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/dfinity/examples/agents-mdgit clone --depth 1 https://github.com/dfinity/examplesWhat 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 | $0.06072 | $0.06072 |
| Opus 5 | $0.03036 | $0.03036 |
| Sonnet 5 | $0.01214 | $0.01214 |
| Haiku 4.5 | $0.00607 | $0.00607 |
Grade A, and why
examples 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 yesterday.
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 — 450 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Agent Instructions
Guidelines for AI agents (Claude, Codex, Cursor, Copilot, etc.) working in this repository.
ICP Skills
ICP skills are tested, frequently-updated instruction files maintained by DFINITY (see https://skills.internetcomputer.org). Consult the relevant skills before making changes — do not rely on training-data knowledge of ICP tooling. For background on how agents consume ICP skills, see the AI coding agents guide.
How this repo is set up: it uses autosync, an ICP skill that installs the sync mechanism. A committed SessionStart hook (.claude/settings.json → .claude/sync-ic-skills.sh) mirrors the latest skills into .claude/skills/ at the start of every session, so they stay current with nothing to commit when a skill changes (the skills directory itself is gitignored). The first time it runs, Claude Code asks you to trust the hook. This targets Claude Code only — other agents (Cursor, Copilot, Codex, …) don't run the hook and instead use the on-demand fallback noted below.
ICP skills auto-update each session via a SessionStart hook
(.claude/sync-ic-skills.sh) and live in your agent skills directory — you don't
need to run anything to refresh them. Skills are authoritative — prefer them over
general knowledge for all ICP work. If they are not present (hook hasn't run, or
jq is missing), fetch them on demand per the "Use skills now" steps above.
On-demand fallback (any agent, no hook needed): fetch the index once per session from https://skills.internetcomputer.org/.well-known/skills/index.json, then fetch the matching skill's SKILL.md before writing ICP code for a task. This is how non–Claude Code agents (Cursor, Copilot, Codex, …) use the skills, since the SessionStart hook is Claude Code–only.
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.
- yesterday First seen · 450 lines · 6,072 tokens per session scan A 74c209907959
examples AGENTS.md is an instructions file published in the GitHub repository dfinity/examples (613 stars, last pushed 4d ago), licensed Apache-2.0. It adds 6,072 tokens to every session, about $0.0304 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
moonbit-ic-cdk AGENTS.md
Instructions for eliezhao/moonbit-ic-cdk, covering project agents.md guide, project structure, coding convention and tooling.
Get-Started-with-Web3 AGENTS.md
Instructions for beihaili/Get-Started-with-Web3, covering get started with web3 agent notes, 项目定位, ceo 运营目标, 常用命令 and ai-native 内容层.
synadia-agents-labs CLAUDE.md
Instructions for synadia-ai/synadia-agents-labs, covering claude.md, what this repo is, the protocol in 30 seconds, layout and conventions — treat these as rules.
Fullstack-development-agent-skills CLAUDE.md
Claude Code instructions for vaquarkhan/Fullstack-development-agent-skills, a project described as: Full stack development agent skills are portable packages of instructions, scripts, and resources that teach an AI agent how to execute specialized or repetitive tasks.
Hackathon-Stellaroid_Earn AGENTS.md
AGENTS.md instructions for Iron-Mark/Hackathon-Stellaroid_Earn, covering agents.md, what this repo is, common commands, frontend (frontend/) and stellar cli (environment setup).
spotify-skill copilot-instructions.md
Instructions for fabioc-aloha/spotify-skill, covering copilot instructions - spotify skill project, project overview, what this project is, project type and what are claude desktop skills?.