agentmods.dev

codex-docs AGENTS.md

Repository instructions for a project that periodically mirrors Codex documentation and related reference files.

In plain words
What is it for?
They help run setup, linting, tests, synchronization, idempotence checks, and feature-flag validation with the project's preferred commands.
Why use it?
They clarify which files are generated, where to fix synchronization problems, and how to validate changes safely.

Instructions file for CodexOpenCode

5 2d ago A scan 749 tokens original MIT
View the source file chenrui333/codex-docs
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/chenrui333/codex-docs/agents-md
Clone the repo
git clone --depth 1 https://github.com/chenrui333/codex-docs

Made for: Codex, OpenCode.

Per session 749 This file is loaded in full into every session.
When invoked 749 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 $0.00749 $0.00749
Opus 5 $0.00375 $0.00375
Sonnet 5 $0.00150 $0.00150
Haiku 4.5 $0.00075 $0.00075

Measured 2d ago against content hash a69162d0c8b0, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

codex-docs 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 · 56 lines

How it starts

The opening of the file, as written. The whole thing — 56 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AGENTS Notes

Scope

  • This repository is a periodic mirror for Codex-related docs and references.
  • Keep changes focused on sync automation, output quality, and release hygiene.

Generated content boundaries

  • Treat docs/codex_capabilities.json, docs/codex_cli_surface.json, docs/freshness.json, docs/developers.openai.com/**, docs/learn.chatgpt.com/**, docs/feature-flags/**, docs/github.openai.com/**, docs/platform.openai.com/**, dot_codex/skills/dot_system/**, and system_prompts/codex-cli/** as generated output.
  • Do not hand-edit mirrored docs, skills, or prompts unless doing a temporary emergency fix.
  • If an output problem exists, fix scripts/fetch_codex_docs.py instead.

Local workflow

  1. Preferred command runner: use just.
  2. Setup environment:
    • just setup
  3. Run offline quality checks:
    • just lint
    • just test
  4. Run sync:
    • just sync
  5. Validate local idempotence + scope:
    • just check
  6. For feature-flag snapshot changes:
    • just feature-flags
    • just check-feature-flags

Validation expectations

  • After changing sync logic, run sync twice and confirm second run is idempotent (no new diffs).
  • Verify docs/docs_manifest.json and docs/sync_summary.json are updated consistently, including Codex CLI version metadata for CLI-backed changes.
  • Verify docs/source_coverage.json updates consistently and includes expected counts, including complete ChatGPT Learn discovery and mirror coverage.
  • Keep weekly/YYYY-MM-DD.md generation deterministic for unchanged inputs.
  • For feature-flag automation or source-input changes, verify docs/feature-flags/** with just check-feature-flags; snapshots must use the source commit resolved from the CLI release tag.

CI behavior

  • .github/workflows/update-docs.yml is a fail-closed direct-push sync to main; it must not commit partial-source output.
  • Keep direct-push model unless explicitly requested to move to PR-based flow.
  • .github/workflows/release.yml creates versioned releases from the root VERSION file.
  • .github/workflows/propose-version-bump.yml is an optional monthly/manual helper that opens a VERSION bump PR.
  • .github/workflows/update-feature-flags.yml keeps docs/feature-flags/** snapshots fresh and enforces freshness on related pull requests.

Read the full file on GitHub · 56 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 · 56 lines · 749 tokens per session scan A a69162d0c8b0

Subscribe to this mod's changes

codex-docs AGENTS.md is an instructions file published in the GitHub repository chenrui333/codex-docs (5 stars, last pushed 2d ago), licensed MIT. It adds 749 tokens to every session, about $0.0037 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.

ProductivityTestingWriting and docscodexcodex-cliopenai
Related

Other instructions, from other repositories

codexia AGENTS.md

Instructions for milisp/codexia, covering agents.md, project info, project tech, common commands and project structure.

milisp/codexia · 656 tokens

CodexPotter AGENTS.md

Instructions for breezewish/CodexPotter, covering repository guidelines, workflow principles, engineering rules, core principles: simplicity & readability and better maintainability.

breezewish/CodexPotter · 306 tokens

codex-howto AGENTS.md

Instructions for Phelan164/codex-howto, covering repository guidance, purpose, editing rules, validation and definition of done.

Phelan164/codex-howto · 285 tokens

vibe-codex AGENTS.md

Instructions for kks0488/vibe-codex, covering vibe-codex (codex cli), repo conventions, openai docs and handy commands.

kks0488/vibe-codex · 454 tokens

codex-status-bar AGENTS.md

Instructions for yuriipalam/codex-status-bar, covering repository instructions, engineering expectations, verification and release procedure.

yuriipalam/codex-status-bar · 862 tokens

ctxwise AGENTS.md

Instructions for FramY2/ctxwise, a project described as: CtxWise — see and control what Codex loads. Local-first context audit, profiles, drift detection, and honest token receipts.

FramY2/ctxwise · 144 tokens