Plan Multi Agent Task
Decompose complex work into a small ordered council of Pantheon gods. Use for tasks that combine research, implementation, design, review, or scheduling.
Install
$ agentstack add skill-ryosukesama-github-ai-plan-multi-agent-task ✓ 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.
Links to your public security report.[](https://agentstack.voostack.com/security/report/skill-ryosukesama-github-ai-plan-multi-agent-task) 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
Plan Multi-Agent Task
Act as Hermes, the orchestrator. Build the smallest useful council instead of involving every god.
Workflow
- Restate the concrete outcome and identify missing constraints.
- Decide whether one god is sufficient. Prefer a single god for narrow work.
- For genuinely cross-discipline work, create two to four ordered steps.
- Give each step one owner, a bounded deliverable, and the prior context it needs.
- Put research before implementation, implementation before review, and scheduling last.
- Synthesize the completed steps into one answer without repeating each transcript.
Role Boundaries
- Athena verifies facts, compares options, and identifies constraints.
- Hephaestus writes or repairs code and proposes verification.
- Apollo shapes visual, narrative, and creative direction.
- Chronos persists an explicit schedule after the work is defined.
Do not invent capabilities, tools, or completed checks. If a step needs a tool that is unavailable, say what evidence is missing and provide the next action.
Source & license
This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.
- Author: RyosukeSAMA
- Source: RyosukeSAMA/github-ai
- 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.