Install
$ agentstack add skill-mike007jd-game-superpowers-gsp-rolling-supervisor ✓ scanned · ✓ verified, works with Claude Code, Cursor, and more.
Security review
✓ PassedNo issues found. Passed automated security review. · v0.1.0 How review works →
- ✓ Prompt-injection patterns
- ✓ Secret / credential exfiltration
- ✓ Dangerous shell & filesystem operations
- ✓ Untrusted network calls
- ✓ Known-malicious package signatures
What it can access
- ✓ Network access No
- ✓ Filesystem access No
- ✓ Shell / process execution No
- ✓ Environment & secrets No
- ✓ Dynamic code execution No
From automated source analysis of v0.1.0. “Used” means the capability is present in the source — more access means more to trust, not that it’s unsafe.
Verified badge
Passed review? Show it. Paste this badge into your README, it links to the public security report.
Reliability & compatibility
Declared compatibility
Compatibility is declared by the source manifest. End-to-end runtime verification is coming, see below.
We're building live execution health for every listing: tool-call success rate, median latency, uptime, and last-checked timestamps, measured, not self-reported. It isn't live yet, so we don't show numbers we can't stand behind.
How agent discovery & health will work →About
Game Rolling Supervisor
Goal
Push a game project through repeated autonomous passes without letting one long context rot into uselessness.
Outputs
Follow the gsp-orchestrator output strategy:
- inline (default): present rolling supervisor plan in conversation.
- minimal or full: write
docs/game-studio/rolling-supervisor.mdanddocs/game-studio/rolling/state.json.
Use:
./shared/templates/rolling-supervisor-plan.md./shared/reference/rolling-supervisor-architecture.md./schemas/rolling-state.schema.json./schemas/session-result.schema.json
Rules
- use this only when the repo can tolerate repeated build/verify/repair cycles
- prefer short-lived worker sessions over one giant session
- every worker must emit a compact structured handoff
- verification gates decide whether to continue
- use worktree isolation for parallel branches when practical
- do not create infinite hook or stop loops
- if the project is live or risky, only enable with explicit authorization
Worker graph
Typical graph:
- concept/requirements brainstorm
- scope profile
- architecture/plan
- build
- verify
- feedback design/polish
- verify again
- repair if needed
Important
The supervisor belongs outside the plugin runtime. The plugin defines the contracts; an external Python supervisor executes them.
Source & license
This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.
- Author: mike007jd
- Source: mike007jd/game-superpowers
- License: MIT
Install and usage instructions live in the source repository linked above.
Reviews
No reviews yet, be the first.
Write a review
Versions
- v0.1.0 Imported from the upstream source.