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/codester1000/raindrop-mcp/agents-mdgit clone --depth 1 https://github.com/codester1000/raindrop-mcpWhat 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 | $0.00599 | $0.00599 |
| Opus 5 | $0.00300 | $0.00300 |
| Sonnet 5 | $0.00120 | $0.00120 |
| Haiku 4.5 | $0.00060 | $0.00060 |
Grade A, and why
raindrop-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 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 — 38 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Agent Operating Guide
Shared Mission
- Deliver production-ready enhancements to the Raindrop MCP server while preserving full MCP protocol compliance.
- Prefer existing patterns in
src/services/raindropmcp.service.tsand related modules before inventing new abstractions. - Keep responses concise, cite relevant files/lines, and recommend verification steps (tests, builds) after changes.
Primary Agent Briefs
Claude (Anthropic)
- Use
CLAUDE.mdfor the canonical project tour: current version, capabilities, tooling commands, and architectural notes. - When adding tools or resources, mirror the declarative
toolConfigspattern and reuse the Zod schemas undersrc/types/. - Validate destructive actions (collection/tag/delete) with clear preconditions and meaningful error messages.
GitHub Copilot / Code Generation Agents
- Follow
.github/copilot-instructions.mdfor style, dependency, and testing conventions (TypeScript + bun, Vitest, zod validation). - Reference
.github/instructions/mcp-*.instructions.mdwhen working on MCP transports, refactors, or inspector tooling. - Keep imports sorted (external→internal), prefer async/await, and avoid
console.login MCP-facing code—use existing logging helpers instead.
Other LLM Operators (e.g., Cursor, ChatGPT)
- Defer to the same guidelines as Copilot unless a task explicitly targets documentation or analysis.
- Surface open questions back to the user when Raindrop API behavior is ambiguous; default to the OpenAPI definitions in
raindrop-complete.yaml.
Development Workflow
- Install & run with bun:
bun run dev,bun run start:prod,bun run build,bun run test,bun run type-check. - Generated assets: use
bun run generate:schemaorbun run generate:clientonly when the OpenAPI spec changes. - Tests live in
tests/; use Vitest and update coverage when new tools/resources are introduced.
Protocol & Resource Notes
- MCP manifest, tool registration, and resource handling are centralized in
RaindropMCPService(src/services/raindropmcp.service.ts). - Dynamic resources (
mcp://collection/{id},mcp://raindrop/{id}) should stay lightweight and fetch live data viaRaindropService. - Authentication depends on the
RAINDROP_ACCESS_TOKENenvironment variable—never hard-code secrets.
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 · 38 lines · 599 tokens per session scan A fc337c17868b
raindrop-mcp AGENTS.md is an instructions file published in the GitHub repository codester1000/raindrop-mcp (0 stars, last pushed 8mo ago), licensed MIT. It adds 599 tokens to every session, about $0.0030 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.
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 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).
next.js AGENTS.md
Instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.