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.
npx agentmods add instructions/oodaris/autocodex/agents-mdgit clone --depth 1 https://github.com/oodaris/autocodexWrote 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.
[](https://agentmods.dev/instructions/oodaris/autocodex/agents-md)<a href="https://agentmods.dev/instructions/oodaris/autocodex/agents-md"><img src="https://agentmods.dev/badge/instructions/oodaris/autocodex/agents-md.svg" alt="Measured on agentmods" height="20"></a>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 | $0.00821 | $0.00821 |
| Opus 5 | $0.00411 | $0.00411 |
| Sonnet 5 | $0.00164 | $0.00164 |
| Haiku 4.5 | $0.00082 | $0.00082 |
Grade A, and why
autocodex AGENTS.md scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 4d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 65 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Agent Instructions
This project uses bd (beads) for issue tracking. Run bd onboard to get started.
Repo note: this repo's .beads is on the Dolt backend. Verify with bd info --json and bd dolt show --json (if connection_ok is false, run dolt sql-server --data-dir "$(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 syncis deprecated/no-op onbd 0.56.1in this repo; do not rely on it for state propagation.- Canonical issue state is Dolt (
.beads/dolt). Treat.beads/issues.jsonlas an optional compatibility mirror only. - In a fresh clone, run
bd migrate sync beads-synconce 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.yamlif missing (falls back to the embedded config ifconfig.example.yamlis absent). - Creates autonomy templates/schemas in
docs/. - Creates Harness v2 policy assets when missing (
.codex/,docs/agents/,scripts/dev/harness-cli-preflight.sh, anddocs/runbooks/harness-cli-preflight.md). - Writes a minimal skill pack to
skills/and expectsskills.pathsto includeskills. - Does not overwrite existing files unless
--forceis provided. - If
bdis missing, bead creation/updates are skipped with a warning. - For contributor onboarding, prefer
autocodex bootstrap --profile max_capability --ready.
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.
- 4d ago First seen · 65 lines · 821 tokens per session scan A 6fc156500509
autocodex AGENTS.md is an instructions file published in the GitHub repository oodaris/autocodex (16 stars, last pushed 6mo ago), licensed MIT. It adds 821 tokens to every session, about $0.0041 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.
Other instructions, from other repositories
safeclaw CLAUDE.md
Instructions for ykdojo/safeclaw, covering safeclaw, testing end to end, multiple sessions, mounting local projects and research sessions.
code-conductor CLAUDE.md
Instructions for ryanmac/code-conductor, covering claude.md, project overview, documentation map, key development commands and running tests.
pi-goals AGENTS.md
Instructions for transcendr/pi-goals, covering agents — pi-goals, extension architecture, required quality gate, repo artifact hygiene and solo scratchpads.
myace CLAUDE.md
Claude Code instructions for niels-emmer/myace, a project described as: MyACE makes your AI coding agent's rules, skills, and workflows portable.
TaskWing CLAUDE.md
Claude Code instructions for josephgoksu/TaskWing, covering claude.md, cli binaries, project identity, how ai tools talk to taskwing (no mcp) and build & test commands.
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).