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.
curl -O https://raw.githubusercontent.com/toonight/get-shit-done-for-antigravity/main/.agents/agents/gsd-executor.mdgit clone --depth 1 https://github.com/toonight/get-shit-done-for-antigravityWrote 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/agents/toonight/get-shit-done-for-antigravity/gsd-executor)<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.
<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>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 | $0.00042 | $0.00996 |
| Opus 5 | $0.00021 | $0.00498 |
| Sonnet 5 | $0.00008 | $0.00199 |
| Haiku 4.5 | $0.00004 | $0.00100 |
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.
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:
.gsd/STATE.md— current position, accumulated decisions, known blockersPROJECT_RULES.md— canonical rules that constrain how you work- 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 --onelinebefore 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.
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.
- 9d ago First seen · 103 lines · 42 tokens per session scan A e4ce79680318
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.
Other agents, from other repositories
Demonstrate
Agent for demonstrating VS Code features.
playwright-test-generator
Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.
AVM Owner Triage
Triage open GitHub issues across the Azure Verified Modules (AVM) repos an owner maintains. Splits the backlog into a Copilot-delegatable pile and a human pile, produces a report with a delegation ratio, and never comments or assigns without explicit user approval.
Ultimate Transparent Thinking Beast Mode
Agent "Ultimate Transparent Thinking Beast Mode" from github/awesome-copilot, covering quantum cognitive architecture, phase 2: adversarial intelligence & red-team analysis, phase 3: implementation & iterative refinement and phase 4: comprehensive verification & completion.
Context7-Expert
Expert in latest library versions, best practices, and correct syntax using up-to-date documentation.
Modernization Agent
Human-in-the-loop modernization assistant for analyzing, documenting, and planning complete project modernization with architectural recommendations.