dotagents AGENTS.md

A project instruction file for AI coding agents maintaining dotagents, a vendor-neutral convention for organizing context used by coding agents.

In plain words
What is it for?
It is for routing work to the relevant contribution guide, terminology, decisions, specifications, review persona, and validation instructions.
Why use it?
It directs agents to the right project documents before changing terminology, proposals, documentation, or examples, reducing inconsistent edits.

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/bgreenwell/dotagents/agents-md
Clone the repo
git clone --depth 1 https://github.com/bgreenwell/dotagents

Made for: Codex, OpenCode.

Per session 185 This file is loaded in full into every session.
When invoked 185 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 $0.00185 $0.00185
Opus 5 $0.00093 $0.00093
Sonnet 5 $0.00037 $0.00037
Haiku 4.5 $0.00018 $0.00018

Measured 2d ago against content hash 7f416035ec7b, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

dotagents 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 · 21 lines

What it actually says

AGENTS.md

Project purpose

You are maintaining dotagents, a draft, vendor-neutral convention for organizing project context for AI coding agents.

Prioritize clarity, interoperability, safety, and consistency between the proposal and its checked-in examples.

Context routing

  • Before changing documentation or examples: READ CONTRIBUTING.md.
  • When checking release or version history: READ CHANGELOG.md.
  • When changing terminology or directory semantics: READ docs/terminology.md.
  • When making a structural or naming decision: CONSULT docs/decisions.md.
  • When working on an active proposal: CHECK docs/specs/README.md.
  • When reviewing the convention: ADOPT .agents/personas/standards-reviewer.md.

Validation

  • After changing this router or routed files, use .agents/skills/validate-context-routes/SKILL.md.
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 · 21 lines · 185 tokens per session scan A 7f416035ec7b

Subscribe to this mod's changes

dotagents AGENTS.md is an instructions file published in the GitHub repository bgreenwell/dotagents (87 stars, last pushed 1mo ago), licensed MIT. It adds 185 tokens to every session, about $0.0009 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.