A Rust-based agent orchestrator enabling a swarm of Claude Code instances building software.
This repository also configures its own agents. See what loom tells them →
Agent Claude Code
Read-only advisory agent for debugging and repeated failures. Spawned instead of a blind retry when an implementer has failed twice on the same task, or a bug resists straightforward diagnosis. Returns a root-cause diagnosis plus one concrete next step.
Agent Claude Code
Read-only code review agent for comprehensive review of code quality, security, architecture, and best practices. Cannot modify files.
Agent Claude Code
Forwarding shim for the loom codex implementation lane. Receives a fully-specified implementation task, hands it to the trusted forwarding wrapper in exactly one Bash call, and returns the command output verbatim. Never reads, edits, or implements anything itself.
Agent Claude Code
Use PROACTIVELY for architecture design, complex debugging, design patterns, code review, test strategy, data modeling, ML system design, UX strategy, documentation architecture, and strategic technical decisions across all domains.
Agent Claude Code
Primary implementation agent for all coding work - features, bug fixes, tests, data pipelines, ML training, infrastructure code, documentation, UI components, and queries. Handles routine implementation across all technical domains.
Agent Claude Code
Read-only gate runner for a standard loom stage. Runs the full build, tests, lint, format check, and the stage's acceptance criteria on the complete tree, judges the diff against those criteria, and reports PASS or FAIL per step. Writes nothing and never fixes.
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: