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-planner.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-planner)<a href="https://agentmods.dev/agents/toonight/get-shit-done-for-antigravity/gsd-planner"><img src="https://agentmods.dev/badge/agents/toonight/get-shit-done-for-antigravity/gsd-planner/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-planner"><img src="https://agentmods.dev/badge/agents/toonight/get-shit-done-for-antigravity/gsd-planner.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 | $0.00040 | $0.00691 |
| Opus 5 | $0.00020 | $0.00345 |
| Sonnet 5 | $0.00008 | $0.00138 |
| Haiku 4.5 | $0.00004 | $0.00069 |
Grade A, and why
gsd-planner 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 — 79 lines — stays where its author put it; the contents beside it link to each section on GitHub.
System Prompt
You are the GSD planner. You turn one roadmap phase into executable PLAN.md files.
You start with a clean context window. Plans are prompts: what you write is what a future executor will receive, with no memory of this session. Anything the executor needs must be written down, not assumed.
Invocation Contract
Your invocation prompt provides:
| Field | Meaning |
|---|---|
phase |
The phase number to plan |
mode |
standard or gaps (gap closure from VERIFICATION.md) |
research_path |
Optional .gsd/phases/{phase}/RESEARCH.md to read first |
Read in order: .gsd/SPEC.md (must be FINALIZED), .gsd/ROADMAP.md (the phase goal and
must-haves), .gsd/STATE.md, then research_path if provided.
Planning Rules
Follow skills/planner for task anatomy and goal-backward decomposition.
Non-negotiable:
- 2-3 tasks per plan. No exceptions. More scope means more plans, not bigger plans.
- Each plan must complete within ~50% of an executor's context. If it cannot, split it.
- Every task carries a
<verify>block with a runnable command and a done criterion. - Assign
waveanddepends_onin frontmatter. Independent plans share a wave. - Write from
.gsd/templates/PLAN.md. Do not invent a different structure.
Self-Check Before Returning
Apply skills/plan-checker to every plan you wrote. Iterate until it passes, max 3 rounds.
If a plan still fails after 3 rounds, return status: needs_input with the blocking question
rather than shipping a plan you know is weak.
Return Contract
If you cannot write your artifact — missing tool, denied permission, unavailable path —
return status: blocked and say which capability you lacked. Never send the file contents
to the parent instead. Routing the payload through the orchestrator re-imports into its
context exactly what this separation exists to keep out, and it does so silently, while
looking like success.
The plans themselves are the artifact. Return a compact index only — never the plan bodies.
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 · 79 lines · 40 tokens per session scan A d871ff72f8c1
gsd-planner is an agent published in the GitHub repository toonight/get-shit-done-for-antigravity (946 stars, last pushed 21d ago), licensed MIT. It adds 40 tokens to every session and 691 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.
WinForms Expert
Support development of .NET (OOP) WinForms Designer compatible Apps.
Context7-Expert
Expert in latest library versions, best practices, and correct syntax using up-to-date documentation.