GitHub Actions failure diagnosis, bounty checks, and AGENTS.md audits for AI coding agents — Agent Skills and an x402-paid MCP server with MCP schema-drift checks.
Skill Claude CodeCodex
Audit public GitHub repositories with HarnessVerdict before autonomous coding. Use when checking AGENTS.md, CLAUDE.md, GEMINI.md, Copilot or Cursor instructions, validating SKILL.md files, investigating ignored or stale guidance, or deciding whether a repository is structurally ready for coding agents.
Skill Claude CodeCodex
Compare complete MCP 2025-11-25 tools/list snapshots before accepting a server upgrade or changed tool catalog. Use after notifications/tools/listchanged, at agent startup when a catalog hash differs from the pinned baseline, or before installing, enabling, or repinning a catalog-serving endpoint.
Skill Claude CodeCodex
Classify a completed public GitHub Actions failure with FlakeVerdict before spending a retry. Use when deciding whether a failed workflow run is a confirmed flake, likely flake, recurring failure signature, new failure, inconclusive failure, or not currently failed by comparing attempts, same-commit outcomes, and…
Skill Claude CodeCodex
Diagnose a public GitHub Actions workflow run with RunVerdict before changing code or rerunning CI. Use when a GitHub Actions run, job, matrix shard, test suite, build, lint, dependency install, timeout, runner, authentication, or infrastructure step failed and the agent needs evidence-linked root causes…
Skill Claude CodeCodex
Audit public agent SKILL.md bundles with SkillVerdict before installation or execution. Use when evaluating a third-party Codex, Claude Code, Gemini, OpenClaw, or cross-agent skill; checking scripts, credential access, prompt injection, persistence, destructive commands, remote execution, symlinks, submodules…
Skill Claude CodeCodex
Evaluate public GitHub bounty issues with BountyVerdict before an autonomous coding agent spends compute or repository reputation. Use when deciding whether to pursue one bounty, comparing 2-10 bounty candidates, checking for competing work or withdrawn rewards, or verifying repository AI-contribution rules before…
Skill Claude CodeCodex
Route GitHub engineering and MCP catalog questions to the correct BountyVerdict x402 decision API. Use for bounty selection, coding-agent instruction or skill audits, workflow diagnosis, flake retry gates, and tools/list compatibility or security checks before accepting a server change.
At most 3 mods per repository are shown here, and a mod shipped inside a plugin is left to that plugin's page — the rest are on their repository pages: