route-github-agent-checks
Installation
SKILL.md
Route GitHub Agent Checks
Choose exactly one bounded live check, validate its unpaid x402 challenge, and use the typed result as a decision gate. Do not buy a broad bundle when one endpoint answers the task.
Select the check
| Need | Product | Method and path | Maximum | Operating skill |
|---|---|---|---|---|
| Assess one public bounty issue | BountyVerdict | GET /api/verdict |
50,000 atomic USDC | preflight-github-bounties |
| Rank 2–10 public bounty issues | BountyVerdict Portfolio | POST /api/portfolio |
400,000 atomic USDC | preflight-github-bounties |
| Audit repository coding-agent instructions | HarnessVerdict | GET /api/harness |
30,000 atomic USDC | audit-agent-harness |
| Audit one public skill before installation | SkillVerdict | GET /api/skill |
60,000 atomic USDC | preflight-agent-skills |
| Diagnose one public GitHub Actions run | RunVerdict | GET /api/run |
40,000 atomic USDC | diagnose-github-actions |
| Decide whether one completed failed run merits a retry | FlakeVerdict | GET /api/flake |
70,000 atomic USDC | classify-github-flakes |
Use RunVerdict when the root cause or next repair action is unknown. Use FlakeVerdict only for the narrower retry-versus-investigate decision. If no row fits, do not purchase; find a more relevant service.