flow

Adversarial test generation. Writes tests designed to break the implementation, runs them, and reports failures as findings.

Fix CI failures. Use when bin/flow ci or bin/ci fails and needs diagnosis.

Documentation and maintainability review. Receives diff, investigates codebase and docs, produces findings for comprehension barriers and documentation drift.

Cognitively isolated compliance audit and process analysis. Receives diff, state file data, plan, and project rules. Produces findings categorized by the three Learn tenants: process gaps, rule compliance, and missing rules.

Pre-mortem incident analysis. Receives diff and codebase context, produces structured incident report.

Context-isolated code review. Receives diff and project conventions, produces structured findings for architecture, simplicity, and correctness.

Abort the current FLOW feature. Closes the PR, deletes the remote branch, removes the worktree, and deletes the state file. Available from any phase. Use --manual for confirmation prompt.

Phase 4: Code Review — six tenants assessed by four cognitively isolated agents (reviewer, pre-mortem, adversarial, documentation) launched in parallel. Parent session gathers context, triages findings, and fixes.

Phase 3: Code — execute plan tasks one at a time with TDD. Review diff before each commit. bin/flow ci must pass before moving to the next task. Project architecture standards enforced.

Review the full diff, then git add + commit + push. Use at every commit checkpoint in the FLOW workflow.

Phase 6: Complete — merge the PR, remove the worktree, and delete the state file. Final phase.

Display the current FLOW configuration from .flow.json — version and per-skill autonomy settings.

Capture a brainstormed solution as a pre-planned issue with an Implementation Plan section for fast-tracking through the Plan phase.

Decompose a large project into GitHub issues with sub-issue and blocked-by relationships, milestones, and phase labels.

Full codebase documentation accuracy review — reports drift between code behavior and documentation.

Audit instruction corpus health — CLAUDE.md, rules, and memory for staleness, misplacement, duplication, and contradictions.

Fetch open issues, analyze mechanically, rank by impact, and display a dashboard with recommended work order.

Phase 5: Learn — audit rule compliance and identify process gaps. Routes findings to CLAUDE.md, .claude/rules/, and plugin issues.

Capture a correction or learning to the FLOW state file. Invoke explicitly with /flow:flow-note. Fast — captures and continues without interrupting flow.

Process decomposed issues sequentially overnight via flow-start --auto, tracking outcomes and generating a morning report.

Phase 2: Plan — invoke DAG decomposition, explore the codebase, design the approach, and create an implementation plan.

One-time project setup — configure and commit workspace permissions, install bin/* stubs, and write the version marker. Run once after installing or upgrading FLOW. Usage: /flow:flow-prime

Reset all FLOW artifacts. Closes PRs, removes worktrees, deletes branches, clears state files.

Phase 1: Start — begin a new feature. Creates a worktree, upgrades dependencies, opens a PR, creates .flow-states/<branch>/state.json, and configures the workspace. Usage: /flow:flow-start <feature name words>

Show current SDLC phase, PR link, timing, and what comes next. Reads .flow-states/<branch>/state.json. Use any time you want to know where you are in the workflow.

13 hooks across 7 events