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/inference-gateway/adl/agents-mdgit clone --depth 1 https://github.com/inference-gateway/adlWrote 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/inference-gateway/adl/agents-md)<a href="https://agentmods.dev/instructions/inference-gateway/adl/agents-md"><img src="https://agentmods.dev/badge/instructions/inference-gateway/adl/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 | $0.00799 | $0.00799 |
| Opus 5 | $0.00400 | $0.00400 |
| Sonnet 5 | $0.00160 | $0.00160 |
| Haiku 4.5 | $0.00080 | $0.00080 |
Grade A, and why
adl 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 4d 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 — 39 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md
This repository is the source of truth for the ADL (Agent Definition Language) JSON Schema. There is no application code — the only shipped artifact is schema/v1/schema.json (JSON Schema Draft-07, apiVersion: adl.inference-gateway.com/v1). Work here is schema edits plus docs. README.md covers ADL concepts and the manifest format; CONTRIBUTING.md covers setup, versioning, and releases in depth.
Commands
Recommended environment: flox activate (provides task, Node.js, Prettier, ajv). Manual setup: Node.js 24.x, then npm install --no-save ajv@8 ajv-cli@5 ajv-formats@3 — there is no package.json on purpose and the install is a one-off local to the working tree; never commit node_modules/.
task compile— AJV-compile the schema (the exact check CI runs)task validate -- path/to/manifest.yaml— validate a manifest against the schematask format/task format:check— Prettier auto-format / check (CI runsnpx --yes [email protected] --check .)npx ajv compile --spec=draft7 -c ajv-formats -s schema/v1/schema.json— manual fallback without go-task
CI has two checks, both must pass: Compile JSON Schema (AJV) and Check formatting (Prettier). A .githooks/pre-commit hook runs Prettier on staged files; activate once per clone with git config core.hooksPath .githooks. If it blocks a commit, fix with npx [email protected] --write <file>.
Schema versioning contract — the most important rule
Within schema/v1/, only backwards-compatible additions: new optional fields, new definitions, additive enum values. Do not tighten constraints, rename fields, remove fields, or make optional fields required. A breaking change requires a new schema/v2/schema.json with apiVersion: adl.inference-gateway.com/v2; v1 is kept, not removed. Released git tags are immutable — downstream consumers (notably adl-cli) pin to them, so never edit a released tag. For a v2 proposal, open an issue or discussion before editing.
Style
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.
- 4d ago First seen · 39 lines · 799 tokens per session scan A 574f0d219323
adl AGENTS.md is an instructions file published in the GitHub repository inference-gateway/adl (33 stars, last pushed today), licensed Apache-2.0. It adds 799 tokens to every session, about $0.0040 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
noddde CLAUDE.md
Instructions for dogganidhal/noddde, covering noddde — claude development guide, project overview, spec authority principle, monorepo layout (turborepo + yarn) and architecture.
tenets CLAUDE.md
Instructions for bardiakhosravi/tenets, covering claude.md and repository overview.
ddd-architecture-coach CLAUDE.md
Instructions for jed1978/ddd-architecture-coach, covering claude.md, repository nature, editing rules specific to this skill, content architecture and when working in this repo.
fastify-boilerplate AGENTS.md
AGENTS.md instructions for marcoturi/fastify-boilerplate, covering agents.md, project overview, quick reference, architecture and layer boundaries (critical).
appointme CLAUDE.md
Instructions for bravodev-hub/appointme, covering claude.md, build and development commands, running the full stack (recommended), backend only and frontend only.
event-store-adapter-js AGENTS.md
AGENTS.md instructions for j5ik2o/event-store-adapter-js, covering agents.md, 言語, github pull request のモニタリング, $grill-me 実行時の作業判断 and 軽い作業の場合.