adl AGENTS.md

adl AGENTS.md is an instructions file for Codex, OpenCode from inference-gateway/adl. It costs 799 tokens per session, scanned A, original, Apache-2.0.

Contributor instructions for ADL, a JSON Schema that defines the Agent Definition Language manifest format. JSON Schema is a machine-readable way to describe and validate the structure of JSON data.

In plain words
What is it for?
Use them to edit the schema, validate ADL manifests, compile the schema with AJV, check formatting, and follow the project’s versioning and contribution rules.
Why use it?
They identify the schema as the project’s main product and provide the exact checks needed to catch invalid or incorrectly formatted changes.

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/inference-gateway/adl/agents-md
Clone the repo
git clone --depth 1 https://github.com/inference-gateway/adl

Made for: Codex, OpenCode.

Wrote 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.

agentmods badge for adl AGENTS.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/inference-gateway/adl/agents-md.svg)](https://agentmods.dev/instructions/inference-gateway/adl/agents-md)
Your own site
<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>
Per session 799 This file is loaded in full into every session.
When invoked 799 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 $0.00799 $0.00799
Opus 5 $0.00400 $0.00400
Sonnet 5 $0.00160 $0.00160
Haiku 4.5 $0.00080 $0.00080

Measured 4d ago against content hash 574f0d219323, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

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.

AGENTS.md · 39 lines

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 schema
  • task format / task format:check — Prettier auto-format / check (CI runs npx --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

Read the full file on GitHub · 39 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. 4d ago First seen · 39 lines · 799 tokens per session scan A 574f0d219323

Subscribe to this mod's changes

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.