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/sevensir888/codex-command-center/agents-mdgit clone --depth 1 https://github.com/sevensir888/codex-command-centerWhat 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 | $0.00556 | $0.00556 |
| Opus 5 | $0.00278 | $0.00278 |
| Sonnet 5 | $0.00111 | $0.00111 |
| Haiku 4.5 | $0.00056 | $0.00056 |
Grade A, and why
codex-command-center 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 3d 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
Codex Command Center Repository Guidelines
Purpose
- This repository contains Codex Command Center, a Windows-first Tauri 2 + React + TypeScript desktop application for organizing local Codex engineering work.
- Keep the product Codex-only. Do not add Claude, Gemini, generic provider switching, OAuth provider management, remote SSH orchestration, cloud sync, telemetry, accounts, or marketplace features.
Product Model
- The primary workflow is
Project -> Task -> Codex Session -> File Changes -> Result. - Projects are local folder references only. Do not copy project source code into application storage.
- Tasks are lightweight engineering objectives with Planned, Active, Completed, and Blocked statuses.
- Codex sessions are indexed as external local history. Do not mutate Codex session files.
- Git review should stay lightweight: branch, staged and unstaged files, diff, stage, unstage, and commit.
Architecture
- Frontend:
src/with React and TypeScript. - Native shell:
src-tauri/with Rust commands for filesystem, process, Git, Codex, Skills, and MCP discovery. - Storage: local JSON state under the user local app data directory. SQLite may be introduced only if the data model outgrows JSON.
- Keep native commands small and explicit. Avoid adding background services or long-running supervisors.
UI Rules
- English-only UI and repository-facing text.
- Use restrained desktop-native styling: dark, dense, readable, subtle borders, clear spacing.
- Do not build an IDE, code editor, terminal emulator, chat client, or advanced Git client.
- Do not show raw secrets, tokens, API keys, or stack traces in normal UI.
- Error messages should be understandable, for example: "Codex CLI was not found." or "This directory is not a Git repository."
Implementation Rules
- Prefer small, direct data structures over framework-heavy abstractions.
- Keep task organization more prominent than raw session browsing.
- Keep all functionality local-first. Do not send project paths, source code, sessions, Git diffs, or configuration to external services.
- Use existing package scripts from
package.json. - Do not create generated reports, screenshots, or build artifacts in the repository unless explicitly requested.
Validation
- For ordinary changes run the narrowest useful checks, usually
npm run build. - For native changes, also run
npm run tauri:buildwhen Rust/Cargo and Tauri prerequisites are available. - If Rust/Cargo is unavailable, report that clearly instead of claiming the Tauri build passed.
Git
- Do not commit, tag, push, merge, or rewrite history unless explicitly requested.
- Preserve unrelated user changes.
- Keep changes focused on the requested product direction.
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.
- 3d ago First seen · 43 lines · 556 tokens per session scan A 107b3e7ac30a
codex-command-center AGENTS.md is an instructions file published in the GitHub repository sevensir888/codex-command-center (155 stars, last pushed 4d ago), licensed Apache-2.0. It adds 556 tokens to every session, about $0.0028 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
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。.
TechShorts AGENTS.md
AGENTS.md instructions for LarsenCodeLabs/TechShorts, covering repository structure, core product constraints, development and verification, security and configuration and solana/anchor protocol rules.
codex-desktop-linux AGENTS.md
AGENTS.md instructions for ilysenko/codex-desktop-linux, covering agents.md, purpose, non-negotiable rules, source routing and editing guidance.
codex-provider-sync AGENTS.md
Instructions for Dailin521/codex-provider-sync, covering ai / agent operator guide, vnext architecture baseline, goal, choose the interface and safe operating flow.
parallel-code CLAUDE.md
Instructions for johannesjo/parallel-code, covering parallel code, stack, commands, project structure and conventions.
ai-driven-development AGENTS.md
Instructions for CodeAlive-AI/ai-driven-development, covering ai-driven development — development guide, git publishing defaults, when to create tags and releases, requires a new tag/release and does not require a new tag/release.