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/milisp/codexia/agents-mdgit clone --depth 1 https://github.com/milisp/codexiaWhat 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 | $0.00656 | $0.00656 |
| Opus 5 | $0.00328 | $0.00328 |
| Sonnet 5 | $0.00131 | $0.00131 |
| Haiku 4.5 | $0.00066 | $0.00066 |
Grade A, and why
codexia 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.
How it starts
The opening of the file, as written. The whole thing — 67 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md
Project Info
- Agent os for
codex cliandclaude code cli- agent - use
codex app-serverandclaude-agent-sdk-rsto connect Codexia
Project tech
- Package manager: bun
- Framework: React + shadcn + tailwindcss + TypeScript + Tauri v2
- Don't use emit_all
- UI: use shadcn UI components first, Button, Input, etc.
- code comment language: English-only
- Zustand: for state management with persistence
- Don't break Fast Refresh: a
.tsxfile rendering UI must only export PascalCase components (no lowercase JSX-returning helpers), otherwise HMR falls back to a full page reload and drops in-flight events
Common Commands
bun tauri dev- read the backend outputbunx tsc --noEmit- test frontend if frontend changebunx react-doctor@latest --no-telemetry --category Bugs- fix frontend if frontend changebunx --bun shadcn@latest add <dep>- add shadcn depcargo check -p codexiaif rust code change- only
cargo buildwhen I ask - Don't run
cargo fmt
Project Structure
codexia/
├── src/ # React frontend source
│ ├── components/ # UI components
│ ├── components/ui/ - shadcn UI components │ ├── components/cc/ - claude-code components
│ ├── components/codex/` - codex components
│ ├── views/ # View components
│ ├── hooks/ # Custom React hooks
│ ├── store/ # Zustand state management
│ ├── services/ # Business logic services
│ └── types/ # TypeScript type definitions
├── src-tauri/ # Rust backend source
│ ├── src/
│ │ ├── lib.rs # Main Tauri application
│ ├── capabilities/ # Tauri capabilities
│ └── Cargo.toml # Rust dependencies
├── Cargo.toml # Workspace root Cargo.toml
├── crates/
│ ├── codex/ # Codex crate
│ ├── cc/ # Claude Code crate
│ ├── db/ # Database crate
│ └── shared/ # Shared crate
- use
@/hooks@/typesetc.
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 First seen · 67 lines · 656 tokens per session scan A ebd435a018f0
codexia AGENTS.md is an instructions file published in the GitHub repository milisp/codexia (903 stars, last pushed 4d ago), licensed MIT. It adds 656 tokens to every session, about $0.0033 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
ai4j AGENTS.md
Instructions for LnYo-Cly/ai4j, covering repository guidelines, project identity, monorepo scope, harness anything and hard rules.
ai4j CLAUDE.md
Instructions for LnYo-Cly/ai4j: 本项目以 AGENTS.md 作为 coding agent 指令的唯一权威入口。.
scodex AGENTS.md
AGENTS.md instructions for lauzhihao/scodex, covering agent policy, communication, context, safety and git safety.
scodex CLAUDE.md
Claude Code instructions for lauzhihao/scodex, covering claude policy, communication, context, safety and git safety.
openai-cookbook AGENTS.md
Instructions for openai/openai-cookbook, covering repository guidelines, project structure & module organization, build, test, and development commands, coding style & naming conventions and testing guidelines.
azure-search-openai-demo AGENTS.md
Instructions for Azure-Samples/azure-search-openai-demo, covering instructions for coding agents, overall code layout, adding new data, adding a new azd environment variable and adding a new setting to "developer settings" in rag app.