#debugging

Plugin-first AI terminal workspace for Codex and Claude Code with planning, CI/CD debugging, reusable agents, skills, TODOs, and MCP tool integrations.

git diff for your agent's context window. See exactly what your LLM saw — turn by turn, block by block.

Local replay debugger for Browser Use failures with screenshots, model I/O, failed-step timelines, and public-safe HTML exports.

8 款生产级 AI Agent Skill：持久记忆、代码安全评审、自然语言数据分析、调试复现、测试生成、IaC 安全扫描、性能诊断、文档生成 | 8 production-ready agent skills (memory, code-review security, NL data analysis, agentic debugger, testforge, iac-guard, perf-doctor, docsmith). Pure Python stdlib, zero dependencies.

Council skill for Codex, Claude Code, and AI coding agents: expert review before coding, architecture decisions, refactors, and debugging.

Open standard for AI agent capabilities. Write once, run in any compatible runtime. — pip install intentos

Zero-config, OTLP-native flight recorder for your backend. Records every request, query, job, and exception — correlated — into a beautiful TUI, a JSON CLI, and an MCP server your coding agent can drive. Local-first.

Claude Code harness — fewer tokens, fewer bugs, audit-ready. 11 engineering skills. Apache-2.0.

Autonomous crash recovery for your terminal: wrap a command; on crash, headless Claude Code diagnoses, tests, patches on a branch, and writes a post-mortem.

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。

特别适用于GPT/AI聊天文件传输的本地优先粘贴，拖动和文件切换工具 | Local-first paste, drag, and file handoff tool — especially useful for GPT/AI chat file transfer.

Crumbtrail SDKs and CLI — bug-context capture for coding agents. Source for the crumbtrail, crumbtrail-core, crumbtrail-node, crumbtrail-react, crumbtrail-react-native and crumbtrail-tauri npm packages.

An autonomous AI agent that watches server logs, detects crashes, writes code fixes, and automatically opens GitHub Pull Requests.

Local-first DevTools for debugging LangGraph checkpoints and agent memory.

Debug any product by USING it (living the full user cycle, all features, like a picky user) instead of green tests. Start interview (Goal+Benchmark), two modes: Solo and Agentic+ (delegate fixes to agents). Claude Code skill.

Claude Code skill + /debug command that finds a bug's root cause from real runtime data — temporary NDJSON probes, a localhost ingest server for browser/container/remote targets, and verifiable cleanup.