agentmods.dev

api-mcp CLAUDE.md

Project instructions for a remote MCP server that connects Claude to ZapSign, an electronic-signature service, through OAuth and a web API.

In plain words
What is it for?
Guiding work on the server's authentication, API client, MCP tools, tests, and Cloudflare Worker structure.
Why use it?
They give an agent the project rules, architecture, required reading, and coding constraints before it changes the code.

Instructions file

1 4d ago A scan 845 tokens original MIT
View the source file ZapSign/api-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/zapsign/api-mcp/claude-md
Clone the repo
git clone --depth 1 https://github.com/ZapSign/api-mcp
Per session 845 This file is loaded in full into every session.
When invoked 845 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 $0.00845 $0.00845
Opus 5 $0.00423 $0.00423
Sonnet 5 $0.00169 $0.00169
Haiku 4.5 $0.00085 $0.00085

Measured yesterday against content hash 3e2ba5a262c0, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

api-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 yesterday.

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 · 83 lines

How it starts

The opening of the file, as written. The whole thing — 83 lines — stays where its author put it; the contents beside it link to each section on GitHub.

ZapSign MCP Server — Claude Code Instructions

What This Project Is

Remote MCP server (Cloudflare Workers + TypeScript) that connects Claude AI to ZapSign's electronic signature API via OAuth 2.1. Target: Anthropic MCP Connectors Directory.

MANDATORY: Read Before Any Task

  1. AGENTS.md — Coding standards, architecture patterns, commit convention. Non-negotiable.
  2. The assigned task, issue, or pull request — Scope, acceptance criteria, dependencies, and blockers.
  3. Relevant code, tests, and documentation — Confirm the current contract before changing it.

Architecture

src/index.ts          → Worker entry (OAuthProvider wiring)
src/server.ts         → McpServer factory (new per request)
src/auth/             → OAuth handler, API token validation, token exchange
src/api/              → ZapSign HTTP client + endpoint constants
src/errors/           → Error hierarchy (base, api, auth, valid.)
src/types/            → Cloudflare Env bindings, ZapSign API types
src/utils/            → Logger, MCP response formatters, scope
src/tools/            → 12 MCP tools (docs×5, signers×4, tpl×3)

Non-Negotiable Rules (from AGENTS.md)

  • No any — use unknown + type guards
  • No else after return — early return pattern always
  • No switch — use Record<string, handler> maps
  • No enum — use as const objects
  • No as assertions — except with untyped libs (comment why)
  • Max 40 lines per function, max 2 nesting levels
  • McpServer created PER REQUEST (CVE GHSA-345p-7cg4-v4c7) — never cache globally
  • Tools never call fetch() directly — always through ZapSignClient
  • Every tool needs annotations: readOnlyHint, destructiveHint, idempotentHint, openWorldHint: true, title
  • Tool responses: JSON.stringify(result) — no pretty-print, 25k token limit
  • Error messages must be ACTIONABLE for Claude (explain how to recover)

Dev Commands

npm run dev          # wrangler dev (local server)
npm run typecheck    # tsc --noEmit
npm run lint         # eslint src/
npm run test         # vitest run
npm run deploy       # wrangler deploy

Read the full file on GitHub · 83 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. yesterday First seen · 83 lines · 845 tokens per session scan A 3e2ba5a262c0

Subscribe to this mod's changes

api-mcp CLAUDE.md is an instructions file published in the GitHub repository ZapSign/api-mcp (1 stars, last pushed 4d ago), licensed MIT. It adds 845 tokens to every session, about $0.0042 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.

Backend and APIsSecurityTesting
Related

Other instructions, from other repositories

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.

github/spec-kit · 7,104 tokens

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.

openai/codex · 5,182 tokens

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).

microsoft/vscode · 6,785 tokens

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.

langchain-ai/langchain · 4,345 tokens

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).

microsoft/vscode · 5,001 tokens

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.

vercel/next.js · 7,296 tokens