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.
git clone --depth 1 https://github.com/stevegustafson32/google-multi-accountWrote 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/commands/stevegustafson32/google-multi-account/reauth)<a href="https://agentmods.dev/commands/stevegustafson32/google-multi-account/reauth"><img src="https://agentmods.dev/badge/commands/stevegustafson32/google-multi-account/reauth.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 5.1 | $0.00016 | $0.00798 |
| Opus 5 | $0.00008 | $0.00399 |
| Sonnet 5 | $0.00003 | $0.00160 |
| Haiku 4.5 | $0.00002 | $0.00080 |
Grade A, and why
reauth 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 6d 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 — 82 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Google Multi-Account MCP — Re-authorize
Re-consent every configured Google account against the current scope list. Use this when:
- Drive tools fail with
Insufficient Permission— the account's token was minted before Drive was added, and Google binds scopes to the refresh token at consent time. - Any tool returns a
reauth_commandhint — the refresh token was revoked or expired. driveScopechanged in~/.google-multi-mcp/config.json(full⇄file).- The server logs
Drive scope not yet consented for: …at startup.
Gmail and Calendar keep working the whole time. Only the newly-added scope is missing.
Step 1: Confirm what needs it
node -e "const c=require(require('os').homedir()+'/.google-multi-mcp/config.json');for(const a of c.accounts){console.log(a.label,a.email,'scopeVersion:',a.scopeVersion??'(pre-Drive)')}"
Any account showing (pre-Drive) or a scopeVersion below 2 needs re-consent.
Step 2: Run it
macOS / Linux
cd ~/.google-multi-mcp/server && npm run setup -- --reauth
Windows (PowerShell)
cd $env:USERPROFILE\.google-multi-mcp\server ; npm run setup -- --reauth
If npm isn't found, the user is on a version manager Claude didn't inherit:
source ~/.nvm/nvm.sh && cd ~/.google-multi-mcp/server && npm run setup -- --reauth
This walks every configured account through Google's consent screen, one after another. It does not ask any questions — it reuses the labels and emails already in the config.
Step 3: Warn the user about the two screens they'll see
This is the step people get stuck on. Tell them BEFORE the browser opens.
Screen 1 — "Google hasn't verified this app." Red warning triangle, and a Back to safety button that does not complete setup.
This is expected. The plugin uses an OAuth client that hasn't been through Google's formal verification review — the same screen appears for any self-published app requesting Gmail or Drive access. Nothing is wrong.
Click Advanced (bottom left), then Go to google-multi-account (unsafe).
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.
- 6d ago First seen · 82 lines · 16 tokens per session scan A 70f993d14ebc
reauth is a command published in the GitHub repository stevegustafson32/google-multi-account (2 stars, last pushed 1mo ago), licensed MIT. It adds 16 tokens to every session and 798 once invoked, about $0.0001 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 commands, from other repositories
checklist
Generate a custom checklist for the current feature based on user requirements.
clarify
Identify underspecified areas in the current feature spec by asking up to 5 highly targeted clarification questions and encoding answers back into the spec.
specify
Create or update the feature specification from a natural language feature description.
analyze
Perform a non-destructive cross-artifact consistency and quality analysis across spec.md, plan.md, and tasks.md after task generation.
converge
Assess the current codebase against the feature's spec, plan, and tasks, then append any remaining unbuilt work as new tasks to tasks.md so implement can complete it.
implement
Execute the implementation plan by processing and executing all tasks defined in tasks.md.