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/ningzimu/codex-gpt-image/agents-mdgit clone --depth 1 https://github.com/ningzimu/codex-gpt-imageWrote 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/ningzimu/codex-gpt-image/agents-md)<a href="https://agentmods.dev/instructions/ningzimu/codex-gpt-image/agents-md"><img src="https://agentmods.dev/badge/instructions/ningzimu/codex-gpt-image/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 | $0.00290 | $0.00290 |
| Opus 5 | $0.00145 | $0.00145 |
| Sonnet 5 | $0.00058 | $0.00058 |
| Haiku 4.5 | $0.00029 | $0.00029 |
Grade A, and why
codex-gpt-image 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.
What it actually says
AGENTS.md
Contribution Flow
- All non-trivial changes should go through a pull request.
- PR titles must follow Conventional Commit style, for example:
feat: add image edit optionfix: handle expired Codex authdocs: clarify Claude Code installation
- Commit messages, PR titles, changelog entries, and release notes must be written in English.
Changelog
- User-visible changes must update
CHANGELOG.md. - Add unreleased entries under
## Unreleased. - Use one of these sections:
### Features### Improvements### Fixes### Documentation
- Changelog entries must be written in English.
Release Process
- Versions use SemVer.
- Git tags must use a leading
v, for examplev0.1.0. - GitHub Releases are generated from the matching
CHANGELOG.mdversion section. - Do not write GitHub Release notes manually unless updating an existing release body to match
CHANGELOG.md.
Verification
- Before opening a PR, verify changed GitHub workflow YAML parses when practical.
- For workflow shell snippets, run a syntax check such as
bash -nwhen practical. - For script changes, run
python3 -m py_compile skills/codex-gpt-image/scripts/codex_gpt_image.py.
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 · 35 lines · 290 tokens per session scan A a4024f3ca7a2
codex-gpt-image AGENTS.md is an instructions file published in the GitHub repository ningzimu/codex-gpt-image (55 stars, last pushed 2mo ago), licensed MIT. It adds 290 tokens to every session, about $0.0014 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
codex-ppt-skill AGENTS.md
Instructions for ningzimu/codex-ppt-skill, covering agents.md, contribution flow, changelog, release process and verification.
donna-starter AGENTS.md
AGENTS.md instructions for AtlasOmnia/donna-starter, covering agent operating principles, behavior, autonomy — don't pester and working style.
gomaa CLAUDE.md
Claude Code instructions for M4F-S/gomaa, covering 🎯 agent operational directives & execution protocol, role & objective, core rules and execution protocol.
fable-method AGENTS.md
Instructions for ardhaecosystem/fable-method, covering agents.md - the fable method, triviality gate (run first), fit gate (run next, before step 0), step 0 - classify the ask and step 1 - define done.
hermes-codex-operator AGENTS.md
Instructions for AlekseiUL/hermes-codex-operator, a project described as: A local-first operator that turns plain-language ideas into tracked, verified Codex work—planned by Hermes, executed by Codex, and explained back to you.
portable-agent-skills AGENTS.md
Instructions for ch1109/portable-agent-skills: Read CONTRIBUTING.md before changing a Skill.