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/luca-mastrostefano/agent-native-setup/agents-mdgit clone --depth 1 https://github.com/luca-mastrostefano/agent-native-setupWrote 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/luca-mastrostefano/agent-native-setup/agents-md)<a href="https://agentmods.dev/instructions/luca-mastrostefano/agent-native-setup/agents-md"><img src="https://agentmods.dev/badge/instructions/luca-mastrostefano/agent-native-setup/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 | $0.00400 | $0.00400 |
| Opus 5 | $0.00200 | $0.00200 |
| Sonnet 5 | $0.00080 | $0.00080 |
| Haiku 4.5 | $0.00040 | $0.00040 |
Grade A, and why
agent-native-setup 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.
What it actually says
agent-native-setup — Agent Contract
A wizard that scaffolds an agent-native project setup into a new repo.
Read INSTRUCTION.md first — the standard engineering contract (the
four execution principles, when to write an RFC, how this repo stays agent-native). This file
is the project-specific map; CLAUDE.md and GEMINI.md (symlinks) point here.
@INSTRUCTION.md
Navigation
| Topic | Where |
|---|---|
| Project entry point | README.md |
| Architecture & decisions | docs/architecture/ |
| Proposals & decisions | docs/rfc/ (proposed/ → active/) |
| How to contribute | CONTRIBUTING.md |
| Security policy | SECURITY.md |
Command surface
task install # set up git hooks (once)
task lint # run linters
task format # auto-format
task typecheck # type-check
task test # run tests
task quality # full local gate
task rfc-sync # sync RFCs to their Status folder
task check-index # fetch + validate every community-index entry (network)
task improvement -- "<idea>" # log an idea in docs/improvements.md
Run task --list for the full, current set (also injected at session start via the
.claude/settings.json SessionStart hook).
When you work out a repeatable process — a build, check, migration, or fix sequence
you'd otherwise rediscover — capture it as a task with a one-line desc:, so the next
contributor runs it deterministically instead of leaving the knowledge in a chat or a
throwaway script.
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 · 42 lines · 400 tokens per session scan A c50411dc7436
agent-native-setup AGENTS.md is an instructions file published in the GitHub repository luca-mastrostefano/agent-native-setup (5 stars, last pushed yesterday), licensed MIT. It adds 400 tokens to every session, about $0.0020 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
codedb AGENTS.md
AGENTS.md instructions for justrach/codedb, covering codedb agent guidelines, what codedb is (and isn't), review guidelines, pre-merge verification and security-sensitive areas.
Puppetmaster AGENTS.md
AGENTS.md instructions for professorpalmer/Puppetmaster, covering agents.md, first: are you a puppetmaster worker?, default subagent runtime: puppetmaster, when to start a puppetmaster swarm (do this by default) and match the verb to the task shape (single feature ≠ swarm).
claude-code-blueprint CLAUDE.md
Instructions for faizkhairi/claude-code-blueprint, covering global claude behavior rules, verify-after-complete (mandatory), what to verify depends on what was built, verification mindset and after verification.
agent-skills AGENTS.md
Instructions for powabase-ai/agent-skills, covering agents.md, repository structure, prerequisites & commands, writing skill.md files and frontmatter (required).
agents CLAUDE.md
Claude Code instructions for wshobson/agents, a project described as: Multi-harness agentic plugin marketplace for Claude Code, Codex, Cursor, OpenCode, GitHub Copilot, and Google Antigravity.
agent-skills GEMINI.md
Instructions for powabase-ai/agent-skills: This repository ships the powabase agent skill at skills/powabase/SKILL.md — it teaches you to build on Powabase, the AI Backend-as-a-Service (RAG / knowledge bases, agents, multi-agent orchestration, workflows) and its Supabase-style BaaS layer (PostgREST, auth, storage…