What is codex-settings AGENTS.md?

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

Use them when editing Codex profiles, skills, tests, plugin manifests, marketplace entries, or repository configuration.

They explain the project structure, required naming and configuration conventions, and which validation checks apply to different changes.

How feiskyer/codex-settings configures Codex and OpenCode

Reuse

Borrowing it

Nothing to install: this file belongs to feiskyer/codex-settings. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file

curl -O https://raw.githubusercontent.com/feiskyer/codex-settings/main/AGENTS.md

Clone the repo

git clone --depth 1 https://github.com/feiskyer/codex-settings

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.

README.md

[![agentmods](https://agentmods.dev/badge/instructions/feiskyer/codex-settings/agents-md/github.svg)](https://agentmods.dev/instructions/feiskyer/codex-settings/agents-md)

Your own site

<a href="https://agentmods.dev/instructions/feiskyer/codex-settings/agents-md"><img src="https://agentmods.dev/badge/instructions/feiskyer/codex-settings/agents-md/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

Your own site · 80×15

<a href="https://agentmods.dev/instructions/feiskyer/codex-settings/agents-md"><img src="https://agentmods.dev/badge/instructions/feiskyer/codex-settings/agents-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 1,302 This file is loaded in full into every session.

When invoked 1,302 The same file — it is already loaded in full.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

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.

Model	Per session	Once invoked
Fable 5.1	$0.01302	$0.01302
Opus 5.5	$0.00521	$0.00521
Sonnet 5.5	$0.00260	$0.00260
Haiku 4.5	$0.00130	$0.00130

Measured yesterday against content hash a18bf167e549, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, 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 yesterday.

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 · 60 lines

How it starts

The opening of the file, as written. The whole thing — 60 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.

Definition of Done

A change in this repository is finished when all of these hold. Work through them without stopping for approval between steps:

The change itself is complete, including every file it implies — update a Skill's agents/openai.yaml when its purpose, display name, or default invocation changes, and update the Skills table in README.md when a Skill is added or removed.
The validation commands matching the changed files have been run and pass. Fix failures caused by the change and rerun affected checks; report unrelated failures separately.
.codex-plugin/plugin.json version is bumped if released Plugin content changed.
The final report states which validation commands ran, which integration checks were skipped and why, and any assumption the change rests on.

Stop early only for a genuine blocker: a missing credential, an ambiguous requirement where the readings lead to materially different work, or an action outside the scope described above.

Read the full file on GitHub · 60 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.

yesterday Changed · +20 tokens per session a18bf167e549
1mo ago Changed · -38 lines · -409 tokens per session fb290e7652fa
1mo ago Changed · +14 lines · +455 tokens per session 1837348ae8a0
2mo 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 (248 stars, last pushed yesterday), licensed MIT. It adds 1,302 tokens to every session, about $0.0052 per session on Opus 5.5. 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.

Building agents agentic-ai agents ai codex copilot litellm

codex-settings AGENTS.md next to 6 instructions from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
codex-settings AGENTS.mdfeiskyer/codex-settings	Instructions file	248	yesterday	MIT	A	1,302	Codex, OpenCode
copilot-pro-dev-samples copilot-instructions.mdpnp/copilot-pro-dev-samples	Instructions file	169	3d ago	MIT	A	534	GitHub Copilot
vscode buildNext.instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	9,719	GitHub Copilot
next.js AGENTS.mdvercel/next.js	Instructions file	143k	yesterday	MIT	A	7,461	Codex, OpenCode
langchain AGENTS.mdlangchain-ai/langchain	Instructions file	149k	yesterday	MIT	A	4,680	Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	5,516	GitHub Copilot
vscode copilot-instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	3,093	GitHub Copilot

codex-settings: Instructions file for Codex