Chatgpt-Codex-App-Plus AGENTS.md

Chatgpt-Codex-App-Plus AGENTS.md is an instructions file for Codex, OpenCode from phenomenoner/Chatgpt-Codex-App-Plus. It costs 361 tokens per session, scanned A, original, MIT.

A set of instructions for coding agents contributing to the Chatgpt-Codex-App-Plus repository. It defines the project boundary, trusted sources, change rules, and checks to run before publishing.

In plain words
What is it for?
Maintaining the repository, refreshing approved public sources, adding regression tests, reviewing scanner or exporter changes, and checking work before publication.
Why use it?
It helps agents avoid exposing private project data, changing unrelated work, or claiming a change is ready without verification.

Instructions file for CodexOpenCode

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/phenomenoner/chatgpt-codex-app-plus/agents-md
Clone the repo
git clone --depth 1 https://github.com/phenomenoner/Chatgpt-Codex-App-Plus

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 Chatgpt-Codex-App-Plus AGENTS.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/phenomenoner/chatgpt-codex-app-plus/agents-md.svg)](https://agentmods.dev/instructions/phenomenoner/chatgpt-codex-app-plus/agents-md)
Your own site
<a href="https://agentmods.dev/instructions/phenomenoner/chatgpt-codex-app-plus/agents-md"><img src="https://agentmods.dev/badge/instructions/phenomenoner/chatgpt-codex-app-plus/agents-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 361 This file is loaded in full into every session.
When invoked 361 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 $0.00361 $0.00361
Opus 5 $0.00180 $0.00180
Sonnet 5 $0.00072 $0.00072
Haiku 4.5 $0.00036 $0.00036

Measured 3d ago against content hash ed2db6849ba3, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

Chatgpt-Codex-App-Plus 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 3d 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 · 27 lines

What it actually says

Repository agent instructions

Scope

  • Keep this repository public-safe, self-contained, and useful to readers with no private project context.
  • Preserve unrelated work. Do not publish, tag, change repository visibility, or modify scheduled automation unless the active user request explicitly authorizes it.

Source and provenance

  • manifest/public-sources.json is the only authority for local source export. Do not broaden it automatically.
  • Vendor original components maintained here. Prefer a versioned pointer when a canonical public repository already exists.
  • Never import authentication, sessions, memories, goals, logs, attachments, project trust paths, backups, local plugin caches, or connector state.

Changes and verification

  • Edit authored repository files intentionally. Use scripts/public_sync.py sync --apply only for manifest-authorized mechanical refreshes.
  • For an existing exporter or scanner defect, add a discriminating regression and demonstrate fail-first when the old behavior is safely reproducible. Credential findings must remain non-exemptible.
  • Before a completion or publication claim, run the focused repository and vendored component checks that can falsify the changed behavior, python scripts/public_sync.py validate, and git diff --check.
  • Run the full repository suite only when exporter/scanner infrastructure, shared schemas or catalogs, release-wide behavior, or a remaining coverage gap makes the blast radius repository-wide.
  • Read the full public diff after scanners pass. Replace private shorthand with behavior, impact, verification, and honest limitations.

Publishing

  • Stage explicit files in a mixed worktree. Do not use a broad add when unrelated files exist.
  • Keep README, ABOUT, repository description, topics, catalog, and notices aligned when the public positioning changes.
  • Do not claim official OpenAI, Anthropic, or upstream-project status.
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. 3d ago First seen · 27 lines · 361 tokens per session scan A ed2db6849ba3

Subscribe to this mod's changes

Chatgpt-Codex-App-Plus AGENTS.md is an instructions file published in the GitHub repository phenomenoner/Chatgpt-Codex-App-Plus (2 stars, last pushed 9d ago), licensed MIT. It adds 361 tokens to every session, about $0.0018 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.

Related

Other instructions, from other repositories