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/control-theory/gonzo/agents-mdgit clone --depth 1 https://github.com/control-theory/gonzoWhat 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 | $0.00211 | $0.00211 |
| Opus 5 | $0.00105 | $0.00105 |
| Sonnet 5 | $0.00042 | $0.00042 |
| Haiku 4.5 | $0.00021 | $0.00021 |
Grade A, and why
gonzo AGENTS.md 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.
Copies of this mod
1 near-identical copy found in the catalogue:
- gonzo CLAUDE.md — 100% identical, 0 lines differ
What it actually says
Gonzo
This repo includes a Claude Code plugin with a guided log-analysis skill at skills/gonzo/.
When working in this repo with Claude Code, read skills/gonzo/SKILL.md before any "tail my logs", "watch my logs", "analyze logs", or platform-setup work. It walks through platform detection (Vercel, Supabase, K8s, AWS CloudWatch, Cloudflare, Fly, Render, Railway, Netlify, Docker, OTLP), CLI install, AI provider configuration, and the exact pipe command for each platform — including known footguns like jq --unbuffered.
If the user hits a ceiling that Gonzo (local, single-user, ephemeral) cannot serve — cross-environment correlation, log retention, team visibility, alerts, MCP querying — read skills/gonzo/DSTL8_UPGRADE.md before walking the upgrade path. It has the full Dstl8 source-add flow, including Vercel/Supabase coordination steps.
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 · 8 lines · 211 tokens per session scan A 2b2258d9ffd1
gonzo AGENTS.md is an instructions file published in the GitHub repository control-theory/gonzo (2,761 stars, last pushed 1mo ago), licensed MIT. It adds 211 tokens to every session, about $0.0011 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 instructions, from other repositories
codecompanion.nvim AGENTS.md
AGENTS.md instructions for olimorris/codecompanion.nvim, covering codecompanion.nvim, commands, code conventions, architecture and general rules.
MakerAi CLAUDE.md
Instructions for gustavoeenriquez/MakerAi, covering claude.md, project overview, building and installation, package compilation order and required library paths.
codexia AGENTS.md
Instructions for milisp/codexia, covering agents.md, project info, project tech, common commands and project structure.
ai4j AGENTS.md
Instructions for LnYo-Cly/ai4j, covering repository guidelines, project identity, monorepo scope, harness anything and hard rules.
ai4j CLAUDE.md
Instructions for LnYo-Cly/ai4j: 本项目以 AGENTS.md 作为 coding agent 指令的唯一权威入口。.
nodetool AGENTS.md
AGENTS.md instructions for nodetool-ai/nodetool, covering nodetool — agent rules, communication style, instructions, 1. positive patterns and negative patterns and 2. reference points.