Borrowing it
Nothing to install: this file belongs to ntorga/agent-starter-kit. 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/ntorga/agent-starter-kit/main/AGENTS.mdgit clone --depth 1 https://github.com/ntorga/agent-starter-kitWrote 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/ntorga/agent-starter-kit/agents-md)<a href="https://agentmods.dev/instructions/ntorga/agent-starter-kit/agents-md"><img src="https://agentmods.dev/badge/instructions/ntorga/agent-starter-kit/agents-md/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/instructions/ntorga/agent-starter-kit/agents-md"><img src="https://agentmods.dev/badge/instructions/ntorga/agent-starter-kit/agents-md.svg" alt="Reviewed on agentmods" width="80" 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 | $0.02587 | $0.02587 |
| Opus 5.5 | $0.01035 | $0.01035 |
| Sonnet 5.5 | $0.00517 | $0.00517 |
| Haiku 4.5 | $0.00259 | $0.00259 |
Grade A, and why
agent-starter-kit 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 1mo 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 — 124 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md
Before anything else: read
AGENTS.override.mdin the project root if it exists. It holds project-specific behavior changes and important instructions that take precedence over every rule in this file.
This is a style book for code that reads itself. You will apply these rules by matching patterns, so match on the reasoning behind each rule, not its wording. The goal is code that explains itself and clearly belongs in the project it lives in. The concrete rules live in .agents/rules/code/. They are split by domain: general coding, shell, debugging. Read the files your change touches.
Specialized workflows have their own playbooks under .agents/skills/: agent behavior, code review, UI verification, architecture, context maintenance. Read the relevant playbook before doing that kind of work.
Honesty and Ambiguity
If a request is flawed, say so.
- Proceed without asking: any non-destructive, reversible action the task needs. Git is the safety net. Stopping to confirm the obvious wastes the session.
- Stop and ask: destructive or irreversible actions (deleting a repository, dropping a database, force-pushing to main), and genuinely non-obvious trade-offs.
- When intent could mean different things, or your work surfaces a finding worth raising, state the problem, offer three options with trade-offs, and recommend one (
.agents/skills/agent-decision/SKILL.md). Keep it brief, in a conversational tone. - When the ambiguity only changes how (not what), proceed and document your default.
Git
- Run git from the repository root. Do not use
git -Cor other global git flags. Permission patterns match plaingit <command>forms only. - Commit mechanics follow
.agents/rules/git.md: conventional prefixes, branch names that mirror them, single-phrase messages, one logical change per commit, schema changes called out. You MUST NOT squash or rebase.
Readability Over Performance
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.
- 1mo ago Changed · -23 lines · -668 tokens per session 4817a07d7db8
- 2mo ago First seen · 147 lines · 3,255 tokens per session scan A 4a7a8197e35e
agent-starter-kit AGENTS.md is an instructions file published in the GitHub repository ntorga/agent-starter-kit (148 stars, last pushed 1mo ago), licensed MIT. It adds 2,587 tokens to every session, about $0.0103 per session on Opus 5.5. 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
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.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, cache eligibility and rollout and applying the notice (cutover).
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 copilot-instructions.md
Copilot instructions for microsoft/vscode, covering vs code copilot instructions, project overview, root folders, core architecture (src/ folder) and built-in extensions (extensions/ folder).
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.