cadlens-mcp: Agent for Claude Code

.claude/agents/mcp-tool-implementer.md

mcp-tool-implementer is an agent for Claude Code from cadlens-co/cadlens-mcp. It costs 63 tokens per session (604 once invoked), scanned A, original, MIT.

A code-generation workflow for adding tools to the cadlens-mcp server, an MCP server that connects an agent to CADLens functions. It follows the project’s existing TypeScript structure and adds the related registration, types, and integration test.

In plain words
What is it for?
Use it when adding a CADLens tool: provide its name, purpose, API endpoint, and request and response formats, then create the tool files and test scaffolding.
Why use it?
It removes repetitive setup when introducing a new server tool and helps keep the new code consistent with the existing project.

Agent for Claude Code

Written for Claude Code: installed under .claude/.

This is cadlens-co/cadlens-mcp's own configuration. It tells Claude Code how to work on cadlens-mcp itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything cadlens-mcp configures →

Reuse

Borrowing it

Nothing to install: this file belongs to cadlens-co/cadlens-mcp. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/cadlens-co/cadlens-mcp/main/.claude/agents/mcp-tool-implementer.md
Clone the repo
git clone --depth 1 https://github.com/cadlens-co/cadlens-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 mcp-tool-implementer

README.md
[![agentmods](https://agentmods.dev/badge/agents/cadlens-co/cadlens-mcp/mcp-tool-implementer/github.svg)](https://agentmods.dev/agents/cadlens-co/cadlens-mcp/mcp-tool-implementer)
Your own site
<a href="https://agentmods.dev/agents/cadlens-co/cadlens-mcp/mcp-tool-implementer"><img src="https://agentmods.dev/badge/agents/cadlens-co/cadlens-mcp/mcp-tool-implementer/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.

agentmods 80×15 button for mcp-tool-implementer

Your own site · 80×15
<a href="https://agentmods.dev/agents/cadlens-co/cadlens-mcp/mcp-tool-implementer"><img src="https://agentmods.dev/badge/agents/cadlens-co/cadlens-mcp/mcp-tool-implementer.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 63 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 604 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 $0.00063 $0.00604
Opus 5 $0.00032 $0.00302
Sonnet 5 $0.00013 $0.00121
Haiku 4.5 $0.00006 $0.00060

Measured 10d ago against content hash 5f2839ce9144, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

mcp-tool-implementer 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 10d 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/agents/mcp-tool-implementer.md · 37 lines

How it starts

The opening of the file, as written. The whole thing — 37 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You scaffold new MCP tools for cadlens-mcp following the established pattern. Your bias is consistency, not invention.

The pattern (study before writing)

  1. src/tools/<name>.ts exports a ToolDefinition object: name, description, inputSchema, handler.
  2. handler signature: (args: Record<string, unknown>, ctx: ToolContext) => Promise<unknown>. Return a plain JSON-serializable value — the central dispatcher in src/server.ts handles JSON.stringify and error wrapping.
  3. Throw Error for failures. CADLens API errors automatically become CadlensApiError instances from src/api/client.ts:fetch.
  4. Register the new tool in src/tools/registry.ts — add the import and append to the TOOLS array.
  5. Add an integration test under tests/integration/<name>.test.ts mirroring tests/integration/get-job.test.ts. Mock the CADLens REST endpoint with nock. Use buildCtx() from tests/helpers/build-ctx.ts.

Inputs you should expect

  • A new tool name (cadlens_<verb>_<thing>) and a short description of what it does.
  • The CADLens REST endpoint it maps to, with request/response shape — or a pointer to the section of mcp-server-reference.md that documents it.

Process

  1. Read mcp-server-reference.md for the endpoint contract.
  2. Read 1–2 existing tools to match style (src/tools/get-job.ts for a trivial read, src/tools/parse-file.ts for an upload/poll flow).
  3. Create the tool file. Keep inputSchema matching the doc — type: 'object', list required, prefer enums over free-form strings.
  4. Register in registry.ts.
  5. Add types to src/api/types.ts if the response shape isn't already covered.
  6. Write the integration test with at least: happy path, one error case.
  7. Run npm run typecheck && npm run lint && npm test and report results.

Things to avoid

  • Don't add tools that overlap with existing ones — check the registry first.
  • Don't change the ToolContext shape just to pass new state — if you need new state, add it to the dispatcher in src/server.ts first.
  • Don't add comments narrating what the code does. Only document non-obvious why-decisions inline.

Read the full file on GitHub · 37 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. 10d ago First seen · 37 lines · 63 tokens per session scan A 5f2839ce9144

Subscribe to this mod's changes

mcp-tool-implementer is an agent published in the GitHub repository cadlens-co/cadlens-mcp (1 stars, last pushed 1mo ago), licensed MIT. It adds 63 tokens to every session and 604 once invoked, about $0.0003 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.

Related

Other agents, from other repositories

Power Platform MCP Integration Expert

Expert in Power Platform custom connector development with MCP integration for Copilot Studio - comprehensive knowledge of schemas, protocols, and integration patterns.

github/awesome-copilot · 31 tokens

integrations-engineer

Third-party integration specialist for SMB Product-Builder archetypes. Owns the integration contract — OAuth2/API-key flows, webhook signature verification, idempotency keys, retry/backoff with jitter, rate-limit handling, secret storage, and sandbox→prod promotion — for Stripe, Twilio, QuickBooks, Google/Microsoft…

avelikiy/great_cto · 106 tokens

gate

API quality gates — linting, style enforcement, breaking change CI, and API governance.

tonone-ai/tonone · 19 tokens

dotnet-architecture-reviewer

Reviews a .NET codebase or repository and produces a structured architecture report — layering and dependency-rule violations, coupling, CQRS/handler hygiene, EF Core boundary leaks, testability, and concrete prioritized fixes. Use when the user wants an architecture review, a "second opinion" on structure, a PR-level…

StefanTheCode/dotnet-ai-toolkit · 102 tokens

broadcasting-agent

Creates WebSocket broadcasting infrastructure (NestJS backend) and real-time consumption on the frontend (Next.js or React). Use when adding real-time event broadcasting to a bounded context, creating Socket.IO gateways, or implementing frontend event listeners. Dispatched after infrastructure layer is complete.

Softtor/nestjs-hexagonal · 58 tokens

api-explorer

Explore and analyze API-related code. Use when investigating endpoints, routing, or HTTP handling.

huangjia2019/claude-code-engineering · 22 tokens