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/a1-x-tech/mcp-google-docs/claude-mdgit clone --depth 1 https://github.com/A1-x-Tech/mcp-google-docsWrote 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/a1-x-tech/mcp-google-docs/claude-md)<a href="https://agentmods.dev/instructions/a1-x-tech/mcp-google-docs/claude-md"><img src="https://agentmods.dev/badge/instructions/a1-x-tech/mcp-google-docs/claude-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 | $0.02341 | $0.02341 |
| Opus 5 | $0.01171 | $0.01171 |
| Sonnet 5 | $0.00468 | $0.00468 |
| Haiku 4.5 | $0.00234 | $0.00234 |
Grade A, and why
mcp-google-docs 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 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 — 136 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md — mcp-google-docs
MCP server for the Google Docs API v1 (TypeScript, stdio). Mixed read/write:
tools cover document creation (incl. from Markdown), reading as text/structure/
Markdown, index-based text editing, character/paragraph styles, lists, tables,
breaks, images, Drive-backed comments and export; raw_request is the escape
hatch. The server talks to https://docs.googleapis.com with a Bearer token
(the token is minted from an OAuth2 refresh token via
https://oauth2.googleapis.com/token, or a static GOOGLE_DOCS_ACCESS_TOKEN,
mostly for testing). Export, Markdown conversion and comments have no Docs API
endpoints — the client calls Drive API v3 on https://www.googleapis.com as an
internal dependency; no general-purpose Drive tool is exposed.
Commands
npm run dev # run from source (tsx watch)
npm test # unit tests + dist smoke, no network
npm run typecheck # types for src + tests
npm run build # emit dist/
npm run smoke # live check: read-only by default; GOOGLE_DOCS_SMOKE_LIVE_WRITE=1
# runs create→edit→export→delete on a disposable doc (cleanup in finally)
Architecture
src/config.ts— env → config. Credentials: either the refresh tripleGOOGLE_DOCS_CLIENT_ID+GOOGLE_DOCS_CLIENT_SECRET+GOOGLE_DOCS_REFRESH_TOKEN(all three orConfigErrorincomplete_oauth_config) orGOOGLE_DOCS_ACCESS_TOKEN; optionalGOOGLE_DOCS_API_BASE,GOOGLE_DOCS_DRIVE_API_BASE,GOOGLE_DOCS_TIMEOUT_MS,GOOGLE_DOCS_MAX_RETRIES. No credentials at all is NOT an error: the fields stayundefinedand the server starts degraded. Also home toCredentialsError/MISSING_CREDENTIALS_MESSAGE(opens with the historical startup error verbatim, then names the variables and the restart) andhasCredentials().src/client.ts— all HTTP and all wire mapping for BOTH hosts. Token lifecycle (cache until ~60s before expiry, dedupe concurrent refreshes, one forced re-mint + replay on 401); the privatesend()core resolves the path against the given base and rejects foreign origins (SSRF guard), enforces an AbortController timeout that also covers reading the body (bytes, because exports are binary), retries 429 always but 5xx/network errors only for GET — replaying a write after an ambiguous failure would duplicate it — and throwsGoogleDocsError(status, body). Typed per-endpoint methods build the batchUpdate requests and computedfieldsmasks; pure exported helpers (buildTextStyle,buildParagraphStyle,mapBulletPreset,hexToRgbColor,extractBlocks,extractDocumentText,extractTabTree) carry the normalized→wire vocabulary and the text extraction. Drive methods (exportDocument,importMarkdown,createDocumentFromMarkdown, comments,deleteFilefor smoke cleanup) use the same core with the Drive base;request()(raw_request surface) is pinned to the Docs base.src/tools/documents.ts—create_document,get_document,read_document_text,list_tabs,export_document,import_markdown.src/tools/text.ts—insert_text,replace_range,replace_all_text,delete_range.src/tools/styles.ts—style_text,style_paragraph,set_paragraph_bullets.src/tools/tables.ts—insert_table,edit_table.src/tools/structure.ts—insert_break.src/tools/images.ts—insert_image,replace_image.src/tools/comments.ts—list_comments,manage_comment.src/tools/raw.ts—raw_request(GET/POST, Docs host only).src/tools/util.ts—ok/fail, the four annotation presets (READ_ONLY/WRITE/UPDATE/DESTRUCTIVE) and shared zod schema factories (documentIdSchema,indexSchema,tabIdSchema,segmentIdSchema,hexColorSchema).src/index.ts— wires everyregister*into the McpServer.loadConfigOrDegraded()catchesConfigError, pingsstartup_failed(fire-and-forget) and degrades the config to "no credentials"; an unconfigured start prependsUNCONFIGURED_PREFIX— plusConfiguration problem: <message>when a ConfigError was caught — to the initializeinstructions, andoninitializedsendsserver_startfor a configured install orunconfigured_start(with the reason) otherwise.src/telemetry.ts— anonymous usage pings (ids/names/versions only, never data or arguments; fire-and-forget, must never block or throw; opt-outASKADS_TELEMETRY=0).server_startmeans "a usable install started";unconfigured_startis a degraded start andstartup_faileda malformed config caught at load — both carry areasonfrom a closed vocabulary (missing_credentials,incomplete_oauth_config) — never a variable's name or value.
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 · 136 lines · 2,341 tokens per session scan A b897d256286b
mcp-google-docs CLAUDE.md is an instructions file published in the GitHub repository A1-x-Tech/mcp-google-docs (0 stars, last pushed 5d ago), licensed MIT. It adds 2,341 tokens to every session, about $0.0117 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
next.js AGENTS.md
AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.
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.
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).
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.
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.
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).