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/helloworld-open/word-mcp-server/agents-mdgit clone --depth 1 https://github.com/HelloWorld-Open/word-mcp-serverWrote 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.
[](https://agentmods.dev/instructions/helloworld-open/word-mcp-server/agents-md)<a href="https://agentmods.dev/instructions/helloworld-open/word-mcp-server/agents-md"><img src="https://agentmods.dev/badge/instructions/helloworld-open/word-mcp-server/agents-md.svg" alt="Measured on agentmods" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5 | $0.00597 | $0.00597 |
| Opus 5 | $0.00298 | $0.00298 |
| Sonnet 5 | $0.00119 | $0.00119 |
| Haiku 4.5 | $0.00060 | $0.00060 |
Grade A, and why
word-mcp-server 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 4d 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 — 45 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Word MCP Server — 开发者速查
Build & test
npm run build # tsc, output to build/
npm test # vitest run --exclude 'tests/integration/**' (skips smoke tests, needs Word)
npm run dev # tsc --watch
npx tsc --noEmit # typecheck-only (no linter configured)
Architecture constraints (enforced by tests/arch/arch.test.ts)
src/word/must NOT import fromsrc/server/src/server/must NOT access.rawon COM proxy objects
Entry points
build/parent.js— watchdog process, spawns/restartsbuild/child.jsbuild/child.js— MCP server, createsWordSession+ wires all tools- MCP client config:
{ "command": "node", "args": ["path/to/build/parent.js"] }
Platform
- Windows-only (
"os": ["win32"],"cpu": ["x64"]) - Requires MSVC Build Tools (winax native addon), Word installed
COM proxy layers
word/com-proxy/: DocumentProxy, SelectionProxy, RangeProxy — typed COM wrappers- SectionProxy + HeaderFooterProxy + FieldProxy — section/header/footer operations
- CollectionProxy<T> with itemFactory — generic COM collection wrapper
All proxy methods wrap COM calls with try-catch + safe defaults. No bare COM access in business logic (arch test enforces this).
Key patterns
- Content writing: always streaming.
word_stream_start({baseStyleProfile:{...}}) → word_stream_block(×N) → word_stream_end(). - Tool registration:
createRegTool→mcpCallmiddleware: rate limit → precheck → ensureReady → timeout → handler → audit → circuit breaker → recovery. - Cursor: ContextSanitizer ensures cursor in main body before edits. After header/footer/page-number/watermark ops, cursor auto-restored.
- Anti-patterns in
src/index.ts:68-98(set font before typing, find+goTo, undo after save, word_open vs word_document).
Mocks
word/com-proxy/com-proxy.mock.ts: MockDocumentProxy, MockSelectionProxy, MockRangeProxy, mockSectionProxy, mockHeaderFooterProxy.tests/unit/test-helpers.ts: createMockDoc, createMockSel, createMockSession.tests/arch/uses ts-morph (devDep) for AST-level constraint checks.
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.
- 4d ago First seen · 45 lines · 597 tokens per session scan A 9b4c2968f7d4
word-mcp-server AGENTS.md is an instructions file published in the GitHub repository HelloWorld-Open/word-mcp-server (3 stars, last pushed 2mo ago), licensed MIT. It adds 597 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
mcp-server-powerpoint copilot-instructions.md
Copilot instructions for sbroenne/mcp-server-powerpoint, covering project instructions — powerpointmcp, critical files (read these first), sister projects, what is powerpointmcp? and session model (mcp server).
mcp-server-powerpoint architecture-patterns.instructions.md
Instructions for sbroenne/mcp-server-powerpoint, covering architecture patterns, .net class design (mandatory), layered architecture (critical), command pattern and structure (per domain).
mcp-server-powerpoint critical-rules.instructions.md
Instructions for sbroenne/mcp-server-powerpoint, covering critical rules - must follow, rule 1: success/errormessage invariant, rule 1b: no exception suppression in core, rule 30: real-com integration tests only, strict tdd and rule: 1-based indexing everywhere.
mcp-server-powerpoint mcp-server-guide.instructions.md
Instructions for sbroenne/mcp-server-powerpoint, covering mcp server development guide, llm-facing content rules, two kinds of tools: hand-written vs. generated, implementation pattern: single hand-written dispatch tool and error handling (mandatory).
mcp-server-powerpoint testing-strategy.instructions.md
Instructions for sbroenne/mcp-server-powerpoint, covering testing strategy, strict tdd (red → green), test project layout, serialization is mandatory and trait tagging (required for surgical filtering).
mcp-server-powerpoint code-review.instructions.md
Instructions for sbroenne/mcp-server-powerpoint, covering copilot code review, interop and resource safety, contract and path completeness and protocol, tests, and user-facing surfaces.