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/thegreencedar/codex-autoresearch/agents-mdgit clone --depth 1 https://github.com/TheGreenCedar/codex-autoresearchWrote 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/thegreencedar/codex-autoresearch/agents-md)<a href="https://agentmods.dev/instructions/thegreencedar/codex-autoresearch/agents-md"><img src="https://agentmods.dev/badge/instructions/thegreencedar/codex-autoresearch/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 | $0.02034 | $0.02034 |
| Opus 5 | $0.01017 | $0.01017 |
| Sonnet 5 | $0.00407 | $0.00407 |
| Haiku 4.5 | $0.00203 | $0.00203 |
Grade A, and why
codex-autoresearch 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 5d 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 — 131 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md
Purpose And Scope
- Optimize for evidence, resumability, and small reviewable diffs.
- This file is the repository-maintainer contract. It is not the Autoresearch operator manual, a command inventory, or a detailed architecture index.
- The repository root is a wrapper. The product package is
plugins/codex-autoresearch. - Before running Git, installs, builds, tests, release work, or Autoresearch commands, identify the owning repository, package root, and target
--cwd. - Start mutation work with
git status --short --branch. Preserve unrelated changes and do not broaden cleanup to make the tree convenient. - Package scripts live in
plugins/codex-autoresearch/package.json; root npm commands are not product evidence unless root scripts are added later. - Use the repository checkout when changing Autoresearch itself. Treat source behavior and installed-plugin behavior as different until their version and built-entrypoint fingerprint agree.
Canonical Sources
Read the smallest relevant owner before changing a contract:
| Question | Canonical source |
|---|---|
| Public promise, installation, and first run | root README.md |
| Codex operator behavior | plugins/codex-autoresearch/skills/codex-autoresearch/SKILL.md and its relevant reference |
| Documentation audiences and invariant product facts | plugins/codex-autoresearch/docs/STYLE.md |
| Implementation ownership and package shape | plugins/codex-autoresearch/docs/architecture.md |
| Shared CLI, report, and dashboard decisions | plugins/codex-autoresearch/docs/control-plane.md |
| Development, checks, packaging, and release | plugins/codex-autoresearch/docs/maintainers.md |
| Command names, arguments, policies, help, handlers, and compatibility | plugins/codex-autoresearch/lib/command-table.ts |
| User-facing release history | root CHANGELOG.md |
| Executable package commands | plugins/codex-autoresearch/package.json |
| Release and branch behavior | .github/workflows/ |
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.
- 5d ago First seen · 131 lines · 2,034 tokens per session scan A b61da3c2260d
codex-autoresearch AGENTS.md is an instructions file published in the GitHub repository TheGreenCedar/codex-autoresearch (836 stars, last pushed 6d ago), licensed Apache-2.0. It adds 2,034 tokens to every session, about $0.0102 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
openlegion CLAUDE.md
Claude Code instructions for openlegion-ai/openlegion, covering claude.md — engine, commands & testing, git workflow, work patterns and architecture.
openlegion AGENTS.md
AGENTS.md instructions for openlegion-ai/openlegion, a project described as: Secure autonomous AI agent framework and platform. Build AI teams by describing what you want. Orchestrate agents that can do everything a human can do.
OwnPilot AGENTS.md
Instructions for ownpilot/OwnPilot, covering ownpilot, architecture, key patterns, commands and tech stack.
nightshift AGENTS.md
AGENTS.md instructions for orwa-mahmoud/nightshift: AI-assisted contributions are welcome. The same correctness, security, licensing, testing, and quality standards apply regardless of which tools are used.
SeekMoney-ai CLAUDE.md
Claude Code instructions for zykooooooooo/SeekMoney-ai, covering claude.md, project overview, development commands, development and production.
Polaris AGENTS.md
AGENTS.md instructions for sponge-b0b/Polaris, covering agents.md, purpose and authority, domain vocabulary, coding conduct and secrets.