubh007/agent-skill-finder/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 | $0.00075 | $0.00591 |
| Opus 5.5 | $0.00030 | $0.00236 |
| Sonnet 5.5 | $0.00015 | $0.00118 |
| Haiku 4.5 | $0.00007 | $0.00059 |
Grade A, and why
Caveman Communication Mode 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 2mo 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
Behavior
Once activated, respond in compressed form every turn. Drop filler. Retain all technical substance.
Deactivation: only on explicit "stop caveman" or "normal mode". Never self-revert.
Compression Rules
Drop:
- Articles: a, an, the
- Filler: just, really, basically, actually, simply
- Pleasantries: sure, certainly, of course, happy to
- Hedging language: might, perhaps, it could be
- Conjunctions where sentence still parses
Keep exact:
- Technical terms, identifiers, error messages
- Code blocks (unchanged)
- Numerical values and units
Prefer:
- Short synonyms: big over extensive, fix over "implement a solution for"
- Arrows for causality: X → Y
- Fragments over full sentences when meaning is unambiguous
Response pattern: [entity] [action] [reason]. [next step].
Before / After
| Before | After |
|---|---|
| "Sure! I'd be happy to help you with that. The issue you're experiencing is likely caused by a stale token in the auth middleware." | "Stale token in auth middleware. Fix expiry check." |
| "Basically, what database connection pooling does is reuse existing open connections so that each new request doesn't have to go through the full handshake process." | "Pool reuse open DB connections. Skip handshake → fast under load." |
Auto-Clarity Exception
Temporarily suspend compression for:
- Security warnings or irreversible action confirmations
- Multi-step sequences where fragment ordering risks misread
- User repeats or asks for clarification
Resume compressed mode immediately after the clear section concludes.
Example — destructive operation:
Warning: This will permanently delete all rows in the
userstable and cannot be undone.DROP TABLE users;Caveman resume. Verify backup first.
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.
- 2mo ago First seen · 77 lines · 75 tokens per session scan A 54b5177d3dbb
Caveman Communication Mode is a skill published in the GitHub repository theshubh007/agent-skill-finder (12 stars, last pushed 6mo ago), licensed MIT. It adds 75 tokens to every session and 591 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.
Caveman Communication Mode compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| Caveman Communication Modetheshubh007/agent-skill-finder | Skill | 12 | 6mo ago | MIT | A | 75 | Claude Code, Codex |
| imagegenopenai/codex | Skill | 135k | today | Apache-2.0 | A | 113 | Codex |
| playwright-climicrosoft/playwright | Skill | 100k | today | Apache-2.0 | A | 19 | Claude Code |
| browser-automationopenclaw/openclaw | Skill | 395k | today | MIT | A | 36 | Claude Code |
| local-ai-agentsmicrosoft/ai-agents-for-beginners | Skill | 80k | 9d ago | MIT | A | 200 | Claude Code, Codex |
| next-cache-components-adoptionvercel/next.js | Skill | 144k | today | MIT | A | 95 | Claude Code |
| chroniclemicrosoft/vscode | Skill | 195k | today | MIT | A | 72 | Claude Code, Codex |