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/apollographql/skills/agents-mdgit clone --depth 1 https://github.com/apollographql/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/instructions/apollographql/skills/agents-md)<a href="https://agentmods.dev/instructions/apollographql/skills/agents-md"><img src="https://agentmods.dev/badge/instructions/apollographql/skills/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 | $0.00705 | $0.00705 |
| Opus 5 | $0.00352 | $0.00352 |
| Sonnet 5 | $0.00141 | $0.00141 |
| Haiku 4.5 | $0.00071 | $0.00071 |
Grade B, and why
skills AGENTS.md scanned grade B 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.
Unrestricted tool accessmediumExcessive agency
A wildcard tool grant or "run any command" leaves no least-privilege boundary at all.
allowed-tools: Bash(tool:*) Read Write Edit Glob Grep How it starts
The opening of the file, as written. The whole thing — 73 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md
This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository.
Repository Overview
This repository contains AI agent skills for Apollo GraphQL tools, following the Agent Skills format. Skills are documentation bundles that AI coding assistants can use to provide context-aware help with Apollo technologies.
Repository Structure
skills/
├── <skill-name>/
│ ├── SKILL.md # Main skill file (required) - has YAML frontmatter
│ └── references/ # Supporting documentation (optional)
│ └── *.md
Skill File Format
Every SKILL.md must include YAML frontmatter with:
name: skill identifier (lowercase, hyphenated)description: multi-line description with numbered use caseslicense: MITcompatibility: runtime requirementsmetadata: author (apollographql) and versionallowed-tools: permitted tools for the skill
Example frontmatter pattern:
---
name: skill-name
description: >
Description of the skill. Use this skill when:
(1) first use case,
(2) second use case.
license: MIT
compatibility: Requirements
metadata:
author: apollographql
version: "1.0"
allowed-tools: Bash(tool:*) Read Write Edit Glob Grep
---
Validation
Skills should be validated against the Agent Skills specification at https://agentskills.io/specification
Validate locally with gh skill publish --dry-run (or skills-ref validate skills/<name>) before opening a PR.
Adding a New Skill
- Create
skills/<skill-name>/SKILL.mdwith proper frontmatter - Add reference files in
skills/<skill-name>/references/as needed - Update
README.mdto document the new skill (follow existing patterns) - Ensure consistency with existing skills' frontmatter format
Releasing / Versioning
CI's version-check enforces two independent bumps — both must strictly increase or the check fails.
- Per-skill: the
metadata.versionin everyskills/<name>/SKILL.mdwhose content you changed. Each changed skill is checked separately, so if you touch two skills you must bump both. This is the one most often forgotten. - Plugin:
.claude-plugin/plugin.json#versionis whatclaude plugin updatechecks. Bump it whenever you touchskills/,commands/,agents/,hooks/, orplugin.jsonitself, otherwise existing users won't see the change. New installs always pull the latest content regardless.
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 · 73 lines · 705 tokens per session scan B 4f242cdbfa82
skills AGENTS.md is an instructions file published in the GitHub repository apollographql/skills (110 stars, last pushed 1mo ago), licensed MIT. It adds 705 tokens to every session, about $0.0035 per session on Opus 5. A static security scan graded it B with 1 finding (unrestricted tool access). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other instructions, from other repositories
sdks AGENTS.md
AGENTS.md instructions for morpho-org/sdks, covering engineering rules, 1. architecture, layering: one direction, no exceptions, modularity: one reason to exist and testability: pure cores, i/o at the edge.
sdks CLAUDE.md
Claude Code instructions for morpho-org/sdks, a project described as: Typescript SDKs to interact with the Morpho protocols.
graphjin AGENTS.md
AGENTS.md instructions for dosco/graphjin, covering graphjin agent guide, architectural overview, directory structure & responsibilities, build commands and coding guidelines.
NornicDB AGENTS.md
AGENTS.md instructions for orneryd/NornicDB, covering nornicdb development guide for ai agents, core philosophy, 🎯 golden rules, 1. prove value before merging and 2. test-driven bug fixes.
api-gateway CLAUDE.md
Claude Code instructions for membrane/api-gateway, covering claude.md, git & commit policy, working principles, 1. think before coding and 2. simplicity first.
LAP CLAUDE.md
Claude Code instructions for Lap-Platform/LAP, covering lap - lean api platform, what this is, quick reference, install and run tests.