codex-settings AGENTS.md

Repository instructions for a Codex settings project containing shared configuration, reusable skills, tests, and plugin packaging files.

In plain words
What is it for?
Use them when editing Codex profiles, skills, tests, plugin manifests, marketplace entries, or repository configuration.
Why use it?
They explain the project structure, required naming and configuration conventions, and which validation checks apply to different changes.

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/feiskyer/codex-settings/agents-md
Clone the repo
git clone --depth 1 https://github.com/feiskyer/codex-settings

Made for: Codex, OpenCode.

Per session 1,236 This file is loaded in full into every session.
When invoked 1,236 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 $0.01236 $0.01236
Opus 5 $0.00618 $0.00618
Sonnet 5 $0.00247 $0.00247
Haiku 4.5 $0.00124 $0.00124

Measured 2d ago against content hash 9a71bc51cb56, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

codex-settings 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 · 84 lines

How it starts

The opening of the file, as written. The whole thing — 84 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Repository Guidelines

Repository Structure

  • config.toml is the shared Codex CLI configuration and points to the local copilot-gateway provider at localhost:4141.
  • Root-level *.config.toml files are optional Codex Profiles (chatgpt, azure, github-copilot, and openrouter). Keep the <name>.config.toml naming required by codex --profile <name>.
  • skills/<name>/SKILL.md contains reusable workflows. Put deterministic helpers in scripts/, detailed references in references/, UI metadata in agents/openai.yaml, and offline regression tests in tests/.
  • .codex-plugin/plugin.json packages the existing root skills/ tree as the codex-settings Plugin without duplicating it.
  • .agents/plugins/marketplace.json exposes the repository root as the Plugin source.
  • skills/github-fix-issue/ and skills/github-review-pr/ replace the former GitHub Custom Prompts. Do not recreate duplicate workflows under prompts/.
  • litellm_config.yaml is only for the optional GitHub Copilot through LiteLLM profile. It is not the backend used by the default config.toml.

Validation Commands

Run checks that match the files you changed. The standard offline suite is:

# TOML syntax
python3 -c 'import pathlib, tomllib; [tomllib.loads(p.read_text()) for p in pathlib.Path(".").glob("**/*.toml")]'

# Plugin package and marketplace
python3 -m json.tool .codex-plugin/plugin.json >/dev/null
python3 -m json.tool .agents/plugins/marketplace.json >/dev/null
python3 ~/.codex/skills/.system/plugin-creator/scripts/validate_plugin.py .

# Skill structure
for skill in skills/*; do
  test ! -f "$skill/SKILL.md" || \
    python3 ~/.codex/skills/.system/skill-creator/scripts/quick_validate.py "$skill"
done

# Python scripts and offline tests
python3 -m compileall -q skills
ruff check skills
for test_dir in skills/*/tests; do
  test ! -d "$test_dir" || python3 -m unittest discover -s "$test_dir" -v
done

# Bundled shell and JavaScript helpers
bash -n skills/brainstorming/scripts/start-server.sh \
  skills/brainstorming/scripts/stop-server.sh \
  scripts/test-plugin-install.sh \
  scripts/update-codex-plugins.sh \
  scripts/test-update-codex-plugins.sh
bash scripts/test-update-codex-plugins.sh
node --check skills/brainstorming/scripts/server.cjs
node --check skills/brainstorming/scripts/helper.js

Read the full file on GitHub · 84 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 · 84 lines · 1,236 tokens per session scan A 9a71bc51cb56

Subscribe to this mod's changes

codex-settings AGENTS.md is an instructions file published in the GitHub repository feiskyer/codex-settings (236 stars, last pushed 19d ago), licensed MIT. It adds 1,236 tokens to every session, about $0.0062 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.