# Verify > Drive the contracts engine's runtime surface (the stdio MCP server) to verify changes end-to-end. Scoped to public-plugins/plugins/healthcare/skills/contracts/ and ../../servers/documents/. - Skill: `anthropics-healthcare/verify` (Agent Skill) - Install (CLI): `npx skillmds@latest add anthropics-healthcare/verify` - Raw SKILL.md: https://api.skillmd.com/api/skills/anthropics-healthcare/verify/raw - Safety review: pending - Works with: Claude Code, Claude.ai, OpenAI Codex - Category: AI & ML - Author: anthropics (https://skillmd.com/u/anthropics-healthcare) - Updated: 2026-09-09 - Page: https://skillmd.com/skills/anthropics-healthcare/verify --- # Verifying contracts-engine changes The engine is the MCP server at `../../servers/documents/src/index.mjs` — plain runnable `.mjs`, no build step; the source IS the shipped artifact. Most changes are drivable without a full /contracts session by speaking JSON-RPC to the server over stdio. - Typecheck: `cd ../../servers/documents && bun run check` (tsc over the .mjs via checkJs). There is no bundle; edits to src are live immediately. - Data: `~/.claude/data/healthcare/documents/data.sqlite` — the dir is the *server's* name (`documents`), not the skill's (`contracts`); shared across checkouts; safe to delete — schema v-check tells users to do the same. For throwaway runs point `CLAUDE_HEALTHCARE_DATA` at a scratch PARENT dir (the server appends `documents/`) — never drive tests against the live db. Corpus names live in `corpus_documents.corpus`; query before assuming. - CLI mode: `node ../../servers/documents/src/index.mjs ''` runs one tool call without MCP — result JSON on stdout, exit 1 + stderr on error. Bare invocation is MCP stdio. - Schema changes: views and triggers are dropped/recreated on every open, so editing one reaches existing databases for free. Dropping a *column* is breaking — it needs a `SCHEMA_VERSION` bump and forces every user to delete their db. Verify either kind by opening the real db read-only afterwards and checking `PRAGMA user_version` did not move. - **Concurrency changes need racing, not single runs**: spawn ≥16 servers with `&` under `/bin/bash` (zsh backgrounding under the CC sandbox emits bogus `nice(5)` failures), fresh AND warm db, ≥60 trials each. Desktop-side repro evidence: `~/Library/Logs/Claude/main.log`, grep `LocalMcpServerManager`. - **Tool schemas must be JSON Schema draft 2020-12.** The API validates them when an *agent* spawns, so a bad schema shows up as "agent terminated early: input_schema is invalid" — never as a server error, and never in a plain tools/list. Two zod idioms silently emit draft-07: `z.tuple([...])` (array-form `items` → use `z.array().length(n)`) and `z.union([...])`/`.nullish()` on primitives (`type: [...]` → use `.optional()` or one type). `servers/documents/test/schema.test.ts` guards this; run `bun test` after touching any tool's inputSchema, and spawn a real agent (`claude --plugin-dir -p "spawn subagent_type 'healthcare:documents-reader-cli' …" --allowedTools Agent`) after changing agent tool lists. - MCP smoke: pipe `initialize` → `notifications/initialized` → `tools/list` / `tools/call` lines into `node ../../servers/documents/src/index.mjs` and read the JSON-RPC replies. A sequential client (write line, read reply) avoids out-of-order confusion. Core chain worth driving after engine changes: `corpus_prepare` (temp dir with a .txt) → `write runs/briefs` → `find` with `cites: [{doc_id, lines, has}]` (expect one citation per cite, `kind:"exact"`) AND a bogus `has` (expect the row rejected, batch intact) → `coverage`. The CLI takes ` -` with JSON on stdin, which is how workers send document text without shell escaping. - **Sweep** is `sweep.mjs` (no agent loop, one toolless extraction per doc — verify it with `--limit 2` against a scratch `CLAUDE_HEALTHCARE_DATA` db; also pass `--groups` with one 2-doc family JSON and expect `family: