Borrowing it
Nothing to install: this file belongs to gabriele-mastrapasqua/codex-lean-team. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/gabriele-mastrapasqua/codex-lean-team/main/AGENTS.mdgit clone --depth 1 https://github.com/gabriele-mastrapasqua/codex-lean-teamWrote 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/gabriele-mastrapasqua/codex-lean-team/agents-md)<a href="https://agentmods.dev/instructions/gabriele-mastrapasqua/codex-lean-team/agents-md"><img src="https://agentmods.dev/badge/instructions/gabriele-mastrapasqua/codex-lean-team/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 5.1 | $0.00986 | $0.00986 |
| Opus 5 | $0.00493 | $0.00493 |
| Sonnet 5 | $0.00197 | $0.00197 |
| Haiku 4.5 | $0.00099 | $0.00099 |
Grade A, and why
codex-lean-team 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 7d 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 — 108 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Lean Team v2: execution-first engineering
Model hierarchy
- Luna (root): fastest, cheapest, for all direct implementation. Reasoning effort: high.
- Luna (specialist): same economical model for focused work. Reasoning effort: high by default, max for debugger and native/unsafe code.
Default execution policy
The root agent (Luna) implements tasks directly by default, but may delegate a narrow sub-question to a specialist when it would save time or reduce risk. Most tasks are completed by the main agent alone; a task with concrete uncertainty or a specialist domain should use one focused, read-only specialist early. The root keeps ownership of edits and validation.
Routing
- Clear or ordinary task → Luna implements directly.
- Cross-module but clear → Luna implements directly.
- Ambiguous architecture → Luna inspects → delegate to Luna planner for competing designs or rollback/compatibility tradeoffs → Luna implements.
- Difficult bug → Luna reproduces or inspects → delegate to Luna debugger at max for cross-layer, intermittent, previously failed, or multi-hypothesis bugs → Luna fixes.
- Unfamiliar or cross-cutting path → Luna delegates one narrow question to Luna explorer as an early scout when it can quickly remove uncertainty.
- Native or unsafe code → delegate to Luna native at max for C/C++, Rust, SIMD, CUDA/Metal, memory ownership, atomics, or FFI boundaries.
- High-risk implementation → Luna implements → delegate to Luna reviewer before completion.
- Performance with benchmark → delegate to Luna performance specialist.
- AI/ML, infrastructure, deployment, CI/CD, cloud, containers → delegate to the matching Luna specialist at high when the task is materially in that domain.
"Cross-module" is not a trigger. Multi-file changes are normal development.
Delegation guidelines
Delegate when a specialist can answer a concrete question, reduce uncertainty, or cover a domain the root agent is not confident in. A full blocker is not required: use one focused specialist early when its output is likely to change the next implementation step.
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.
- 7d ago First seen · 108 lines · 986 tokens per session scan A d585ae13b6a4
codex-lean-team AGENTS.md is an instructions file published in the GitHub repository gabriele-mastrapasqua/codex-lean-team (3 stars, last pushed 1mo ago), licensed MIT. It adds 986 tokens to every session, about $0.0049 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
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.
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).
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.
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.
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).
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.