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 agentmods add skills/juliusbrussee/caveman-code/plugin-creatornpx skills add JuliusBrussee/caveman-code --skill plugin-creatorgit clone --depth 1 https://github.com/JuliusBrussee/caveman-codeWhat 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 | $0.00080 | $0.01144 |
| Opus 5 | $0.00040 | $0.00572 |
| Sonnet 5 | $0.00016 | $0.00229 |
| Haiku 4.5 | $0.00008 | $0.00114 |
Grade A, and why
plugin-creator 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 2d 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 — 125 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Plugin Creator
You scaffold new cave plugins. A cave plugin is a directory published to GitHub (or any zip URL) with a .cave-plugin/plugin.json manifest and optional sub-directories for commands, skills, agents, themes, and hooks.
Manifest Schema
{
"name": "my-plugin",
"version": "0.1.0",
"description": "A short, clear description of what this plugin does.",
"author": "your-github-handle",
"license": "MIT",
"homepage": "https://github.com/your-handle/my-plugin",
"caveVersion": ">=0.65.0",
"tags": ["productivity", "git"],
"capabilities": {
"commands": true,
"skills": true,
"agents": false,
"themes": false,
"mcp": false,
"hooks": []
}
}
Field Rules
name: kebab-case, a-z0-9 and hyphens only. Must be unique in the marketplace.version: semver ("major.minor.patch").description: one sentence, plain text.tags: free-form strings forcaveman plugin searchmatching.capabilities.commands: settrueifcommands/directory is present.capabilities.skills: settrueifskills/directory is present.capabilities.agents: settrueifagents/directory is present.capabilities.themes: settrueifthemes/directory is present.capabilities.mcp: settrueif.mcp.jsonis present.capabilities.hooks: array of hook entries (see below).
Hook Entry Shape
{ "event": "PostToolUse", "command": "hooks/post-tool-use.sh", "matcher": "Bash" }
Directory Structure
my-plugin/
├── .cave-plugin/
│ └── plugin.json ← required
├── commands/
│ └── my-command.md ← markdown slash commands
├── skills/
│ └── my-skill/
│ └── SKILL.md ← skill with frontmatter
├── agents/
│ └── my-agent.md ← agent definition markdown
├── themes/
│ └── my-theme.json ← theme JSON (cave theme format)
├── hooks/
│ └── post-tool-use.sh ← hook scripts (chmod +x)
├── .mcp.json ← optional MCP server definitions
└── README.md
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.
- 2d ago First seen · 125 lines · 80 tokens per session scan A d9733d09a23c
plugin-creator is a skill published in the GitHub repository JuliusBrussee/caveman-code (929 stars, last pushed 18d ago), licensed MIT. It adds 80 tokens to every session and 1,144 once invoked, about $0.0004 per session on Opus 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
weekly-digests
Generate a serial week-by-week narrative digest of a project's full claude-mem timeline. Splits the timeline into per-ISO-week files, then runs one consecutive subagent per week — each receiving the prior week's carry-forward block — to produce one chapter per ISO week of data. Use when asked for "weekly digests"…
skill-creator
Create, install, or update skills in the workspace. Use when (1) installing a skill from a URL or remote source, (2) creating a new skill from scratch, (3) updating or restructuring existing skills. Always use this skill for any skill installation or creation task.
skill-template
Template for creating new Agent Skills for context engineering. Use this template when adding new skills to the collection.
geo-audit
Full website GEO+SEO audit with parallel subagent delegation. Orchestrates a comprehensive Generative Engine Optimization audit across AI citability, platform analysis, technical infrastructure, content quality, and schema markup. Produces a composite GEO Score (0-100) with prioritized action plan.
Agent Development
This skill should be used when the user asks to "create an agent", "add an agent", "write a subagent", "agent frontmatter", "when to use description", "agent examples", "agent tools", "agent colors", "autonomous agent", or needs guidance on agent structure, system prompts, triggering conditions, or agent development…
skill-creator
Scaffold a new yoyo skill when a human or community issue asks for one ("add a skill for X", "create a skill that does Y"). Generates correct frontmatter, validates, writes to disk.