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/agent-network-protocol/agentnetworkprotocol/agents-mdgit clone --depth 1 https://github.com/agent-network-protocol/AgentNetworkProtocolWhat 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 | $0.00714 | $0.00714 |
| Opus 5 | $0.00357 | $0.00357 |
| Sonnet 5 | $0.00143 | $0.00143 |
| Haiku 4.5 | $0.00071 | $0.00071 |
Grade A, and why
AgentNetworkProtocol 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 — 59 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Repository Guidelines
Project Structure & Module Organization
- Root contains protocol specifications and white papers (e.g.,
01-*.md,06-*.md,07-*.md,08-*.md). vnext/andchinese/vnext/hold candidate drafts for core protocols 01–09.docs/anddocs/chinese/hold guides, links, and community operations.chinese/mirrors core documents in Chinese plus research notes and process docs.blogs/andblogs/cn/store long-form articles;blogs/images/holds blog assets.images/andstandard/provide shared figures and standards references.examples/contains sample ADP assets and API interface YAMLs.scripts/includes dependency-free Python and JavaScript utilities for repo maintenance.
Protocol Ownership Boundary
- Profile specifications indexed by this repository belong to the ANP protocol set. Do not add an implementation-owned profile outside the
anp.*namespace to the ANP Profile index merely because it transports ANP messages or uses ANP capability discovery. - Vendor or product-private protocols, fixtures, storage limits, client scheduling rules, and UI watchdogs stay in the owning product repository. ANP documents may describe the generic extension mechanism without adopting a private profile as an ANP specification.
Build, Test, and Development Commands
This repository is documentation-first and has focused tests for maintenance automation.
- Run maintenance scripts with UV:
uv run python scripts/add_copyright.pyuv run python scripts/rename_images.pyuv run python scripts/replace_spaces_with_hyphens.py
- Test contributor avatar automation with
node --test tests/update_contributors.test.js.
Coding Style & Naming Conventions
- Documentation is Markdown; keep headings concise and sectioned with
##/###. - Use descriptive, kebab-case filenames for new documents and assets when possible.
- For Python scripts, follow Google Python Style; keep comments and logs in English.
- Prefer clear, action-oriented titles like
add,update,docs:in commit messages.
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 · 59 lines · 714 tokens per session scan A 154a16b5b15b
AgentNetworkProtocol AGENTS.md is an instructions file published in the GitHub repository agent-network-protocol/AgentNetworkProtocol (1,407 stars, last pushed 4d ago), licensed Apache-2.0. It adds 714 tokens to every session, about $0.0036 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
intelligent-terminal localization.instructions.md
Instructions for microsoft/intelligent-terminal, covering localization instructions for .resw resource files, components with localized resources, locale categories, authoritative locale list (from terminalapp) and adding or updating localized strings.
intelligent-terminal rust-localization.instructions.md
Instructions for microsoft/intelligent-terminal, covering localization instructions for rust wta (yaml locale files), file structure, file format, the en-us.yml source file and non-translatable token rules.
cybara AGENTS.md
Instructions for metaspartan/cybara, covering cybara agent rules, package manager policy (strict), command translation, typescript type safety and no comments.
hello-halo CLAUDE.md
Claude Code instructions for openkursar/hello-halo: No hardcoded text. Use t('English text').
Aether AGENTS.md
AGENTS.md instructions for Zhou-Shilin/Aether, a project described as: A stunning, localized, general-purpose AI Agent for Android, iOS & Mac. | Aether 扶摇.
xpert AGENTS.md
AGENTS.md instructions for xpert-ai/xpert, covering agents guide for xpert, general, backend (nestjs), backend i18n and frontend (angular).