Borrowing it
Nothing to install: this file belongs to brucemcpherson/gas-fakes. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/brucemcpherson/gas-fakes/main/.agents/skills/gas-fakes-dev/SKILL.mdgit clone --depth 1 https://github.com/brucemcpherson/gas-fakesWrote 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/skills/brucemcpherson/gas-fakes/gas-fakes-dev)<a href="https://agentmods.dev/skills/brucemcpherson/gas-fakes/gas-fakes-dev"><img src="https://agentmods.dev/badge/skills/brucemcpherson/gas-fakes/gas-fakes-dev/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.
<a href="https://agentmods.dev/skills/brucemcpherson/gas-fakes/gas-fakes-dev"><img src="https://agentmods.dev/badge/skills/brucemcpherson/gas-fakes/gas-fakes-dev.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00000 | $0.07711 |
| Opus 5 | $0.00000 | $0.03855 |
| Sonnet 5 | $0.00000 | $0.01542 |
| Haiku 4.5 | $0.00000 | $0.00771 |
Grade A, and why
gas-fakes-dev scanned grade A with 2 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 10d 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
- **Network Call Safety**: All network-based commands (e.g., `curl`) MUST include an aggressive timeout (e.g., `--max-time 5` or `--connect-timeout 2`) to prevent processes from hanging and accruing costs in the event of Runs shell commandslowCapability
Expected in a hook, worth knowing in a rule or an instructions file.
- **Retry Mechanism**: Always implement a retry loop (e.g., 5 retries with 5s delay) for `gcloud iam` commands that depend on recently created resources. A simple busy-wait or `execSync` to a sleep command can be used in How it starts
The opening of the file, as written. The whole thing — 260 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Summary
This skill enables the agent to assist in the development of the gas-fakes project. The primary objective is to emulate Google Apps Script (GAS) behavior using Node.js and Google APIs, allowing Apps Script code to run in a local Node.js environment.
Usage
- When you need to implement fake/mock functionality for GAS classes or methods.
- When creating test scripts to verify the implemented functionalities.
- When assisting a human developer with Node.js and Google APIs integration.
Workflow
0. Local Model Consultation (Hybrid Hierarchical Delegation)
Before drafting implementation plans, code, tests, refactoring, debugging, analyzing logs, or drafting documentation, Gemini (the Strategic Planner) must first gather all relevant file context, decompose the request into structured atomic sub-tasks, and call the local model (via the omlx:query_local_model tool with the prompt parameter) to generate precise code implementations, detailed tests, refactored components, bug fixes, or documentation updates.
1. Context and Specification Check
Before implementing, verify the specifications of the target Google Apps Script classes and methods. Ensure that the functionality you are about to build aligns with real GAS behavior.
2. Implementation & Focused Execution (CRITICAL DELEGATION GATE)
[!IMPORTANT] ZERO-TOLERANCE DELEGATION GATE You are FORBIDDEN from using
write_fileorreplaceto implement logic, write tests, perform refactoring, diagnose/fix debug errors, or draft documentation yourself. MANDATORY SEQUENCE:
- Gather context (Research).
- CALL
omlx/query_local_modelwith a comprehensive prompt containing specific constraints.- Review and synthesize the output.
- Apply changes to files (e.g., in
src/,test/, etc.).EXCEPTION: This mandate only applies if the local model is available and its use has not been explicitly forbidden by the user. If unavailable or forbidden, you may proceed with the tasks using your own weights, but you MUST document the reason in your
update_topic.You MUST explicitly state "Delegating logic generation/task to local Gemma model" in your
update_topicsummary when transitioning to execution.
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.
- 10d ago First seen · 260 lines · 0 tokens per session scan A 6d402d42c3e3
gas-fakes-dev is a skill published in the GitHub repository brucemcpherson/gas-fakes (79 stars, last pushed 3d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 7,711 tokens. A static security scan graded it A with 2 findings (makes network calls, runs shell commands). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-01.
Other skills, from other repositories
apify-actor-development
Important: Before you begin, fill in the generatedBy property in the meta section of .actor/actor.json. Replace it with the tool and model you're currently using, such as "Claude Code with Claude Sonnet 4.5". This helps Apify monitor and improve AGENTS.md for specific AI tools and models.
dynamo-recipe-runner
Select, validate, patch, and deploy existing NVIDIA Dynamo Kubernetes recipes. Use for model/backend/GPU/deployment-mode recipe bring-up; use router-starter for router-only mode work and troubleshoot for broken deployments.
mcp-server
Configure, launch, validate, and troubleshoot CCAM's comprehensive MCP server for Claude Code, Codex, and other MCP hosts. Use when installing dependencies, building the server, selecting stdio, HTTP, or REPL transport, setting mutation/destructive policy, supplying dashboard authentication, or checking complete tool…
enterprise
Enterprise-grade systems with microservices, Kubernetes, Terraform, and AI Native methodology. For multi-feature initiatives spanning a release timeline, combine with /sprint master-plan (v2.1.13) to group features into a single 8-phase sprint container with shared scope/budget and 4 auto-pause triggers…
deploy
Elixir/Phoenix deployment patterns — Dockerfile, fly.toml, runtime.exs, mix release, rel/ overlays. Use when configuring Fly.io, Docker, CI/CD, health checks, or production migrations.
spring-boot-project-creator
Creates and scaffolds a new Spring Boot project (3.x or 4.x) by downloading from Spring Initializr, generating package structure (DDD or Layered architecture), configuring JPA, SpringDoc OpenAPI, and Docker Compose services (PostgreSQL, Redis, MongoDB). Use when creating a new Java Spring Boot project from scratch…