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/keithhegit/ultra-codex-agents.md/agents-mdgit clone --depth 1 https://github.com/keithhegit/ultra-codex-agents.mdWhat 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 | $0.00281 | $0.00281 |
| Opus 5 | $0.00140 | $0.00140 |
| Sonnet 5 | $0.00056 | $0.00056 |
| Haiku 4.5 | $0.00028 | $0.00028 |
Grade A, and why
ultra-codex-agents.md 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.
What it actually says
Global Coding Discipline
Think Before Coding
Before changing code, identify the goal, assumptions, ambiguity, and success criteria. If the ambiguity affects architecture, data, user experience, security, or destructive operations, ask before proceeding. If the ambiguity is minor, make a reasonable assumption and state it after acting.
Simplicity First
Implement the minimum code that solves the requested problem. Do not add speculative features, abstractions, configurability, or broad error handling. Prefer the existing project style and local patterns over new architecture. If the solution starts growing larger than the problem, simplify.
Surgical Changes
Touch only files and lines needed for the requested outcome. Do not refactor, reformat, rename, or clean up unrelated code. Remove only unused code introduced by your own changes. Mention unrelated issues separately instead of fixing them silently.
Goal-Driven Execution
Turn the request into verifiable success criteria. For bugs, reproduce or identify the failing behavior before fixing when feasible. For features, verify the expected behavior through tests, commands, or clear reasoning. After changes, report what was verified and what was not.
Relationship To Skills
These rules are the default behavior for coding work.
For complex, multi-file, risky, or OpenSpec-based tasks, use the appropriate orchestration skill or workflow entry point.
Project-specific AGENTS.md instructions override these global defaults.
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.
- 2d ago First seen · 35 lines · 281 tokens per session scan A b7b1ff3faed8
ultra-codex-agents.md AGENTS.md is an instructions file published in the GitHub repository keithhegit/ultra-codex-agents.md (1 stars, last pushed 4mo ago), licensed Apache-2.0. It adds 281 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 2026-08-31.
Other instructions, from other repositories
AutoVideo-Agent AGENTS.md
Instructions for wangxin6x/AutoVideo-Agent, covering agents.md, project rules and development.
codex-command-center AGENTS.md
Instructions for sevensir888/codex-command-center, a project described as: A local desktop control center for organizing Codex projects, engineering tasks, sessions, Git changes, Skills, and MCP configuration.
GameStudio-CodexKIT AGENTS.md
Instructions for hoatv2211/GameStudio-CodexKIT, covering gamestudio-codexkit operating contract, active sources of truth, primary distribution, repository-local maintenance and evidence.
zhijuan-codex-agency-chief-of-staf AGENTS.md
Instructions for papperrollinggery/zhijuan-codex-agency-chief-of-staf: 当当前 Git 根目录是本仓库时，默认任务是维护 Agency Chief of Staff Skill 的源码，而不是运行已安装的 Skill。.
arxiv-wiki AGENTS.md
AGENTS.md instructions for synabreu/arxiv-wiki, covering agents.md, project goal and rules.
init-claude-md AGENTS.md
AGENTS.md instructions for LetheChen/init-claude-md, covering agents.md, session maintenance protocol, core rules (from karpathy), language and project conventions.