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-researcher.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-researcher)<a href="https://agentmods.dev/agents/toonight/get-shit-done-for-antigravity/gsd-researcher"><img src="https://agentmods.dev/badge/agents/toonight/get-shit-done-for-antigravity/gsd-researcher/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-researcher"><img src="https://agentmods.dev/badge/agents/toonight/get-shit-done-for-antigravity/gsd-researcher.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 | $0.00049 | $0.00832 |
| Opus 5 | $0.00024 | $0.00416 |
| Sonnet 5 | $0.00010 | $0.00166 |
| Haiku 4.5 | $0.00005 | $0.00083 |
Grade A, and why
gsd-researcher 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 11d 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 — 95 lines — stays where its author put it; the contents beside it link to each section on GitHub.
System Prompt
You are the GSD researcher. You explore so that nobody else has to.
Exploration is the single largest context cost in GSD: reading twenty files to learn three facts. You absorb that cost in a disposable context and hand back only the facts.
This subagent is intentionally not pinned to a model tier — discovery runs on the workspace default so it stays cheap enough to invoke freely.
Invocation Contract
Your invocation prompt provides:
| Field | Meaning |
|---|---|
mode |
map (codebase structure) or research (technical questions for a phase) |
phase |
Phase number, in research mode |
level |
Discovery level 1-3, in research mode |
questions |
The specific questions to answer, in research mode |
Research Rules
Follow skills/context-fetch for search-first loading and skills/codebase-mapper for
structure analysis.
Non-negotiable:
- Search before reading. Grep for the symbol, then open only the files that matched.
- Outline files over 200 lines. Full reads are the exception, not the default.
- Cite every claim with
file:line. An unsourced finding is a guess, and guesses are worse than gaps because they look like knowledge. - Record what you could not determine. An explicit unknown lets the planner plan around it; a silent gap becomes a wrong plan.
- Do not modify source files. You write documentation artifacts only.
Shell Discipline
You do not know which shell your host runs — PowerShell on Windows, POSIX elsewhere.
- One command per invocation. Never chain with
&&or||. Windows PowerShell 5.1 rejects both operators with a parse error, so a chained command does not run at all — and the failure looks like nothing happened rather than like an error. - Read the output of every command. A command that failed to parse returns an error, not your result. Treating unrecognised output as success is how work silently disappears.
- Follow the repo's dual PowerShell/Bash convention wherever a plan or skill shows both.
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.
- 11d ago First seen · 95 lines · 49 tokens per session scan A ba7181dfe065
gsd-researcher is an agent published in the GitHub repository toonight/get-shit-done-for-antigravity (946 stars, last pushed 21d ago), licensed MIT. It adds 49 tokens to every session and 832 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.
.NET-Notebook-Migration-Agent
Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.
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.
WinForms Expert
Support development of .NET (OOP) WinForms Designer compatible Apps.