What is AutoADHD AGENTS.md?

Rules for AI agents working in the AutoADHD knowledge vault, including which focused instructions to read before editing notes or code. A vault is a structured collection of notes and related files.

Choosing instructions for vault notes, inbox processing, architecture, or code changes, while preserving raw transcripts and following the project's linking and language rules.

They prevent accidental edits to protected content and direct the agent to the right procedures for each type of work.

How uetzel/AutoADHD configures Codex and OpenCode

Reuse

Borrowing it

Nothing to install: this file belongs to uetzel/AutoADHD. 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/uetzel/AutoADHD/main/AGENTS.md

Clone the repo

git clone --depth 1 https://github.com/uetzel/AutoADHD

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.

README.md

[![agentmods](https://agentmods.dev/badge/instructions/uetzel/autoadhd/agents-md/github.svg)](https://agentmods.dev/instructions/uetzel/autoadhd/agents-md)

Your own site

<a href="https://agentmods.dev/instructions/uetzel/autoadhd/agents-md"><img src="https://agentmods.dev/badge/instructions/uetzel/autoadhd/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.

Your own site · 80×15

<a href="https://agentmods.dev/instructions/uetzel/autoadhd/agents-md"><img src="https://agentmods.dev/badge/instructions/uetzel/autoadhd/agents-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 1,628 This file is loaded in full into every session.

When invoked 1,628 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.

Model	Per session	Once invoked
Fable 5.1	$0.01628	$0.01628
Opus 5.5	$0.00651	$0.00651
Sonnet 5.5	$0.00326	$0.00326
Haiku 4.5	$0.00163	$0.00163

Measured 2mo ago against content hash 014e88803002, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

AutoADHD 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 2mo 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 · 146 lines

How it starts

The opening of the file, as written. The whole thing — 146 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AGENTS.md

Rules for any AI agent (Claude, Codex, or future systems) operating in this vault.

Read CLAUDE.md for the full protocol. Read Meta/Architecture.md for the system blueprint. Read Meta/Engineering.md before making code, script, test, or CI changes.

SKILLS (load the right one for your task)

Instead of reading all of CLAUDE.md, load the focused skill for what you're doing:

Task	Skill to read
Creating or editing any vault note	`.claude/skills/vault-writer/SKILL.md`
Processing inbox notes → Canon entries	`.claude/skills/vault-extractor/SKILL.md`
Architecture or system design	`Meta/Architecture.md`
Code or script changes	`Meta/Engineering.md`

Load the skill BEFORE starting the task. It has everything you need in ~200 lines instead of 300+.

CORE RULES

Git is the safety net. Every change is tracked. Mistakes are revertable.
Raw transcripts are sacred. Never edit content under # Raw in Inbox notes.
Don't fabricate. If unsure, say so and ask.
Use wikilinks. [[Name]] is how structure is built.
English for Canon. Raw content stays in its original language.
Locked fields are untouchable. If a note has a locked: array, those fields cannot be changed by any agent.
Provenance is mandatory. Every fact must trace back to a source.
Review gates are structural. See Meta/Architecture.md for the three tiers.

WRITE PERMISSIONS

All folders are writable
Exception: never edit # Raw sections in Inbox notes
Exception: never change locked fields

ENGINEERING RULES

For code and tooling changes, follow TDD by default: test first, then implementation, then refactor.
Run make check before considering code work complete.
Use branches for structural changes to scripts, tests, CI, and automation.
Keep agent content runs and code/tooling changes separate.
Prefer small diffs and small commits over mixed changes.

FOR OPENAI CODEX (GPT-5.4)

Read the full file on GitHub · 146 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.

2mo ago First seen · 146 lines · 1,628 tokens per session scan A 014e88803002

Subscribe to this mod's changes

AutoADHD AGENTS.md is an instructions file published in the GitHub repository uetzel/AutoADHD (25 stars, last pushed 6mo ago), licensed MIT. It adds 1,628 tokens to every session, about $0.0065 per session on Opus 5.5. 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.

AutoADHD AGENTS.md next to 6 instructions from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
AutoADHD AGENTS.mduetzel/AutoADHD	Instructions file	25	6mo ago	MIT	A	1,628	Codex, OpenCode
vscode buildNext.instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	9,719	GitHub Copilot
next.js AGENTS.mdvercel/next.js	Instructions file	143k	yesterday	MIT	A	7,461	Codex, OpenCode
langchain AGENTS.mdlangchain-ai/langchain	Instructions file	149k	yesterday	MIT	A	4,680	Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	5,516	GitHub Copilot
vscode copilot-instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	3,093	GitHub Copilot
deepseek-harness AGENTS.mddeepseek-ai/deepseek-harness	Instructions file	274k	2d ago	MIT	A	4,313	Codex, OpenCode

AutoADHD: Instructions file for Codex