code-review
01Agent
A specialised helper for reviewing code changes, finding bugs, diagnosing causes, and challenging reported problems with counterexamples.
Always-on, self-hosted AI agent runtime — multi-LLM, parallel sub-agents, Telegram/Web/CLI, skills, memory, MCP.
Agent
A specialised helper for reviewing code changes, finding bugs, diagnosing causes, and challenging reported problems with counterexamples.
Agent
A general-purpose sub-agent for difficult coding work that needs careful judgment, such as design, root-cause analysis, or reasoning across several files.
Agent
A read-only sub-agent for locating code, files, settings, and call paths when their location is uncertain. It reports findings with file and line references rather than changing the project.
Agent
A general-purpose sub-agent for carrying out already-defined coding tasks. It can implement, modify, clean up, and verify work when the files and desired result are known.
Agent
A general-purpose sub-agent for small, clearly defined tasks such as summaries, extraction, conversion, or simple lookups. A sub-agent is a separate coding agent given one focused assignment.
Agent
An evaluation grader for coding-skill tests. It checks a runner’s result against a list of required statements, called assertions, and returns a strict JSON decision.
Agent
A controlled test runner for evaluating a coding skill. It runs one test prompt with or without the skill’s instructions and returns the original result for comparison.