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/agent0lab/skills/agents-mdgit clone --depth 1 https://github.com/agent0lab/skillsWhat 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 | $0.00455 | $0.00455 |
| Opus 5 | $0.00228 | $0.00228 |
| Sonnet 5 | $0.00091 | $0.00091 |
| Haiku 4.5 | $0.00046 | $0.00046 |
Grade A, and why
skills 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.
How it starts
The opening of the file, as written. The whole thing — 45 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Agent Instructions
Repository Purpose
This repository contains agent skills for the ERC-8004 Trustless Agents ecosystem. Each top-level directory (8004/, agent0/) is a self-contained skill following the Amp skill structure.
Ground Rules
- NEVER MAKE THINGS UP. If you don't know something, notify your human.
- Double-check everything to ensure it's valid and not made up.
Conventions
- Each skill has a
SKILL.mdwith YAML frontmatter (name,description) as its entry point. - Reference files in
references/are loaded lazily — one concept per file, kept concise. - The
agents/subdirectories contain platform-specific agent configs (e.g.,openai.yaml). - EIP text is the normative baseline. Contracts repo is implementation evidence. Forum threads are rationale/debate.
When Editing Skills
- Keep
SKILL.mdunder 500 lines. - Keep individual reference files focused on a single concept.
- Use exact identifiers and field names from the spec — do not invent aliases.
- Mark version-sensitive content (SDK method names, package names, deployment addresses) with caveats.
- If sources disagree, report the disagreement explicitly rather than picking a side silently.
When Answering ERC-8004 Questions
- Separate normative spec requirements from implementation status and open discussion.
- Include date-sensitive caveats for deployment and support claims.
- Payment rails are explicitly out of scope for ERC-8004.
When Answering Agent0 Questions
- Do not mix TypeScript and Python APIs in one recipe.
- Always ask for network, chainId, RPC URL, and signer details before write workflows.
- Treat indexer/search data as eventually consistent with on-chain state.
Cross-Skill References
- The
8004skill covers protocol-level spec questions. Theagent0skill covers SDK integration. - If a user asks a spec question while in the agent0 context, reference the
8004skill. - If a user asks how to implement something while in the 8004 context, reference the
agent0skill. - Both skills share a common glossary of terms. Prefer spec-defined terms over informal aliases.
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 · 45 lines · 455 tokens per session scan A 4750d9d15f1a
skills AGENTS.md is an instructions file published in the GitHub repository agent0lab/skills (5 stars, last pushed 5mo ago), licensed MIT. It adds 455 tokens to every session, about $0.0023 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 2026-08-31.
Other instructions, from other repositories
ii-agent AGENTS.md
Instructions for Intelligent-Internet/ii-agent, covering ii-agent contributor guide, quick start, repository map, mandatory rules and architecture.
spellbook AGENTS.md
Instructions for majiayu000/spellbook, covering spellbook agent contract, routing, scope rules, threads long-run guardrails and validation.
open-supermarkets AGENTS.md
Instructions for abracadabra50/open-supermarkets, covering agent integration guide, supported frameworks, quick integration, 1. add as skill and 2. agent calls commands.
helm copilot-instructions.md
Instructions for PetePeter/helm, covering gamepad-cli-hub — copilot instructions, project purpose, system overview, data flow pipeline and key controls.
flyto-core CLAUDE.md
Instructions for flytohub/flyto-core, covering claude notes, cross-agent handoff and shared code intelligence.
fusion-skills AGENTS.md
AGENTS.md instructions for CrowdStrike/fusion-skills, covering agents.md, what this is, prerequisites, repository structure and skills ecosystem.