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/web-infra-dev/rsdoctor/agents-mdgit clone --depth 1 https://github.com/web-infra-dev/rsdoctorWrote 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/web-infra-dev/rsdoctor/agents-md)<a href="https://agentmods.dev/instructions/web-infra-dev/rsdoctor/agents-md"><img src="https://agentmods.dev/badge/instructions/web-infra-dev/rsdoctor/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 | $0.01348 | $0.01348 |
| Opus 5 | $0.00674 | $0.00674 |
| Sonnet 5 | $0.00270 | $0.00270 |
| Haiku 4.5 | $0.00135 | $0.00135 |
Grade A, and why
rsdoctor 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 3d 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 — 113 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md
Stack
- Node.js
22.18+, package manager pnpm11.0+(enable viacorepack enable) pnpmworkspace monorepo (topological build ordering)- TypeScript strict mode; target
node 16for library output - Build toolchain: Rslib (based on Rsbuild/Rspack)
- Lint/format: Rstack CLI (
rs lintbacked by Rslint,rs fmtbased on Prettier) - Test runner: Rstest (
pnpm test), E2E: Playwright (pnpm e2e)
Commands
# ── bootstrap ────────────────────────────────────────────────
pnpm install # install all deps + build all packages (prepare hook)
# ── quality checks ───────────────────────────────────────────
pnpm lint # rs lint (error-level only)
pnpm format # rs fmt + heading-case
pnpm test # unit tests via rstest (single worker, NODE_OPTIONS=--max-old-space-size=8192)
pnpm e2e # playwright e2e (requires chromium: cd e2e && npx playwright install chromium)
# ── build ────────────────────────────────────────────────────
pnpm run build # build all package targets in topological order
pnpm --filter '@rsdoctor/core...' run build # build one package and its workspace dependencies
# ── focused dev ──────────────────────────────────────────────
pnpm --filter @rsdoctor/core run build # build one package
pnpm --filter @rsdoctor/core run test # test one package
pnpm -C packages/client build # alternative: use directory path
Project structure
packages/
types/ # shared TypeScript type definitions
utils/ # shared utilities (build / common / error / logger / ruleUtils)
graph/ # module / chunk / package graph data structures
sdk/ # server SDK: data collection, socket.io transport, report serving
core/ # core analysis engine: build-utils, plugins, rules
rspack-plugin/ # Rspack plugin (peerDep: @rspack/core)
webpack-plugin/ # Webpack 5 plugin (peerDep: webpack 5.x)
cli/ # `rsdoctor` CLI binary
agent-cli/ # `@rsdoctor/agent-cli` — agent CLI tooling
client/ # web client (Rsbuild SPA, serves analysis report and report UI)
document/ # documentation site (Rspress)
proto/ # protocol buffer / schema definitions
test-helper/ # test utilities shared across packages
scripts/
rslib.base.config.ts # shared Rslib build config (CJS + ESM dual-package)
rstest.setup.ts # rstest global setup (snapshot serializer)
tsconfig/ # shared tsconfig presets
e2e/ # Playwright E2E tests (cases/ per bundler)
examples/ # runnable example projects (rspack / rsbuild / webpack / rspress)
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.
- 3d ago First seen · 113 lines · 1,348 tokens per session scan A 0e293c12efd1
rsdoctor AGENTS.md is an instructions file published in the GitHub repository web-infra-dev/rsdoctor (1,139 stars, last pushed 4d ago), licensed MIT. It adds 1,348 tokens to every session, about $0.0067 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
patternfly-react-seed AGENTS.md
Instructions for patternfly/patternfly-react-seed, covering agent instructions (patternfly react seed), what this project is, stack, commands to run before you consider work done and repository layout.
maui uitests.instructions.md
Instructions for dotnet/maui, covering ui testing guidelines for .net maui, ui test structure, two-project requirement, base class and infrastructure and naming conventions.
maui copilot-instructions.md
Guidance for GitHub Copilot when working on the .NET MAUI repository.
maui helix-device-tests.instructions.md
Guidelines for running and configuring .NET MAUI device tests on Helix infrastructure.
maui ci-copilot-pipeline-security.instructions.md
Security rules for the Copilot PR-review pipeline. Read before editing.
maui xaml-unittests.instructions.md
Guidelines for writing XAML unit tests in the Controls.Xaml.UnitTests project.