autocodex: Instructions file for Codex

AGENTS.md

autocodex AGENTS.md is an instructions file for Codex, OpenCode from oodaris/autocodex. It costs 821 tokens per session, scanned A, original, MIT.

Repository instructions for Autocodex, including its Beads issue-tracking setup, Dolt data store, synchronization process, and commands for managing work.

In plain words
What is it for?
Use them when starting work in the repository, finding available issues, claiming or closing tasks, checking Beads and Dolt status, or setting up a fresh clone.
Why use it?
They explain where the authoritative issue data is kept and prevent developers from relying on outdated or incorrect synchronization steps.

Instructions file for CodexOpenCode

Written for Codex and OpenCode: the file is AGENTS.md. Also seen: mentions Codex.

This is oodaris/autocodex's own configuration. It tells Codex and OpenCode how to work on autocodex 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 autocodex configures →

Reuse

Borrowing it

Nothing to install: this file belongs to oodaris/autocodex. 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/oodaris/autocodex/main/AGENTS.md
Clone the repo
git clone --depth 1 https://github.com/oodaris/autocodex

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 autocodex AGENTS.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/oodaris/autocodex/agents-md/github.svg)](https://agentmods.dev/instructions/oodaris/autocodex/agents-md)
Your own site
<a href="https://agentmods.dev/instructions/oodaris/autocodex/agents-md"><img src="https://agentmods.dev/badge/instructions/oodaris/autocodex/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 autocodex AGENTS.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/oodaris/autocodex/agents-md"><img src="https://agentmods.dev/badge/instructions/oodaris/autocodex/agents-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 821 This file is loaded in full into every session.
When invoked 821 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 $0.00821 $0.00821
Opus 5.5 $0.00328 $0.00328
Sonnet 5.5 $0.00164 $0.00164
Haiku 4.5 $0.00082 $0.00082

Measured 2mo ago against content hash 6fc156500509, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

autocodex 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 · 65 lines

How it starts

The opening of the file, as written. The whole thing — 65 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Agent Instructions

This project uses bd (beads) for issue tracking. Run bd onboard to get started.

Repo note: this repo's .beads is on the Dolt backend. Verify with bd info --json and bd dolt show --json (if connection_ok is false, run dolt sql-server --data-dir "$(pwd)/.beads/dolt" --host 127.0.0.1 --port 3307).

Beads sync-branch: this repo is configured to sync beads data via the dedicated beads-sync branch (see .beads/config.yaml).

  • bd sync is deprecated/no-op on bd 0.56.1 in this repo; do not rely on it for state propagation.
  • Canonical issue state is Dolt (.beads/dolt). Treat .beads/issues.jsonl as an optional compatibility mirror only.
  • In a fresh clone, run bd migrate sync beads-sync once if you need the local sync-branch worktree (.git/beads-worktrees/beads-sync).

Quick Reference

bd onboard            # One-time setup for this clone (hooks, config, etc.)
bd migrate sync beads-sync  # One-time: set up sync-branch worktree (if needed)
bd ready              # Find available work
bd show <id>          # View issue details
bd update <id> --status in_progress  # Claim work
bd close <id>         # Complete work
bd dolt test --json   # Validate Dolt connectivity for this repo

autocodex defaults (for agents)

Use autocodex bootstrap when you want autonomy ready immediately.

  • Creates autocodex.yaml if missing (falls back to the embedded config if config.example.yaml is absent).
  • Creates autonomy templates/schemas in docs/.
  • Creates Harness v2 policy assets when missing (.codex/, docs/agents/, scripts/dev/harness-cli-preflight.sh, and docs/runbooks/harness-cli-preflight.md).
  • Writes a minimal skill pack to skills/ and expects skills.paths to include skills.
  • Does not overwrite existing files unless --force is provided.
  • If bd is missing, bead creation/updates are skipped with a warning.
  • For contributor onboarding, prefer autocodex bootstrap --profile max_capability --ready.

Read the full file on GitHub · 65 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. 2mo ago First seen · 65 lines · 821 tokens per session scan A 6fc156500509

Subscribe to this mod's changes

autocodex AGENTS.md is an instructions file published in the GitHub repository oodaris/autocodex (16 stars, last pushed 8mo ago), licensed MIT. It adds 821 tokens to every session, about $0.0033 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.

Related

autocodex AGENTS.md compared with instructions from other repositories

autocodex AGENTS.md next to 6 instructions from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
autocodex AGENTS.mdoodaris/autocodexInstructions file168mo agoMITA821Codex, OpenCode
vscode buildNext.instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA9,719GitHub Copilot
next.js AGENTS.mdvercel/next.jsInstructions file143kyesterdayMITA7,461Codex, OpenCode
langchain AGENTS.mdlangchain-ai/langchainInstructions file149kyesterdayMITA4,680Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA5,516GitHub Copilot
vscode copilot-instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA3,093GitHub Copilot
deepseek-harness AGENTS.mddeepseek-ai/deepseek-harnessInstructions file274k2d agoMITA4,313Codex, OpenCode