gf_agent

gf_agent is a skill for Claude Code, Codex from brucemcpherson/gas-fakes. It costs 29 tokens per session (10,372 once invoked), scanned A, original, MIT.

A specialized agent for automating Google Workspace apps such as Docs, Sheets, Slides, Forms, Drive, and Calendar. It runs Google Apps Script locally through a Node.js testing environment.

In plain words
What is it for?
Creating, reading, and updating Workspace files and coordinating tasks across several Google services.
Why use it?
It lets developers test Workspace automation without depending on a live Apps Script session for every change.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one. Also seen: mentions subagents.

Not installable: its command points at a path on the author’s own machine, so it runs nowhere else. The line is /Users/brucemcpherson/Documents/repos/gas-fakes/doccreation/gi-fake-all.json.

Good fit Creating, reading, and updating Workspace files and coordinating tasks across several Google services.

Compare 6 skills from other repositories ↓
Install

Getting it into your agent

There is no command for this one: it runs only inside a plugin, and the catalogue could not identify which plugin ships it. The source is linked below.

Made for: Claude Code, Codex.

Wrote 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.

agentmods badge for gf_agent

README.md
[![agentmods](https://agentmods.dev/badge/skills/brucemcpherson/gas-fakes/gf_agent/github.svg)](https://agentmods.dev/skills/brucemcpherson/gas-fakes/gf_agent)
Your own site
<a href="https://agentmods.dev/skills/brucemcpherson/gas-fakes/gf_agent"><img src="https://agentmods.dev/badge/skills/brucemcpherson/gas-fakes/gf_agent/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for gf_agent

Your own site · 80×15
<a href="https://agentmods.dev/skills/brucemcpherson/gas-fakes/gf_agent"><img src="https://agentmods.dev/badge/skills/brucemcpherson/gas-fakes/gf_agent.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 29 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 10,372 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 1 finding. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00029 $0.10372
Opus 5 $0.00015 $0.05186
Sonnet 5 $0.00006 $0.02074
Haiku 4.5 $0.00003 $0.01037

Measured 9d ago against content hash c19eff30106a, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

gf_agent scanned grade A 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 9d ago.

The scan reads SKILL.md. This mod also ships 1 executable file (scripts/builder.js), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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.

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

2. Sub-Agent uses `curl` + `awk` (or `web_fetch`) to find the information.
gf_agent/SKILL.md · 557 lines

How it starts

The opening of the file, as written. The whole thing — 557 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Skill: gf_agent

Overview

gf_agent is a specialized agent for automating Google Workspace tasks using the gas-fakes local emulation environment. It can generate and execute Google Apps Script (GAS) code locally on Node.js.

Capabilities

  • Automate Workspace: Create, read, and modify Google Docs, Sheets, Slides, Forms, Drive files, and Calendars.
  • Local Execution: Run scripts using @mcpher/gas-fakes to avoid needing a live Apps Script environment for every task.
  • Service Integration: Seamlessly combine multiple Google services (e.g., fetch data from a Sheet and create a Doc).
  • Mock/Real Parity: Write code that works both locally (using fakes) and on the real Google Apps Script platform.

Instructions

  1. Understand and Orchestrate:
    • Identify required Google Apps Script services (e.g., SpreadsheetApp, DriveApp).
    • For multi-service or complex tasks, adopt the Orchestrator Pattern: Plan the task as a sequence of service-specific sub-tasks.
  2. Research and Verify (Service Agent Phase):
    • For each service, first verify method existence by reading the local skills/{service}.md files in the skill directory.
    • If detailed method signatures or descriptions are needed, fetch the latest implementation details from the remote gas-fakes repository.
    • Remote URL: https://raw.githubusercontent.com/brucemcpherson/gas-fakes/main/progress/{service}.md (Note: {service} is lowercase, e.g., spreadsheet.md).
    • Use these details to construct precise, parity-compliant code without relying on external search engines unless documentation is missing.
  3. Generate Script: Create a Node.js script that:
    • Uses standard GAS syntax.
    • (Optional) Uses ScriptApp.isFake for local-only logic like logging or cleanup.
  4. Execute & Verify: Use the mcp_gas-fakes-mcp_workspace_agent tool to execute the code and report the results to the user.

Example Workflow

User: "Summarize the last 5 unread emails and save the summary to a new Google Doc." Agent:

  1. Identify Services: GmailApp, DocumentApp.
  2. Verify Methods:
    • Check skills/gmail.md and skills/document.md.
    • (Optional) Fetch progress/gmail.md and progress/document.md from GitHub for detailed signatures.
  3. Generate Script:
    const threads = GmailApp.getInboxThreads(0, 5);
    let summary = 'Email Summary:\n\n';
    threads.forEach(t => {
      const msg = t.getMessages()[0];
      summary += `From: ${msg.getFrom()}\nSubject: ${msg.getSubject()}\n---\n`;
    });
    const doc = DocumentApp.create('Email Summaries');
    doc.getBody().appendParagraph(summary);
    console.log('Summary saved to Doc ID:', doc.getId());
    
  4. Execute: Call mcp_gas-fakes-mcp_workspace_agent({ script: '...' }).
  5. Report: Confirm completion and provide the Doc ID.

Read the full file on GitHub · 557 lines

Files

What ships with it

44 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

Changes

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.

  1. 9d ago First seen · 557 lines · 29 tokens per session scan A c19eff30106a

Subscribe to this mod's changes

gf_agent is a skill published in the GitHub repository brucemcpherson/gas-fakes (79 stars, last pushed 2d ago), licensed MIT. It adds 29 tokens to every session and 10,372 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-01.