dogwood: Instructions file for Codex

AGENTS.md

dogwood AGENTS.md is an instructions file for Codex, OpenCode from dogwood-policy/dogwood. It costs 726 tokens per session, scanned A, original, Apache-2.0.

Project instructions for Dogwood, a package for defining and checking authorization rules, including procedures for its policy files and command-line checks.

In plain words
What is it for?
Creating authorization schemas, defining service and event rules, following the matching workflow, and running Dogwood validation commands.
Why use it?
They help the assistant follow the correct order when setting up authorization and ensure each stage is validated.

Instructions file for CodexOpenCode

Written for Codex and OpenCode: the file is AGENTS.md. Also seen: reads .claude/ paths; mentions AGENTS.md.

This is dogwood-policy/dogwood's own configuration. It tells Codex and OpenCode how to work on dogwood itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything dogwood configures →

Reuse

Borrowing it

Nothing to install: this file belongs to dogwood-policy/dogwood. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/dogwood-policy/dogwood/main/AGENTS.md
Clone the repo
git clone --depth 1 https://github.com/dogwood-policy/dogwood

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 dogwood AGENTS.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/dogwood-policy/dogwood/agents-md/github.svg)](https://agentmods.dev/instructions/dogwood-policy/dogwood/agents-md)
Your own site
<a href="https://agentmods.dev/instructions/dogwood-policy/dogwood/agents-md"><img src="https://agentmods.dev/badge/instructions/dogwood-policy/dogwood/agents-md/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for dogwood AGENTS.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/dogwood-policy/dogwood/agents-md"><img src="https://agentmods.dev/badge/instructions/dogwood-policy/dogwood/agents-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 726 This file is loaded in full into every session.
When invoked 726 The same file — it is already loaded in full.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 5.1 $0.00726 $0.00726
Opus 5 $0.00363 $0.00363
Sonnet 5 $0.00145 $0.00145
Haiku 4.5 $0.00073 $0.00073

Measured 10d ago against content hash 60fbba41de61, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

dogwood 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 10d 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 · 50 lines

How it starts

The opening of the file, as written. The whole thing — 50 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AGENTS.md

Guidance for AI coding agents working in the Dogwood policy-language package. This file is intentionally short; it points to detailed procedures rather than inlining them, so it costs little when it is not relevant.

Working with Dogwood authorization

Setting up Dogwood authorization has a lifecycle, and there is a procedure (a skill under .claude/skills/) for each stage. Follow the one matching what the user is actually doing — each is the single source of truth for its task, references the guide rather than duplicating it, and enforces a mandatory dogwood CLI validation gate. Ignore this section for unrelated requests.

The lifecycle and its skills (dependency order):

  1. Action schema — declare the Cedar .cedarschema: the entity types (principals/resources), one action per tool/operation, and each action's context.input/output/system layout — hand-written or generated from an MCP tools/list manifest. This is the prerequisite for everything else. → .claude/skills/authoring-action-schema/SKILL.md (gate: dogwood schema action schema.cedarschema)
  2. Service schema (only if needed) — the event schema (.dwschema: event kinds, decision vs history points, pins, the max_window look-back cap) and/or information providers (providers.json + Rhai). Optional; defaults sensibly (request/response/error kinds with only request deciding, a universal principal pin, a 24h window cap, no providers, standard macros). → .claude/skills/authoring-service-schema/SKILL.md (gate: dogwood schema event/providers, then composite dogwood validate)
  3. Policies — turn a natural-language authorization requirement ("permit X only if Y", "deny after Z", "no more than N per hour") into a validated .dw policy. → .claude/skills/autoformalize-policies/SKILL.md (gate: dogwood validate policy.dw --policy-schema schema.cedarschema)
  4. Check / replay — validate or replay existing files with the dogwood CLI. → dogwood-docs/guide/12-cli.md

Read the full file on GitHub · 50 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. 10d ago First seen · 50 lines · 726 tokens per session scan A 60fbba41de61

Subscribe to this mod's changes

dogwood AGENTS.md is an instructions file published in the GitHub repository dogwood-policy/dogwood (383 stars, last pushed 29d ago), licensed Apache-2.0. It adds 726 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.

Related

Other instructions, from other repositories

next.js AGENTS.md

AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.

vercel/next.js · 7,296 tokens

codex AGENTS.md

AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.

openai/codex · 5,153 tokens

vscode buildNext.instructions.md

Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).

microsoft/vscode · 6,785 tokens

spec-kit AGENTS.md

AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.

github/spec-kit · 7,104 tokens

vscode oss-third-party-notices.instructions.md

Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).

microsoft/vscode · 5,001 tokens

langchain AGENTS.md

AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.

langchain-ai/langchain · 4,469 tokens