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/ai4curation/github-ai-integrations/agents-mdgit clone --depth 1 https://github.com/ai4curation/github-ai-integrationsWhat 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 | $0.00155 | $0.00155 |
| Opus 5 | $0.00077 | $0.00077 |
| Sonnet 5 | $0.00031 | $0.00031 |
| Haiku 4.5 | $0.00015 | $0.00015 |
Grade A, and why
github-ai-integrations 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.
What it actually says
CLAUDE.md for
This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository.
WARNING: read this closely as it gets a bit meta.
This is a repo for a copier project intended to allow people to set up their github repo with AI github actions.
- template files are in
template/ - all other files are for this repo itself
So for example
- template/.github/workflows/claude.yml - A template that is copied into a users target repo to set up claude gh actions
- .github/workflows/claude.yml - The actual github actions for this repo itself.
This repo eats its own dogfood! We will occasionally run
copier copy template .
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 · 23 lines · 155 tokens per session scan A 2631fa694564
github-ai-integrations AGENTS.md is an instructions file published in the GitHub repository ai4curation/github-ai-integrations (11 stars, last pushed 6mo ago), licensed MIT. It adds 155 tokens to every session, about $0.0008 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
ai-gene-review CLAUDE.md
Instructions for ai4curation/ai-gene-review, covering ai instructions for ai-gene-review, project overview, repository layout, gene review guidelines and description field quality.
curation-skills AGENTS.md
AGENTS.md instructions for ai4curation/curation-skills, covering agents.md for curation-skills and repo management.
ai-gene-review copilot-instructions.md
Instructions for ai4curation/ai-gene-review, a project described as: Demonstration of AI review of existing functional annotations.
ai-gene-review AGENTS.md
Instructions for ai4curation/ai-gene-review, a project described as: Demonstration of AI review of existing functional annotations.
curation-skills copilot-instructions.md
Copilot instructions for ai4curation/curation-skills, a project described as: Claude skills for a variety of curation and knowledge-based tasks. We currently have 3 skills included, but intend to grow this.
curation-skills CLAUDE.md
Claude Code instructions for ai4curation/curation-skills, a project described as: Claude skills for a variety of curation and knowledge-based tasks. We currently have 3 skills included, but intend to grow this.