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 skyfox675/agents-skills --skill cavemangit clone --depth 1 https://github.com/skyfox675/agents-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/skyfox675/agents-skills/caveman)<a href="https://agentmods.dev/skills/skyfox675/agents-skills/caveman"><img src="https://agentmods.dev/badge/skills/skyfox675/agents-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/skyfox675/agents-skills/caveman"><img src="https://agentmods.dev/badge/skills/skyfox675/agents-skills/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 | $0.00098 | $0.00472 |
| Opus 5 | $0.00049 | $0.00236 |
| Sonnet 5 | $0.00020 | $0.00094 |
| Haiku 4.5 | $0.00010 | $0.00047 |
Grade C, and why
caveman scanned grade C with 2 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.
Downloads and executes remote codehighSupply chain
curl | sh runs whatever the server returns today, which is not necessarily what it returned when this was reviewed.
- **macOS / Linux / WSL / Git Bash:** `curl -fsSL https://raw.githubusercontent.com/JuliusBrussee/caveman/main/install.sh | bash` Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
- **macOS / Linux / WSL / Git Bash:** `curl -fsSL https://raw.githubusercontent.com/JuliusBrussee/caveman/main/install.sh | bash` What it actually says
caveman (pointer skill)
Pointer skill — the implementation is not stored here. The name above is the stable local contract; the body lives upstream and is fetched/installed from source so consumers always get the latest version.
- Canonical source: https://github.com/JuliusBrussee/caveman/blob/main/skills/caveman/SKILL.md
- Raw SKILL.md: https://raw.githubusercontent.com/JuliusBrussee/caveman/main/skills/caveman/SKILL.md
- What it does: Strips filler and uses terse fragment-based output to cut tokens while keeping technical precision; multiple intensity and language variants.
- License: see the JuliusBrussee/caveman repo LICENSE.
Installing this skill
caveman is a full plugin — hooks, a session flag for auto-activation, a statusline token-savings badge, and slash commands. Copying this SKILL.md alone will not work. Run the upstream installer, which detects your agents and configures each:
- macOS / Linux / WSL / Git Bash:
curl -fsSL https://raw.githubusercontent.com/JuliusBrussee/caveman/main/install.sh | bash - Windows (PowerShell 5.1+):
irm https://raw.githubusercontent.com/JuliusBrussee/caveman/main/install.ps1 | iex
Auto-activates in Claude Code, Codex, and Gemini; installs always-on rule files for Cursor, Windsurf, Cline, and Copilot. Full agent list: upstream INSTALL.md.
Security: curl … | bash runs remote code — review install.sh before piping it to a shell. Do not inline the upstream body here.
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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 · 25 lines · 98 tokens per session scan C a2c1a5160631
caveman is a skill published in the GitHub repository skyfox675/agents-skills (10 stars, last pushed 9d ago), licensed MIT. It adds 98 tokens to every session and 472 once invoked, about $0.0005 per session on Opus 5. A static security scan graded it C with 2 findings (downloads and executes remote code, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
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…
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…
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…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…
next-partial-prefetching-adoption
Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…