wjgoarxiv/copilot-swarm

csw-debugging

Diagnose runtime failures with reproducible observations, competing hypotheses, runtime-aware probes, causal root-cause proof, regression tests, and real-surface verification.

csw-deslop

Remove mechanical and AI-generated code smells from a bound diff while locking behavior, preserving intentional safeguards, and applying an evidence-based review rubric.

csw-frontend

Design and implement polished, accessible interfaces through design-system audit, task-centered hierarchy, complete interaction states, responsive behavior, and fresh visual evidence.

csw-git

Perform conservative Git status, commit, history, rebase, and recovery work with explicit mode selection, atomic scope, conflict evidence, and non-destructive recovery paths.

csw-init

Build a concise hierarchical AGENTS.md knowledge base from measured repository structure, verified commands, ownership boundaries, complexity scoring, and deduplicated local guidance.

csw-interview

Turn ambiguous product or technical intent into a decision-complete brief through evidence-first intake, weighted ambiguity tracking, one-question rounds, challenge modes, and explicit handoff boundaries.

csw-loop

Activate when the user types `csw`, prefixes a task with `csw`, or asks to run the full loop; bind observable criteria and drive them through planning, test-first work, real-surface QA, review, cleanup, and machine-receipt completion.

csw-lsp

Configure, diagnose, and prove language-server support through Copilot CLI native LSP surfaces, including root discovery, semantic operations, and graceful failure cases.

csw-plan

Use before non-trivial implementation to explore the real repository, resolve material ambiguity, create one decision-complete plan with observable criteria and rollback, review it adversarially, and stop at explicit user approval.

csw-programming

Implement production code with repository-native tooling, test-first behavior, typed boundaries, compact architecture, language-specific guidance, and real-surface verification.

csw-refactor

Restructure code without unintended behavior change through an explicit intent gate, dependency codemap, characterization tests, reversible checkpoints, and real-surface comparison.

csw-review

Run a binding, all-or-nothing review for broad, risky, shared, security-sensitive, or release-facing work across compliance, code quality, real manual QA, evidence integrity, security, and scope fidelity.

csw-visual-qa

Verify web and terminal interfaces with fresh scenario captures, interaction and accessibility checks, reference-aware review, and explicit evidence-backed verdicts.

csw-work

Execute an explicitly approved plan to evidence-gated completion through durable checkpoints, test-first changes, real-surface QA, review, failure recovery, rollback, cleanup receipts, and current machine evidence.

swarm

Use native Copilot CLI scheduling for two or more independent subtasks, with self-contained delegation packets, host-enforced read-only policy, isolated git worktrees for writers, skeptical integration, and explicit failure and cleanup handling.