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/peltmonger/stardrive/agents-mdgit clone --depth 1 https://github.com/peltmonger/stardriveWhat 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 | $0.02707 | $0.02707 |
| Opus 5 | $0.01354 | $0.01354 |
| Sonnet 5 | $0.00541 | $0.00541 |
| Haiku 4.5 | $0.00271 | $0.00271 |
Grade A, and why
stardrive 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 2d 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 — 125 lines — stays where its author put it; the contents beside it link to each section on GitHub.
🛑 CRITICAL: REPOSITORY BOOTSTRAP DIRECTIVE 🛑
As an AI agent operating in this repository, you MUST execute the following state check before analyzing, coding, or responding to any user prompt:
- CHECK STATE: Silently verify if the file
STARDRIVE_AGENT_MODE.mdexists in the root directory. - IF MISSING (UNINITIALIZED):
- Intercept the prompt: Acknowledge to the user that you are running the initial repository setup first.
- Never (!) proceed without this file being present!
- Read the file
SETUP.mdin the./.ai/directory.. - Execute ALL setup, scaffolding, and configuration instructions defined in
SETUP.mdand related files. Ask the user about clarification where necessary. - Create the
STARDRIVE_AGENT_MODE.mdfile in the root directory to mark initialization as complete, setting its content to "project" or "boilerplate" - depending on what the user's case is about. - Proceed to fulfill the user's original request.
- IF PRESENT (INITIALIZED):
- Directly proceed to fulfilling the user's prompt.
- Mind the content of the
STARDRIVE_AGENT_MODE.mdas it defines your general scope as described in theAGENTS.md.
General information and guidelines for AI agents
Analyze your high-level use case first
Check for an STARDRIVE_AGENT_MODE.md file at the root level. Its content is a single keyword that selects your mode:
boilerplate- You are maintaining the boilerplate code itself as a contributor (not building a new website with it). FollowBOILERPLATE_MODE.md. Do not execute the other.aiguides as setup steps (SETUP.md,CONFIG_GUIDE.md,TRIMMING_GUIDE.md,FAVICON_GUIDE.md); they describe the end-user setup flow. You may still read and update them when your changes affect that flow - keeping them accurate is part of boilerplate maintenance.project- You are using the boilerplate to build a new project and website. Treat this codebase as an already-started project to adjust and extend to the user's specifications, not as a boilerplate. OpenPLAN.mdfirst to see what is still open. If noPLAN.mdexists yet, the configuration has not been planned - runSETUP.mdto create it. IgnoreBOILERPLATE_MODE.md.
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.
- 2d ago First seen · 125 lines · 2,707 tokens per session scan A 2d179f9d114f
stardrive AGENTS.md is an instructions file published in the GitHub repository peltmonger/stardrive (183 stars, last pushed 2d ago), licensed MIT. It adds 2,707 tokens to every session, about $0.0135 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
gdgxica.github.io CLAUDE.md
Instructions for GDGXICA/gdgxica.github.io, covering claude.md, architecture, routing & pages, data layer and component pattern.
one CLAUDE.md
Claude Code instructions for one-ie/one, covering claude.md — business node, setup (2 min, one-time), one key, full authority, who you are and the node shape.
one AGENTS.md
AGENTS.md instructions for one-ie/one, covering agents.md — for an agent working in this repo, orient yourself, the substrate verbs you have, two halves: one reaches, /do builds and build with /do.
deno copilot-instructions.md
Copilot instructions for denoland/deno, covering deno development guide for github copilot, network access, high level overview, key directories and key files to understand first.
page-agent AGENTS.md
AGENTS.md instructions for alibaba/page-agent, covering instructions for coding assistants, project overview, development commands, architecture and monorepo structure.
oxc AGENTS.md
Instructions for oxc-project/oxc, covering agents.md - ai assistant guide for oxc, ai usage policy for contributors, repository structure, core crates and development commands.