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 skills add tanaikech/ggsrun --skill gas-executiongit clone --depth 1 https://github.com/tanaikech/ggsrunWrote 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/tanaikech/ggsrun/gas-execution)<a href="https://agentmods.dev/skills/tanaikech/ggsrun/gas-execution"><img src="https://agentmods.dev/badge/skills/tanaikech/ggsrun/gas-execution/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/tanaikech/ggsrun/gas-execution"><img src="https://agentmods.dev/badge/skills/tanaikech/ggsrun/gas-execution.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00034 | $0.02280 |
| Opus 5 | $0.00017 | $0.01140 |
| Sonnet 5 | $0.00007 | $0.00456 |
| Haiku 4.5 | $0.00003 | $0.00228 |
Grade A, and why
gas-execution 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 12d 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 — 88 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Google Apps Script Execution and Development Skill
Follow these guidelines when writing, reviewing, and executing Google Apps Script (GAS) applications:
Script Execution via ggsrun
- Execution Tool (
exe1): Always prefer theexe1tool of theggsrunMCP server to synchronize local code/directories and run the entry function in a single transaction. - Opt-in Log Retrieval (Default Off): To guarantee sub-second execution,
ggsrundoes not fetch logs from Cloud Logging by default. If you need to inspectLogger.log()orconsole.log()outputs, you must explicitly set thelog: trueparameter (or use the--log/-lflag in CLI mode). Note that enabling log retrieval adds a 5–10 second delay to allow Google's indexing. - Clock-Drift Immunity:
ggsrunqueries Cloud Logging using a wide past window (timestamp >= startTime - 60m) and completely omits any future upper bounds (timestamp <= ...). This makes the query completely immune to local clock drift (e.g., when the host machine's clock is minutes or hours behind the actual time). Do not worry about clock discrepancies when retrieving logs. - Post-Detection Multi-Poll Buffer: Due to Google's parallel logging nodes,
console.logandLogger.logcan index several seconds apart. Onceggsrundetects the first log entry for the current Apps Scriptprocess_id, it automatically queries 4 more times at 2.0-second intervals (providing an 8.0-second stabilization window) to capture all lagging streams. - TUI On-Demand Async Log Injection: When executing via the TUI (
ggsrun fd), the execution result is displayed instantly without waiting. An overlay modal then prompts: "Do you want to retrieve execution logs from Cloud Logging?". If you select Yes, logs are fetched in a background goroutine and dynamically injected into the active text view. - In-Memory Sandbox (
sandbox): For secure execution, pass the path of your whitelist configuration JSON (e.g.sandbox: "sandbox_config.json") toexe1. This instructsggsrunto generate a separate sandbox guard file (_for_sandbox_gas.gs) containing the whitelists, which is evaluated first alphabetically by the GAS V8 engine. The user's execution scripts only undergo static token replacement (e.g.,SpreadsheetApp->_wrappedSpreadsheetApp), meaning their line numbers remain completely unchanged. If an error occurs, the line numbers in the stack trace will match your local source files exactly, allowing you to debug directly. - Auto-Cleanup & Resilient Rollback:
ggsrunperforms an in-memory backup of the remote project state (including all script files and theappsscript.jsonmanifest). On execution completion, runtime sandboxing halts, or process interrupts (Ctrl+C),ggsrunautomatically rolls back all file changes on the remote script project, leaving your codebase 100% clean and pristine. This cleanup behavior is enabled by default. To bypass this cleanup and leave the uploaded files in the remote project, use theundeleteScript: trueoption (or--undeleteScript/--udflag in CLI mode). - Intelligent Manifest Merging: When executing scripts that require Advanced Services or custom dependencies, you can upload a local
appsscript.jsonmanifest.ggsrunwill automatically merge your dependencies (e.g.,enabledAdvancedServicesor customlibraries) with the remote project's existing manifest without breaking critical configurations likeexecutionApiorwebappneeded for execution. - Self-Healing Recovery: If a script execution is interrupted and the remote project is left in an inconsistent state, you can run the
ggsrun recovercommand to immediately restore the project to the pristine ggsrun state. - Designing Return Values: The execution response displays only the value returned by the
returnstatement of the executed function. Design your script to return a meaningful value representing the execution result. - Detailed Logs: You can return detailed logs or execution summaries as the final return string to provide context and results to the user.
- JSON Serialization: If returning structured data (such as objects, arrays, or status maps), use
JSON.stringify()to serialize it before returning.
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.
- 12d ago First seen · 88 lines · 34 tokens per session scan A 6c87cad15b76
gas-execution is a skill published in the GitHub repository tanaikech/ggsrun (172 stars, last pushed 17d ago), licensed MIT. It adds 34 tokens to every session and 2,280 once invoked, about $0.0002 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 2026-08-30.
Other skills, from other repositories
printing-press-amend
Amend a published CLI from one of two input sources: (1) dogfood mode mines the active Claude Code session transcript for friction (missing flags, hand- rolled API payloads, silent-null returns); (2) direct-input mode accepts user-supplied asks (rename a command, add commands or feeds, fix a named bug, optionally…
printing-press
Set up a new integration, connector, or CLI binding for any API. Wrap or generate a ship-ready Go CLI from an OpenAPI, HAR, or Postman spec via the lean research -> generate -> build -> shipcheck loop. Use when the user says build a CLI, wrap this API, set up a new integration, add a connector, integrate with a…
opensrc
Fetch dependency source code to give AI agents deeper implementation context. Use when the agent needs to understand how a library works internally, read source code for a package, fetch implementation details for a dependency, or explore how an npm/PyPI/crates.io package is built. Triggers include "fetch source for"…
lap
LAP CLI -- compile, search, and manage API specs for AI agents. Use when working with API specifications (OpenAPI, GraphQL, AsyncAPI, Protobuf, Postman), compiling specs to LAP format, searching the LAP registry, generating skills from API specs, or publishing APIs. Commands: init, compile, search, get, skill…
lap
LAP CLI -- compile, search, and manage API specs for AI agents. Use when working with API specifications (OpenAPI, GraphQL, AsyncAPI, Protobuf, Postman), compiling specs to LAP format, searching the LAP registry, generating skills from API specs, or publishing APIs. Commands: init, compile, search, get, skill…
binance-spot-openapi-skill
Operate Binance Spot market, account, and order APIs through UXC with a curated OpenAPI schema, Binance query signing, and separate mainnet/testnet link flows.