adc AGENTS.md

Repository instructions for a documentation project that defines a convention for recording comments about agent decisions.

In plain words
What is it for?
Use them to update the specification and examples, run Markdown checks, inspect formatting, and review documentation changes.
Why use it?
They clarify where documentation belongs and how to check Markdown changes before submitting them.

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

Made for: Codex, OpenCode.

Per session 591 This file is loaded in full into every session.
When invoked 591 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 $0.00591 $0.00591
Opus 5 $0.00296 $0.00296
Sonnet 5 $0.00118 $0.00118
Haiku 4.5 $0.00059 $0.00059

Measured 2d ago against content hash b1467d787864, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

adc 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 · 59 lines

How it starts

The opening of the file, as written. The whole thing — 59 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Repository Guidelines

Project Structure & Module Organization

This is a documentation-first repository for the Agent Decision Comments convention. README.md is the canonical specification: it defines the four directives, their format, scope, examples, review workflow, and current version. LICENSE contains the MIT license. There are currently no source, test, generated, or asset directories. Keep new documentation at the repository root unless a larger collection clearly warrants a focused directory such as examples/.

Build, Test, and Development Commands

This repository produces no build artifact. Markdown linting is its primary CI check. Run these commands before submitting a change:

  • npx --yes [email protected] --config .markdownlint.jsonc "**/*.md" runs the same linter version as CI.
  • git diff --check detects trailing whitespace and malformed patches.
  • rg '^#{1,6} ' README.md AGENTS.md reviews the Markdown heading hierarchy.
  • git diff -- README.md AGENTS.md gives a focused review of documentation changes.

Also render changed Markdown in a previewer and verify that fenced examples, lists, and headings display correctly.

Coding Style & Naming Conventions

Write concise Markdown with ATX headings (## Heading), fenced code blocks with language tags, and hyphenated bullets. Follow the existing prose style: short paragraphs, direct present-tense statements, and one sentence per line when practical. Use the exact lowercase directive labels decision:, invariant:, assumption:, and tradeoff:. Examples should demonstrate non-obvious rationale rather than restate code behavior. The Markdownlint configuration excludes code blocks from MD013; directives must remain on one physical line. In docstrings and documentation comments, place normal prose before the directives with a blank line between them. Use ordinary comments for directive-only examples.

Testing Guidelines

The workflow in .github/workflows/markdownlint.yml lints every Markdown file on pushes and pull requests. Confirm every new example matches the format and scope rules in README.md, uses valid syntax for its declared language, and does not contradict another section. Run the local lint command and git diff --check, then inspect the rendered output.

Read the full file on GitHub · 59 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 · 59 lines · 591 tokens per session scan A b1467d787864

Subscribe to this mod's changes

adc AGENTS.md is an instructions file published in the GitHub repository dbrattli/adc (5 stars, last pushed 16d ago), licensed MIT. It adds 591 tokens to every session, about $0.0030 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.