agent-friendly-services AGENTS.md

Repository instructions for contributing entries to a machine-readable directory of services that coding agents can use.

In plain words
What is it for?
They help add providers to a candidate pool, update provider records, resolve unknown entries, and follow the repository’s review process.
Why use it?
They clarify which files are authoritative, where new unverified entries belong, and which generated files must not be edited directly.

Instructions file for CodexOpenCode

Install

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.

agentmods
npx agentmods add instructions/olorinm/agent-friendly-services/agents-md
Clone the repo
git clone --depth 1 https://github.com/Olorinm/agent-friendly-services

Made for: Codex, OpenCode.

Per session 907 This file is loaded in full into every session.
When invoked 907 The same file — it is already loaded in full.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00907 $0.00907
Opus 5 $0.00453 $0.00453
Sonnet 5 $0.00181 $0.00181
Haiku 4.5 $0.00091 $0.00091

Measured 2d ago against content hash eab6fa286dd1, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

agent-friendly-services 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.

AGENTS.md · 48 lines

How it starts

The opening of the file, as written. The whole thing — 48 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AGENTS.md

This repository is a machine-readable directory of agent-friendly services. You (an agent) can contribute to it end-to-end. This file tells you how.

Source of truth

  • Provider data: data/providers/*.yaml — one file per provider (verified index)
  • Candidate pool: data/candidates/*.yaml — same schema, unverified; new providers start here (docs/candidate-pool.md)
  • Field definitions: data/fields.yaml — what every entrypoint and check means
  • Categories: data/categories.yaml
  • README.md and generated/ are build outputs. Never edit them. CI regenerates them on main.

Add a provider (goes to the candidate pool)

  1. Copy an existing file in data/providers/ into data/candidates/<id>.yaml. Use a lowercase id equal to the filename (modal.yamlid: modal). Promotion out of the pool happens later, after a passing M1 agent run + evidence review — not in your PR.
  2. Check inclusion rules first: hosted service + API surface + self-serve access path (an account system, or agent-native pay-per-call like x402). Libraries and frameworks don't qualify. Name the product precisely (Docker Hub, not Docker). Account-less services: mark account-shaped checks (signup, api keys, oauth, scoped tokens, revocation) not_applicable with a note — never supported.
  3. Fill entrypoints with public, login-free official URLs. Omit what you cannot find — a missing entrypoint means "no known URL", and that is fine.
  4. Fill the checks you can verify. Status enum: supported | partial | unsupported | unknown | not_applicable.
  5. Every supported/partial needs an official evidence URL and a verified date. partial and not_applicable also need notes.
  6. Dates are quoted strings: verified: "2026-07-07". Update only the checks you actually verified.
  7. Run npm run validate. Fix what it reports — the messages tell you how.
  8. Optionally run npm run probe -- --only=<id> to confirm your URLs answer.

Update a provider

  1. Change only the fields you re-verified; update only their verified dates.
  2. Leave everything you did not check untouched.

Read the full file on GitHub · 48 lines

Changes

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.

  1. 2d ago First seen · 48 lines · 907 tokens per session scan A eab6fa286dd1

Subscribe to this mod's changes

agent-friendly-services AGENTS.md is an instructions file published in the GitHub repository Olorinm/agent-friendly-services (2 stars, last pushed 9d ago), licensed MIT. It adds 907 tokens to every session, about $0.0045 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.