#ci

Offline, no-AI "safe to ship?" gate for vibe-coded apps — finds the security mistakes AI coding agents make (secrets, unprotected routes, eval-RCE, SQLi, CORS, JWT, leaked keys). CLI + MCP, agent-runnable.

Turn failing pytest runs into structured repair reports: failure parsing, root-cause diagnosis, flaky detection, dry-run fix diffs, and an optional LLM layer. 把失败的 pytest 运行转化为结构化修复报告。

Claude Code skills that stop an agent from reporting work as finished before it has been demonstrated on the running system.

Find Rust test-oracle gaps before mutation testing: static RIPR evidence for CI, editors, and agents.

Portable agent skills (SKILL.md) for Claude Code, Copilot CLI, Codex & Cursor — reviewloop (clear every PR reviewer), ciloop (fix red CI), standup (daily standup from your PRs). Install per-skill or bundled.

Deterministic repo preflight scanner for AI-assisted development workflows

Open, always-on leaderboard + CI gate for autonomous coding agents — every patch sandboxed, every run traced, every regression fails the build. $0 stack.

Behavioral cross-agent testing for agent skills — run a skill on Claude Code and Codex and assert deterministic outcomes.

Cost-free Ollama-powered code-review agent for Claude Code — multi-angle finders, adversarial verify, green/yellow/red CI verdict.

TypeScript CLI for installing agent skills, hooks, and CI/publish templates for Claude Code and related tools.

Release gate for agent plugins: sniff broken hooks, missing manifests, npm payload mistakes, and SARIF/CI issues before users do.

A thin, CI-gated evaluation gate for RAG & LLM systems — golden set, band-based pass/warn/fail gates, LLM-judge or heuristic scorers. pip install raggate

Hermes-inspired security control plane for LLM agents over private DMs: allowlist, PIN, kill switch, rate limits, injection heuristics, secret redaction, audit log.

Fail-closed evidence gates for experiments and AI-agent workflows

Deterministic agent-eval / benchmark-grading hygiene audit CLI. Detects the silent mis-scoring bug class (pytest cov-gate leakage). Free lead-magnet for the paid harness-audit service.

GitHub Action that lints CLAUDE.md-style agent constitution files for missing operational guardrails — spend limits, injection defense, escalation paths, secrets rules

Seven x402 decision APIs and installable agent skills for GitHub bounties, CI, skill security, and MCP drift

Fails your CI when an AI coding agent disables Supabase Row Level Security, widens a Postgres grant, exposes a service_role key, or skips Stripe webhook verification. Zero-dependency Node CLI and GitHub Action, 22 rules.

Run your GitHub Actions CI on your own machine, in seconds. Agent-ready.

Clean, single-use GitHub Actions runners on the Macs and Linux machines you already have, set up by your coding agent. The CLI, MCP server, rules and docs.

Find the deprecated and retired LLM models your code still calls. CLI, pre-commit hook and GitHub Action that fail your build before an OpenAI or Anthropic model is retired.

Agentic Site Score Check 2026 - Free GitHub CI Action for Not Human Search