codex-skills-collection: Instructions file for Codex

AGENTS.md

codex-skills-collection AGENTS.md is an instructions file for Codex, OpenCode from JakubMikolajek/codex-skills-collection. It costs 4,025 tokens per session, scanned A, original, MIT.

Project instructions for a collection of reusable coding-agent skills. They define a workflow of research, planning, implementation, review, and handoff, along with supported commands and expected outputs.

In plain words
What is it for?
Running project workflows such as research, planning, implementation, UI review, debugging, testing, documentation, quality checks, and handoff, with defined outputs for each command.
Why use it?
Multi-step coding work is easier to coordinate when each phase has a clear purpose and deliverable. These instructions help agents follow the project’s process instead of handling tasks inconsistently.

Instructions file for CodexOpenCode

Written for Codex and OpenCode: reads ~/.codex or $CODEX_HOME, but also the file is AGENTS.md. Also seen: mentions Claude Code; mentions AGENTS.md; mentions Codex.

This is JakubMikolajek/codex-skills-collection's own configuration. It tells Codex and OpenCode how to work on codex-skills-collection itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything codex-skills-collection configures →

Reuse

Borrowing it

Nothing to install: this file belongs to JakubMikolajek/codex-skills-collection. 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/JakubMikolajek/codex-skills-collection/main/AGENTS.md
Clone the repo
git clone --depth 1 https://github.com/JakubMikolajek/codex-skills-collection

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 codex-skills-collection AGENTS.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/jakubmikolajek/codex-skills-collection/agents-md/github.svg)](https://agentmods.dev/instructions/jakubmikolajek/codex-skills-collection/agents-md)
Your own site
<a href="https://agentmods.dev/instructions/jakubmikolajek/codex-skills-collection/agents-md"><img src="https://agentmods.dev/badge/instructions/jakubmikolajek/codex-skills-collection/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.

agentmods 80×15 button for codex-skills-collection AGENTS.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/jakubmikolajek/codex-skills-collection/agents-md"><img src="https://agentmods.dev/badge/instructions/jakubmikolajek/codex-skills-collection/agents-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 4,025 This file is loaded in full into every session.
When invoked 4,025 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.

ModelPer sessionOnce invoked
Fable 5.1 $0.04025 $0.04025
Opus 5 $0.02013 $0.02013
Sonnet 5 $0.00805 $0.00805
Haiku 4.5 $0.00402 $0.00402

Measured 10d ago against content hash e4cd9d1ea4db, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

codex-skills-collection 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 10d 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 · 398 lines

How it starts

The opening of the file, as written. The whole thing — 398 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Codex Workflow Contract

This repository provides a Codex-first delivery workflow and reusable skills.

Default Workflow

Always follow:

  1. Research
  2. Plan
  3. Implement
  4. Review

Do not skip phases unless the user explicitly asks to skip them.

Commands

These command-like requests are supported:

  • /research <task-description>
  • /plan <task-description>
  • /docs-flow <task-description>
  • /implement <task-description>
  • /implement-ui <task-description>
  • /review-ui
  • /review <task-description>
  • /e2e <task-description>
  • /code-quality-check
  • /debug <bug-description>
  • /handoff
  • /changelog
  • /context
  • /new-skill <skill-name>
  • /multi-repo <task-description>
  • /test-strategy <module-or-project>
  • /learn
  • /obsidian <session|adr|debug|knowledge>

Expected Outputs

  • /research: Research summary, assumptions, identified gaps, clarification questions, and next-step recommendation.
  • /plan: Phase-based implementation plan with acceptance criteria and explicit quality gates.
  • /docs-flow: Structured documentation artifact plus execution flow artifact (Mermaid + phase checklist + gates).
  • /implement: Scoped implementation aligned with the plan, including test evidence.
  • /implement-ui: Iterative UI implementation with verification loop and mismatch fixes.
  • /review-ui: Read-only PASS/FAIL verification report with precise diff table.
  • /review: Findings-first review report ordered by severity (bugs, regressions, risk, test gaps).
  • /e2e: Scenario list, Page Object and test implementation guidance, execution report expectations.
  • /code-quality-check: Prioritized quality report with concrete action plan.
  • /debug: Debug Report (reproduce → isolate → trace → hypothesize → verify) followed by root-cause fix with regression test.
  • /handoff: .codex-handoff.md with status, in-progress, blocked, decisions, files modified, next steps, open questions. Followed automatically by /obsidian session.
  • /changelog: CHANGELOG block in Keep a Changelog format with version bump recommendation.
  • /context: Session Context Block (stack, test runner, package manager, conventions, constraints, uncertainties).
  • /new-skill: Scaffolded SKILL.md with quality gates enforced, routing tree updated in same task.
  • /multi-repo: Per-repo change plan with contract-owner-first ordering, cross-repo impact map, mandatory handoff.
  • /test-strategy: test-strategy.md with risk map, test levels per zone, coverage targets, tooling, and quality gates.
  • /learn: Appended entries in per-skill references/failure-patterns.md and global skills/routing/FAILURES.md.
  • /obsidian <type>: Markdown note written directly to Obsidian vault — type determines template and destination folder (session → 01-projects/{slug}/sessions/, adr → 02-adr/, debug → 04-debug/, knowledge → 03-skills/domains/).

Read the full file on GitHub · 398 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. 10d ago First seen · 398 lines · 4,025 tokens per session scan A e4cd9d1ea4db

Subscribe to this mod's changes

codex-skills-collection AGENTS.md is an instructions file published in the GitHub repository JakubMikolajek/codex-skills-collection (5 stars, last pushed 5d ago), licensed MIT. It adds 4,025 tokens to every session, about $0.0201 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

next.js AGENTS.md

AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.

vercel/next.js · 7,296 tokens

codex AGENTS.md

AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.

openai/codex · 5,153 tokens

vscode buildNext.instructions.md

Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).

microsoft/vscode · 6,785 tokens

spec-kit AGENTS.md

AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.

github/spec-kit · 7,104 tokens

vscode oss-third-party-notices.instructions.md

Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).

microsoft/vscode · 5,001 tokens

langchain AGENTS.md

AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.

langchain-ai/langchain · 4,469 tokens