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/wildpigking/codex-project-skill-manager/agents-mdgit clone --depth 1 https://github.com/WildPigKing/codex-project-skill-managerWrote 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/wildpigking/codex-project-skill-manager/agents-md)<a href="https://agentmods.dev/instructions/wildpigking/codex-project-skill-manager/agents-md"><img src="https://agentmods.dev/badge/instructions/wildpigking/codex-project-skill-manager/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 | $0.00630 | $0.00630 |
| Opus 5 | $0.00315 | $0.00315 |
| Sonnet 5 | $0.00126 | $0.00126 |
| Haiku 4.5 | $0.00063 | $0.00063 |
Grade A, and why
codex-project-skill-manager 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.
How it starts
The opening of the file, as written. The whole thing — 39 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Codex Project & Skill Manager
Product boundary
- This repository plans how Codex should create future projects and manage user-level skills.
- Existing projects are out of scope. Never move, rename, or reorganize them.
- Existing skills may be inventoried read-only. Propose relocation or classification only after showing the exact plan, and apply it only after explicit user approval.
- Keep all shipped instructions, skills, scripts, configuration, and tests in English. Maintain README.zh-CN.md as a faithful Chinese translation for readers.
Startup routing
- For a question about what this repository does, explain the product from README.md. Do not inspect the user's environment.
- For requests to inspect, set up, bootstrap, or plan a Codex workspace, use $bootstrap-codex-workspace. Start in read-only mode and return a plan.
- For requests about the location or internal structure of a new project, use $organize-codex-projects.
- For requests to inventory, classify, route, install, or update skills or the skills menu, use $manage-codex-skills.
- On the first substantive writable task in this repository, or after a meaningful milestone, use $maintain-project-ai-records.
- When the user asks whether project experience should become a reusable skill, or explicitly authorizes a skill update, use $reflect-codex-workflows.
- Read .agents/skills/SKILLS_MENU.md before selecting a shipped skill. For each distinct task or subrequest, shortlist at most three skills and read only their complete SKILL.md files.
Consent contract
- Discovery and planning are read-only.
- A full workspace bootstrap plan must state the resolved global AGENTS.md path, user skills root, future-projects root, proposed writes, optional skill relocations, and a plan ID. A narrow new-project structure plan needs only the locations and writes relevant to that project.
- Do not treat cloning, opening, or reading this repository as approval.
- Before any write outside this repository, require explicit approval for the current plan ID.
- If the plan changes, invalidate the earlier approval.
- Do not overwrite a complete user AGENTS.md. Update only a clearly delimited managed block and preserve unrelated content.
- A read-only category recommendation is not a persisted classification. Do not record a classification, rebuild a user menu, or create, revise, move, or promote a user skill without approval.
- Repository-local development explicitly requested by the user follows normal task authorization and does not require a workspace plan ID.
- A read-only request suppresses project-record writes, even when the inspection produces a useful milestone.
- Workflow reflection may read the relevant user skills menu and shortlisted user SKILL.md files when cross-project comparison is requested. Do not scan the broader user home.
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 · 39 lines · 630 tokens per session scan A 83066ebed0e3
codex-project-skill-manager AGENTS.md is an instructions file published in the GitHub repository WildPigKing/codex-project-skill-manager (22 stars, last pushed 9d ago), licensed MIT. It adds 630 tokens to every session, about $0.0032 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
sandvault AGENTS.md
AGENTS.md instructions for webcoyote/sandvault, covering agents.md and testing.
agent-deck AGENTS.md
Instructions for breakstring/agent-deck, covering agents.md, 项目定位, 必读文档, 工作流 and 当前代码结构.
codex-token-meter AGENTS.md
AGENTS.md instructions for prefect12/codex-token-meter, covering ai token meter development guide, project shape, build and verification, git workflow and ai token meter test loop.
codex-skills-kit AGENTS.md
Instructions for TAKEOFF69/codex-skills-kit, covering agents.md – codex-skills-kit, what this repo is, layout, validate before committing and conventions.
duetlens CLAUDE.md
Claude Code instructions for xieziyu/duetlens, covering duetlens, 文档约定, 版本控制, 语言 and 文件命名.
codex-switch AGENTS.md
AGENTS.md instructions for ChArLiEdance/codex-switch, covering repository agents and platform isolation.