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 bug-ops/zeph --skill cavemangit clone --depth 1 https://github.com/bug-ops/zephWrote 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/bug-ops/zeph/caveman)<a href="https://agentmods.dev/skills/bug-ops/zeph/caveman"><img src="https://agentmods.dev/badge/skills/bug-ops/zeph/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/bug-ops/zeph/caveman"><img src="https://agentmods.dev/badge/skills/bug-ops/zeph/caveman.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector 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 | $0.00069 | $0.00290 |
| Opus 5.5 | $0.00028 | $0.00116 |
| Sonnet 5.5 | $0.00014 | $0.00058 |
| Haiku 4.5 | $0.00007 | $0.00029 |
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.
What it actually says
Caveman Mode — Ultra-Compressed Output
Rules
- Drop articles (a/an/the) and filler (please, just, simply, basically, essentially).
- Telegraphic fragments, not full sentences. Imperative voice.
- Minimal punctuation. No greetings, no sign-offs, no hedging.
- One idea per line. Prefer lists over prose.
NEVER compress these (keep verbatim)
- Code blocks (``` fences) — copy exactly.
- File paths, shell commands, identifiers, URLs, error strings.
- Numbers, flags, config keys.
Examples
Input: "Could you please explain what this function does?" Output: "Reads config. Returns parsed struct. Errors on missing file."
Input: "How do I add a dependency in Rust?"
Output: "Add to Cargo.toml: my_crate = \"1.0\". Run cargo build."
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 · 37 lines · 69 tokens per session scan A fb19118da686
caveman is a skill published in the GitHub repository bug-ops/zeph (65 stars, last pushed 3d ago), licensed MIT. It adds 69 tokens to every session and 290 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.
Other skills, from other repositories
skill-creator
Create or update a Codex skill with appropriately scoped instructions and any needed supporting resources.
imagegen
Generate or edit raster images when the task benefits from AI-created bitmap visuals such as photos, illustrations, textures, sprites, mockups, or transparent-background cutouts. Use when Codex should create a brand-new image, transform an existing image, or derive visual variants from references, and the output…
simplicio-loop
Unified public entrypoint for Simplicio's body-of-work orchestration: core + loop in one command. Use when the user types /simplicio-loop, says "ralph loop", "keep iterating until done", "finish all open issues", or asks to drain a queue of work autonomously. Runtime-agnostic: binds a real stop-hook where the host…
simplicio-nest-gate
N-Nest protocol — multi-level gate-corrected agent tree. PRIME depth verification, BH port.port.port addressing, per-level confabulation catch.
simplicio-orient
Terminal-first execution — answer facts with the shell, never with the LLM. Use whenever a step needs a fact about the filesystem, git, processes, or system resources, or runs a build/test/lint/diff whose output would flood context. Substitutes deterministic shell/CLI calls for native LLM operations and clamps their…
simplicio-autoresearch
Evolutionary optimize-by-metric loop — mutate a target, evaluate against fixed criteria, KEEP if the score improves (commit) or REVERT if it doesn't (git checkout), repeat, plateau-break after N stagnated runs. Adapts Karpathy's autoresearch pattern (and the ECC autoresearch-agent) with mandatory yool guardrails (§11…