Borrowing it
Nothing to install: this file belongs to rtorcato/repo-tooling. 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/rtorcato/repo-tooling/main/AGENTS.mdgit clone --depth 1 https://github.com/rtorcato/repo-toolingWrote 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/rtorcato/repo-tooling/agents-md)<a href="https://agentmods.dev/instructions/rtorcato/repo-tooling/agents-md"><img src="https://agentmods.dev/badge/instructions/rtorcato/repo-tooling/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/rtorcato/repo-tooling/agents-md"><img src="https://agentmods.dev/badge/instructions/rtorcato/repo-tooling/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 | $0.02791 | $0.02791 |
| Opus 5.5 | $0.01116 | $0.01116 |
| Sonnet 5.5 | $0.00558 | $0.00558 |
| Haiku 4.5 | $0.00279 | $0.00279 |
Grade A, and why
repo-tooling 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 — 126 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md
Orientation for coding agents working with @rtorcato/repo-tooling. Human-readable docs live at https://docs.torcato.dev/repo-tooling/.
What this is
A one-package JavaScript / TypeScript tooling distribution. Ships every preset (TypeScript, Biome, ESLint, Prettier, Vitest, Jest, Commitlint, semantic-release, tsup, esbuild, Vite, Playwright) plus a CLI to scaffold and audit projects. Consumers get one install.
Swift repos (detected via Package.swift) are covered end to end: setup --preset swift-library scaffolds a SwiftPM package, and doctor/fix run the language-agnostic checks plus SwiftLint / Periphery / .gitignore / Package.swift. Python repos (detected via pyproject.toml / setup.py) get doctor/fix — Ruff / mypy / pytest / .gitignore / CI / git hooks — but no setup preset yet. Perl distributions (detected via cpanfile / Makefile.PL / dist.ini) get the same deal: Perl::Critic / perltidy / .gitignore / CI / git hooks, no setup preset. See src/languages/ — one directory per language module, src/base/ for what's shared.
repo-tooling stands alone. The ai-issue-loop pipeline (the loop commands, its skills, and the label / agent-user / skills checks) is an optional companion package, @infrazero/repo-ai, since #658. Nothing here requires it or checks for it; repo-tooling loop only prints a pointer there. Its settings live in repo-ai's own .repo-ai.json. The old rules.aiLoop and rules.requiredSkills keys in .repo-tooling.json are deprecated: they still validate, repo-tooling carries them forward without reading them; apps/docs/docs/guides/ai-setup.md says how to move them. See apps/docs/docs/guides/ai-issue-loop.md for how the two fit together.
CLI surface (agent-friendly)
Every command supports --json and a non-interactive mode. Combine with --yes for fully autonomous use.
| Command | Non-interactive | JSON output | Use case |
|---|---|---|---|
setup --preset <name> |
✅ (non-TTY, or with --yes) |
--dry-run only |
Scaffold a new project. Presets: minimal, library, web-app, node-api, nextjs-app, react-app, swift-library, and the opt-in vite-plus / vite-plus-app (Vite+ owns lint, format, test and build; see apps/docs/docs/guides/vite-plus.md). In an interactive terminal it first prints the file list and lets you deselect; pass --yes for the one-shot behaviour. Add --no-ai-setup to skip the AI agent files (also works with --config and the wizard). |
setup --config <path> |
✅ | --dry-run only |
Scaffold with a full ProjectConfig JSON file. See setup --config-schema. |
setup --config-schema |
✅ | ✅ (JSON Schema) | Print the JSON Schema for ProjectConfig. Use to validate configs before scaffolding. |
setup --dry-run |
✅ | ✅ | Print resolved config + file list without writing. Pair with --preset or --config. |
doctor --json |
✅ | ✅ | Audit a project. Returns { directory, results: [{ check, status, detail, hint? }] }. Status: ok / drift / missing / optional-missing / declared / skipped. |
doctor --offline |
✅ | ✅ | Skip every check that reads live GitHub state via gh (branch protection, repo settings, secrets, milestones); they report status: "skipped". Use it for CI gates, so the result never depends on timing or on which account runs it. |
doctor --rules-from <owner/repo> |
✅ | ✅ | Report how this repo's config/rules differ from a reference repo's .repo-tooling.json (read over gh). Informational only — adds a rulesReference key to the JSON, never a check result, never affects the exit code. |
doctor --snapshot |
✅ | ✅ | Read the live GitHub settings over gh and merge them into rules.github in .repo-tooling.json (#863). Runs no checks; the only doctor mode that writes. The JSON lists omitted fields the token couldn't read and departures from the standard. Refuses --offline and a missing or pre-v4 lockfile. |
setup --from <owner/repo> |
❌ (seeds the wizard) | --dry-run only |
Seed the wizard's defaults from a reference repo's recorded config. Seeded, not skipped — every question is still asked. |
fix --json --yes |
✅ | ✅ | Walk every doctor finding, apply fixers. Returns FixActionRecord[] with `status: applied |
fix <target> --json --yes |
✅ | ✅ | Apply one fixer. Targets from list --json. |
fix --dry-run |
✅ | ✅ | Print what each fixer would write without writing. Combine with --json. |
list --json |
✅ | ✅ | Enumerate every fix target, from the same registry as fix --list --json: targets[], each { target, description, appliesTo, outputs, riskLevel, canFixDrift }. The old tools[] shape is still emitted, derived from the registry, until the next major. |
copy <name> |
✅ | text only | Copy a single preset (biome, tsconfig) into the current directory. |
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 Changed · +1 lines · +90 tokens per session 13bf63e34703
- 6d ago Changed · +1 lines · +90 tokens per session d63b4a5bddb1
- 10d ago Changed · +40 tokens per session c15668e9a432
- 16d ago Changed · +158 tokens per session f76f0686c929
- 20d ago Changed 03fc0aa00521
- 27d ago Changed · +1 lines · +79 tokens per session 68921e2277ca
- 28d ago Changed · +16 tokens per session 5c15152d724e
- 29d ago Changed · +2 tokens per session 5cdfcc10cda2
- 1mo ago Changed · -1 lines · +18 tokens per session dcebb4fc48f6
- 1mo ago First seen · 124 lines · 2,298 tokens per session scan A 0b86449329ea
repo-tooling AGENTS.md is an instructions file published in the GitHub repository rtorcato/repo-tooling (2 stars, last pushed today), licensed MIT. It adds 2,791 tokens to every session, about $0.0112 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 2026-08-31.
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.