agentmods.dev

quick-dingtalk-mcp CLAUDE.md

quick-dingtalk-mcp CLAUDE.md is an instructions file for Claude Code from keithyt06/quick-dingtalk-mcp. It costs 1,491 tokens per session, scanned A, original, MIT.

Project instructions for quick-dingtalk-mcp, a service that lets an AI assistant use DingTalk as the logged-in user rather than as a bot. DingTalk is a workplace messaging and collaboration platform.

In plain words
What is it for?
Use them when developing or deploying the DingTalk MCP service, which provides tools for messages, contacts, calendars, documents, tasks, and other workplace features.
Why use it?
They explain the project's monorepo—a repository containing multiple related parts—its local and remote modes, commands, and conventions.

Instructions file for Claude Code

Written for Claude Code: the file is CLAUDE.md. Also seen: mentions CLAUDE.md; mentions Claude Code.

not rated 8 2mo ago A scan 1,491 tokens original MIT
View the source file keithyt06/quick-dingtalk-mcp
Install

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.

agentmods
npx agentmods add instructions/keithyt06/quick-dingtalk-mcp/claude-md
Clone the repo
git clone --depth 1 https://github.com/keithyt06/quick-dingtalk-mcp

Made for: Claude Code.

Wrote 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.

agentmods badge for quick-dingtalk-mcp CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/keithyt06/quick-dingtalk-mcp/claude-md.svg)](https://agentmods.dev/instructions/keithyt06/quick-dingtalk-mcp/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/keithyt06/quick-dingtalk-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/keithyt06/quick-dingtalk-mcp/claude-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 1,491 This file is loaded in full into every session.
When invoked 1,491 The same file — it is already loaded in full.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.01491 $0.01491
Opus 5 $0.00745 $0.00745
Sonnet 5 $0.00298 $0.00298
Haiku 4.5 $0.00149 $0.00149

Measured 6d ago against content hash d12602165076, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

quick-dingtalk-mcp CLAUDE.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 6d 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.

CLAUDE.md · 96 lines

How it starts

The opening of the file, as written. The whole thing — 96 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CLAUDE.md

Guidance for Claude Code when working in this repository. The root workspace CLAUDE.md (Karpathy coding guidelines: think before coding, simplicity first, surgical changes, goal-driven execution) also applies — this file adds project-specific detail.

What this project is

quick-dingtalk-mcp — an MCP server that wraps DingTalk's official CLI (dws) so an AI assistant acts in DingTalk as the real logged-in user (your avatar and name in the group), not as a bot. This is the whole point: DingTalk's own open-dingtalk/dingtalk-mcp only speaks as a bot. dws authenticates over user-identity OAuth and is itself a thin client to DingTalk's MCP gateway (mcp-gw.dingtalk.com), so this project is a shim that re-exposes that capability to any MCP host.

Two delivery modes share one tool catalog:

  • Local — run on your own machine, stdio to the host. Fastest start, personal use.
  • Remote — one shared AWS deployment serving a whole team, per-user OAuth isolation.

Both expose the same 38 tools (30 named + dingtalk_discover/dingtalk_invoke + 6 deprecated aliases), covering IM, contacts, calendar, docs/drive, todo, DING, attendance, OA approval, AI table, minutes, and mail.

Monorepo layout

npm workspaces (packages/*), "type": "module", Node ≥ 20 (remote needs ≥ 22.6).

  • packages/shared/ — the catalog + dispatch core; both servers depend on it.
    • catalog.json — generated, not hand-edited. All 261 dws commands, pinned to a dws version (_dwsCliVersion, currently 1.0.32). Regenerate with npm run build:catalog (needs dws installed + authenticated), then commit the diff.
    • tier1.json — the 30 named tools + 6 aliases that get first-class MCP tools.
    • scope-map.json, config/oauth-scopes.json — DingTalk OAuth scope mapping.
    • src/*.mjs — schema (build MCP input schema), dispatcher (args → CLI flags), search (keyword search over catalog), errors (PAT error rewriting), annotations. Tested by packages/shared/__tests__/*.test.mjs.
  • packages/local/ — server.mjs, a single stdio MCP server that execFiles dws. Wires into Amazon Quick Desktop / Claude Desktop / Cursor. Docs in docs/setup.md, docs/verification.md; scripts/smoke.sh.
  • packages/remote/ — multi-user AWS deployment.
    • infra/ — CDK (TypeScript via --experimental-strip-types). Stacks: oauth-stack (CloudFront, API GW, OAuth callback, DynamoDB, Secrets Manager, alarms), runtime-stack (Bedrock AgentCore Runtime container running dws), waf-stack (optional, CloudFront-scope, us-east-1). Entry: infra/bin/app.ts.
    • lambda/ — mcp-middleware (verifies HMAC bearer token, loads the user's DingTalk token, SigV4-signs the request to AgentCore), token-refresh-shim, alarm-webhook, and shared/ (hmac, sigv4, sm-client). Tests are *.test.ts colocated.
    • docker/ — the Streamable-HTTP container: server.js dispatches MCP over HTTP, inject-token.mjs provisions a per-user DWS_CONFIG_DIR so each teammate's dws runs under their own identity.
    • scripts/ — install.sh, deploy.sh, ops.sh, teardown.sh, test-e2e.sh.
  • config/ — shared, non-secret config consumed by both deploy scripts and CDK: alarm-presets.json, alarm-thresholds.json (standard/relaxed/strict), i18n.json (zh/en strings), oauth-scopes.json.
  • docs/ — remote deploy/operations/security/observability/cost/FAQ (index in docs/README.md). Public-facing: keep it free of internal dev history, real domains/account IDs, and date-stamped changelog prose.

Read the full file on GitHub · 96 lines

Changes

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.

  1. 6d ago First seen · 96 lines · 1,491 tokens per session scan A d12602165076

Subscribe to this mod's changes

quick-dingtalk-mcp CLAUDE.md is an instructions file published in the GitHub repository keithyt06/quick-dingtalk-mcp (8 stars, last pushed 2mo ago), licensed MIT. It adds 1,491 tokens to every session, about $0.0075 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.

amazon-qclaude-desktopcursordingtalkdwsmcp
Related

Other instructions, from other repositories

mcpm.sh CLAUDE.md

Instructions for pathintegral-institute/mcpm.sh: This file contains conventions that Claude should follow when working on this project.

pathintegral-institute/mcpm.sh · 202 tokens

mcpm.sh GEMINI.md

Instructions for pathintegral-institute/mcpm.sh: Reference CLAUDE.md for project conventions.

pathintegral-institute/mcpm.sh · 11 tokens

Basecamp-MCP-Server CLAUDE.md

Instructions for georgeantonopoulos/Basecamp-MCP-Server, covering claude.md, development commands, setup (one-time) - requires python 3.10+, option 2: using pip (if python 3.10+ already installed) and oauth authentication.

georgeantonopoulos/Basecamp-MCP-Server · 1,662 tokens

ls-mcp AGENTS.md

AGENTS.md instructions for lirantal/ls-mcp, covering agents.md, start here, documentation, prs and issues and releases.

lirantal/ls-mcp · 357 tokens

brightspace-mcp-server AGENTS.md

AGENTS.md instructions for RohanMuppa/brightspace-mcp-server, covering project rules, when adding a new feature, commit format, npm publishing and architecture.

RohanMuppa/brightspace-mcp-server · 551 tokens

cosmos-mcp CLAUDE.md

Instructions for teampolarity/cosmos-mcp, covering cosmos-mcp, layout, tools (authoritative list in src/tools/index.ts), cli subcommands and imessage is the headline source.

teampolarity/cosmos-mcp · 1,310 tokens