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/evolsb/claude-code-google-workspace/claude-mdgit clone --depth 1 https://github.com/evolsb/claude-code-google-workspaceWrote 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/evolsb/claude-code-google-workspace/claude-md)<a href="https://agentmods.dev/instructions/evolsb/claude-code-google-workspace/claude-md"><img src="https://agentmods.dev/badge/instructions/evolsb/claude-code-google-workspace/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 | $0.01995 | $0.01995 |
| Opus 5 | $0.00997 | $0.00997 |
| Sonnet 5 | $0.00399 | $0.00399 |
| Haiku 4.5 | $0.00199 | $0.00199 |
Grade B, and why
claude-code-google-workspace CLAUDE.md scanned grade B with 1 finding 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.
Reads MCP configurationmediumAgent snooping
mcp.json carries server URLs and auth tokens; reading it lets a mod discover and abuse other integrations.
**Add `.mcp.json` to `.gitignore`** — it contains tokens. How it starts
The opening of the file, as written. The whole thing — 244 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Claude Code Google Workspace + Slack MCP Setup
This repo helps users set up Google Workspace and Slack MCP servers for Claude Code.
Your Role
You are a setup assistant. Walk the user through configuring MCP servers for their Google account(s) and optionally Slack. Be concise and direct.
Setup Flow
Step 1: Install Google Workspace CLI
npm install -g @googleworkspace/cli
Verify: gws --version (should be 0.7+)
Step 2: Create GCP Project
Guide the user to https://console.cloud.google.com/projectcreate
- Project name: something like
gws-mcp(must be globally unique) - Note the project ID — you'll need it
Step 3: Enable APIs
gcloud services enable gmail.googleapis.com drive.googleapis.com calendar-json.googleapis.com sheets.googleapis.com docs.googleapis.com --project=PROJECT_ID
Step 4: Create OAuth Consent Screen
Guide user to: https://console.cloud.google.com/apis/credentials/consent?project=PROJECT_ID
- User Type: External (unless Google Workspace admin)
- App name: anything (e.g., "Claude MCP")
- Support email: user's email
- Scopes: skip (scopes are requested at login)
- Test users: Add ALL Google accounts they want to use (critical for unverified apps)
- Save
Step 5: Create OAuth Client (one per Google account)
Guide user to: https://console.cloud.google.com/apis/credentials?project=PROJECT_ID
For EACH Google account:
- Create Credentials → OAuth client ID
- Application type: Desktop app
- Name: descriptive (e.g., "MCP - personal" or "MCP - work")
- Download the JSON → save to
~/.config/gws/client_secret_ACCOUNTNAME.json
CRITICAL: Each Google account MUST have its own OAuth client. Using one client for two accounts causes refresh token invalidation.
Step 6: Authenticate Each Account
For each account:
# Copy this account's client secret into place
cp ~/.config/gws/client_secret_ACCOUNTNAME.json ~/.config/gws/client_secret.json
# Login (browser opens — sign in with the correct Google account)
gws auth login -s drive,gmail,calendar,sheets,docs
# Export credentials
gws auth export --unmasked > ~/.config/gws/ACCOUNTNAME.json
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 · 244 lines · 1,995 tokens per session scan B a6b68b8e1848
claude-code-google-workspace CLAUDE.md is an instructions file published in the GitHub repository evolsb/claude-code-google-workspace (35 stars, last pushed 1mo ago), licensed MIT. It adds 1,995 tokens to every session, about $0.0100 per session on Opus 5. A static security scan graded it B with 1 finding (reads mcp configuration). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other instructions, from other repositories
agentbits AGENTS.md
AGENTS.md instructions for rwaldman/agentbits, covering agent bits — public agent notes, canonical endpoints, how to use this repository, discovery order and mcp install.
mcp-hub CLAUDE.md
Claude Code instructions for ftaricano/mcp-hub, covering claude.md -- mcp-hub, o que e, stack & estrutura, como rodar / validar and setup.
mcp-hub AGENTS.md
AGENTS.md instructions for ftaricano/mcp-hub: As regras operacionais deste repo sao canonicas em CLAUDE.md (fonte unica para Claude/Codex/Hermes). Leia-o antes de tocar em codigo.
askaipods CLAUDE.md
Instructions for Delibread0601/askaipods, covering askaipods — project instructions, release notes style, release workflow, zero-dependency constraint and instruction-content language.
mcp-limitless CLAUDE.md
Claude Code instructions for 199-mcp/mcp-limitless, covering claude.md, project overview, common development commands, install dependencies and build typescript to javascript.
continuum AGENTS.md
AGENTS.md instructions for sudomichael/continuum: This version has breaking changes — APIs, conventions, and file structure may all differ from your training data. Read the relevant guide in nodemodules/next/dist/docs/ before writing any code. Heed deprecation notices.