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 instructions/juliusbrussee/cavegemma/agents-mdgit clone --depth 1 https://github.com/JuliusBrussee/cavegemmaWrote 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/instructions/juliusbrussee/cavegemma/agents-md)<a href="https://agentmods.dev/instructions/juliusbrussee/cavegemma/agents-md"><img src="https://agentmods.dev/badge/instructions/juliusbrussee/cavegemma/agents-md.svg" alt="Measured on agentmods" 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 | $0.02223 | $0.02223 |
| Opus 5 | $0.01111 | $0.01111 |
| Sonnet 5 | $0.00445 | $0.00445 |
| Haiku 4.5 | $0.00222 | $0.00222 |
Grade A, and why
cavegemma AGENTS.md scanned grade A 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 5d 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.
Runs shell commandslowCapability
Expected in a hook, worth knowing in a rule or an instructions file.
7. **CLI flag parsing on diff content.** Passing patch text containing `---` to `claude -p ---xyz` makes the CLI treat `---xyz` as an unknown flag and exit 1 with empty stderr. Always pipe content via stdin (`subprocess. The source is not reproduced here
No licence file
A repository with no LICENSE is all rights reserved by default, so the body is not copied here. The metadata, the measurements and the link are.
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.
- 5d ago First seen · 115 lines · 2,223 tokens per session scan A 8d60a5fc50db
cavegemma AGENTS.md is an instructions file published in the GitHub repository JuliusBrussee/cavegemma (120 stars, last pushed 1mo ago), with no licence file. It adds 2,223 tokens to every session, about $0.0111 per session on Opus 5. A static security scan graded it A with 1 finding (runs shell commands). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other instructions, from other repositories
tuning-engines-cli CLAUDE.md
Instructions for cerebrixos-org/tuning-engines-cli, covering tuning engines mcp server, setup, claude desktop configuration, claude code and available tools.
axolotl AGENTS.md
AGENTS.md instructions for axolotl-ai-cloud/axolotl, covering axolotl, tech stack, commands, training methods and config pattern.
caveman CLAUDE.md
Claude Code instructions for JuliusBrussee/caveman, covering claude.md — caveman, readme is a product artifact, project overview, repository routing and what lives where.
caveman AGENTS.md
AGENTS.md instructions for JuliusBrussee/caveman: Read CLAUDE.md before repository work. Binding routing: this repo owns skills, Engine, and MV3 extension; Agent SDK work belongs in /Users/julb/Desktop/GitHub/caveman-agent-sdk; Browse driver/MCP/benchmark/plugin work belongs in…
caveman GEMINI.md
Gemini CLI instructions for JuliusBrussee/caveman: @./skills/caveman/SKILL.md @./skills/caveman-commit/SKILL.md @./skills/caveman-review/SKILL.md @./skills/caveman-compress/SKILL.md.
earheart AGENTS.md
AGENTS.md instructions for cleanunicorn/earheart, covering agents.md, golden rules, the github flow, step by step, 1. start from an up-to-date main and 2. create a branch.