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/pc035860/scratchpad-mcp/agents-mdgit clone --depth 1 https://github.com/pc035860/scratchpad-mcpWrote 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/pc035860/scratchpad-mcp/agents-md)<a href="https://agentmods.dev/instructions/pc035860/scratchpad-mcp/agents-md"><img src="https://agentmods.dev/badge/instructions/pc035860/scratchpad-mcp/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 | $0.00651 | $0.00651 |
| Opus 5 | $0.00326 | $0.00326 |
| Sonnet 5 | $0.00130 | $0.00130 |
| Haiku 4.5 | $0.00065 | $0.00065 |
Grade A, and why
scratchpad-mcp 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 4d 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 — 43 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Repository Guidelines
Project Structure & Module Organization
src/: TypeScript source. Entry:src/server.ts; helpers insrc/server-helpers.ts; modules insrc/tools/andsrc/database/.tests/: Vitest specs (*.test.ts).scripts/: Utilities andserve-workflow/web viewer.dist/: Build output (generated bytsup). Do not edit.extensions/+dict(symlink): Optional Chinese tokenization assets.
Build, Test, and Development Commands
npm run dev: Watch build with tsup for rapid iteration.npm run build: Produce ESM bundle indist/.npm test/npm run test:watch: Run Vitest once / in watch mode.npm run typecheck: Strict TypeScript type checks (tsc --noEmit).npm run lint/npm run lint:fix: ESLint validate / autofix.npm run format: Prettier formatsrc/**/*.ts.npm run serve/npm run serve:dev: Launch workflow web viewer.
Coding Style & Naming Conventions
- TypeScript strict mode; no
any, explicit return types, preferconst. - Formatting: Prettier (2 spaces, single quotes, semicolons, LF, width 100).
- Linting: ESLint with
@typescript-eslintrules enforced in CI/local. - File names: prefer kebab-case (
server-helpers.ts,tools/search.ts). Some database classes usePascalCasefiles (e.g.,ScratchpadDatabase.ts). - Exports: favor named exports; functions/vars use lowerCamelCase; types/interfaces PascalCase.
Testing Guidelines
- Framework: Vitest (
tests/**/*.test.ts). Example:tests/extraction.test.ts. - Coverage: v8 provider with text/json/html reporters. Keep or improve coverage for touched files.
- Write deterministic, unit-level tests near affected modules; avoid I/O in pure unit tests.
- Run locally:
npm test; for TDD usenpm run test:watch.
Commit & Pull Request Guidelines
- Commits follow Conventional Commits (e.g.,
feat(core): ...,fix(database): ...,docs: ...). - Scope changes logically; keep messages imperative and concise.
- PRs must include: clear description, linked issues, test coverage for changes, and docs updates (README/AGENTS.md) when behavior or commands change.
- For web viewer changes, add before/after screenshots when feasible.
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.
- 4d ago First seen · 43 lines · 651 tokens per session scan A 7dd5ad98f77b
scratchpad-mcp AGENTS.md is an instructions file published in the GitHub repository pc035860/scratchpad-mcp (4 stars, last pushed 11mo ago), licensed MIT. It adds 651 tokens to every session, about $0.0033 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
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).
spec-kit AGENTS.md
AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.
codex AGENTS.md
AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).
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.
deepseek-harness AGENTS.md
AGENTS.md instructions for deepseek-ai/deepseek-harness, covering agents.md, pre-stable apis and released session data, repository layout, commands and host sandbox failures.