BountyVerdict — GitHub & CI Preflight

Choose the right GitHub or CI decision tool for free, then diagnose failed GitHub Actions from a run URL, decide retry versus fix, audit AGENTS.md and…

От сообществаРаботаетБез входаГлобальныйБесплатноТолько чтение

Что умеет

  • Choose Github Agent Decision: Call with no arguments for a free six-tool catalog, or choose the economical next call for a GitHub bounty, coding-agent instructions, failed Actions run, retry decision,
  • Check Github Bounty: Is this public GitHub issue bounty still claimable, or is someone already working on it? Checks current status, reward evidence, competing work, and maintainer signals; returns AV
  • Rank Github Bounties: Which public GitHub bounty should I work on next? Compares 2-10 issue URLs, chooses the strongest non-AVOID candidate or recommends none, and returns cited evidence plus partial

Какие данные видит

Нужен ли аккаунт

Не нужен: сервер работает без входа

Choose the right GitHub or CI decision tool for free, then diagnose failed GitHub Actions from a run URL, decide retry versus fix, audit AGENTS.md and CLAUDE.md, check or rank GitHub bounty issues, and detect breaking MCP tools/list changes. Six paid read-only checks plus a free selector; a first unsigned call returns the exact quote and successful authorized calls cost $0.02-$0.40 USDC via x402 on Base. No buyer API key, repository clone, code execution, or CI mutation.

Список инструментов сервера (7)

Технические названия из tools/list. Нужны только разработчикам.

choose_github_agent_decisionCall with no arguments for a free six-tool catalog, or choose the economical next call for a GitHub bounty, coding-agent instructions, failed Actions run, retry decision, or MCP tools change. Returns exact prices, samples, required fields, and unsigned-quote semantics without inspecting the target.
check_github_bountyIs this public GitHub issue bounty still claimable, or is someone already working on it? Checks current status, reward evidence, competing work, and maintainer signals; returns AVOID, CAUTION, or VIABLE. For 2-7 issues, repeated single checks cost less unless one ranked response is worth the premium; use rank_github_bounties for 8-10. Inspect a representative result before paying: https://bountyverdict-agent-production.mimirslab.workers.dev/api/sample. Exact authorization cap: 0.05 USDC.
rank_github_bountiesWhich public GitHub bounty should I work on next? Compares 2-10 issue URLs, chooses the strongest non-AVOID candidate or recommends none, and returns cited evidence plus partial failures. Its $0.40 price equals eight $0.05 single checks and is cheaper per candidate at 9-10; repeated check_github_bounty calls cost less for 2-7 when ranked orchestration is unnecessary. Inspect a representative result before paying: https://bountyverdict-agent-production.mimirslab.workers.dev/api/portfolio/sample. Exact authorization cap: 0.40 USDC.
audit_agent_harnessCan a coding agent safely work in this public repository without missing project instructions? Audits AGENTS.md, CLAUDE.md, and related instructions at an immutable commit; does not diagnose CI. Inspect a representative result before paying: https://bountyverdict-agent-production.mimirslab.workers.dev/api/harness/sample. Exact authorization cap: 0.03 USDC.
diagnose_github_actions_runWhy did this public GitHub Actions run fail, and what should I fix? Uses bounded failed-job logs and redacted evidence. Use classify_github_actions_flake only for retry-once versus fix. Inspect a representative result before paying: https://bountyverdict-agent-production.mimirslab.workers.dev/api/run/sample. Exact authorization cap: 0.04 USDC.
classify_github_actions_flakeIs this failed GitHub Actions run flaky—should I retry it once or fix the code? Uses the current attempt and bounded history. Use diagnose_github_actions_run for root cause. Inspect a representative result before paying: https://bountyverdict-agent-production.mimirslab.workers.dev/api/flake/sample. Exact authorization cap: 0.07 USDC.
check_mcp_tool_driftWill upgrading to this complete MCP tools/list break my agent or weaken declared safety hints? Compares caller-supplied baseline and current snapshots; never fetches or invokes tools. Inspect a representative result before paying: https://bountyverdict-agent-production.mimirslab.workers.dev/api/mcp-drift/sample. Exact authorization cap: 0.02 USDC.