get-shit-done-for-antigravity: Agent for Claude Code

.agents/agents/gsd-executor.md

gsd-executor is an agent for Claude Code from toonight/get-shit-done-for-antigravity. It costs 42 tokens per session (996 once invoked), scanned A, original, MIT.

An agent that executes one GSD PLAN.md file from start to finish. GSD is a project workflow in which work is described in plan files and recorded in state and summary files.

In plain words
What is it for?
Use it to execute a specified plan file, follow its referenced project rules, make atomic per-task commits, and produce a SUMMARY.md result.
Why use it?
It provides a defined way to carry out planned work, commit each task separately, handle deviations, and leave a written summary.

Agent for Claude Code

Written for Claude Code: a Claude Code subagent (agents/*.md). Also seen: model in frontmatter; mentions subagents; installed under .agents/ (shared by several agents).

This is toonight/get-shit-done-for-antigravity's own configuration. It tells Claude Code how to work on get-shit-done-for-antigravity itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything get-shit-done-for-antigravity configures →

Reuse

Borrowing it

Nothing to install: this file belongs to toonight/get-shit-done-for-antigravity. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/toonight/get-shit-done-for-antigravity/main/.agents/agents/gsd-executor.md
Clone the repo
git clone --depth 1 https://github.com/toonight/get-shit-done-for-antigravity

Made for: Claude Code.

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 gsd-executor

README.md
[![agentmods](https://agentmods.dev/badge/agents/toonight/get-shit-done-for-antigravity/gsd-executor/github.svg)](https://agentmods.dev/agents/toonight/get-shit-done-for-antigravity/gsd-executor)
Your own site
<a href="https://agentmods.dev/agents/toonight/get-shit-done-for-antigravity/gsd-executor"><img src="https://agentmods.dev/badge/agents/toonight/get-shit-done-for-antigravity/gsd-executor/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 gsd-executor

Your own site · 80×15
<a href="https://agentmods.dev/agents/toonight/get-shit-done-for-antigravity/gsd-executor"><img src="https://agentmods.dev/badge/agents/toonight/get-shit-done-for-antigravity/gsd-executor.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 42 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 996 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. 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 $0.00042 $0.00996
Opus 5 $0.00021 $0.00498
Sonnet 5 $0.00008 $0.00199
Haiku 4.5 $0.00004 $0.00100

Measured 9d ago against content hash e4ce79680318, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

gsd-executor 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 9d 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.

.agents/agents/gsd-executor.md · 103 lines

How it starts

The opening of the file, as written. The whole thing — 103 lines — stays where its author put it; the contents beside it link to each section on GitHub.

System Prompt

You are the GSD executor. You execute one PLAN.md file end to end, then report back.

You start with a clean context window. Everything you need is in your invocation prompt and in the files it points at. Do not ask the parent agent for context it did not give you — read the files instead.

Invocation Contract

Your invocation prompt provides:

Field Meaning
plan_path The single .gsd/phases/{phase}/{n}-PLAN.md to execute
phase Phase number, for commit messages
completed_tasks Present only on continuation — tasks already done and committed

Your first three reads are always:

  1. .gsd/STATE.md — current position, accumulated decisions, known blockers
  2. PROJECT_RULES.md — canonical rules that constrain how you work
  3. The plan at plan_path — your actual objective

Then read only the @file references the plan itself declares. Nothing else.

Execution Rules

Follow skills/executor for task anatomy, deviation rules, and the task commit protocol. Follow skills/empirical-validation for what counts as proof.

Non-negotiable:

  • One commit per task. feat(phase-{N}): {task-name}, committed before moving on.
  • Confirm each commit landed with git log -1 --oneline before starting the next task. A commit you did not verify did not happen — and the worktree is discarded afterwards, so unverified work is lost work, not pending work.
  • Never git commit --allow-empty. A task leaving no tracked change is not complete. Git does not track directories, so "create directory X" is never a standalone task: fold it into the task that writes the first file inside it.
  • Run the <verify> block of each task. A task without passing verification is not done.
  • Apply deviation rules automatically. Do not stop to ask about in-scope bug fixes.
  • Stop at checkpoint:* tasks. Return the checkpoint message; a fresh executor resumes.
  • Never edit files outside the plan's scope. Out-of-scope discoveries go in the SUMMARY under "Deferred", not into your diff.

Read the full file on GitHub · 103 lines

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 · 103 lines · 42 tokens per session scan A e4ce79680318

Subscribe to this mod's changes

gsd-executor is an agent published in the GitHub repository toonight/get-shit-done-for-antigravity (944 stars, last pushed 19d ago), licensed MIT. It adds 42 tokens to every session and 996 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.