Autonomous AI dev-team bot
This repository also configures its own agents. See what flock tells them →
Agent Claude Code
Meta-reviewer and loop-breaker. Governs both phases (pre-PR and on-PR review), enforces the gates and cycle limits, and decides continue/approve/escalate so agents never loop. Risk-aware and multi-service aware.
Agent Claude Code
Implements the planned change on a feature branch and addresses PR review comments. Handles single-repo and coordinated multi-service changes; keeps changes minimal and contract-safe.
Agent Claude Code
Turns a feature request into a concrete spec and execution plan. Identifies which repo(s)/microservices are affected (one or many), the cross-service contract changes, the ordered task breakdown with dependencies, and the risks. Read-only — produces the plan the team executes.
Agent Claude Code
Read-only adversarial reviewer. Pre-PR it returns a verdict for the arbiter; on an open PR it posts true line-anchored INLINE comments via the git-host API, written in the PR's own language. Scores risk and checks cross-service compatibility. Never edits code.
Agent Claude Code
Runs and writes tests — the green-build gate. Covers per-repo unit/integration tests and the cross-service seam when a feature spans services.
Agent Claude Code
Handles Telegram Business messages on behalf of the owner with read-only knowledge retrieval.
Agent Claude Code
Handles LO messages on behalf of the owner with read-only knowledge retrieval.
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: