zen-flow

Discover files with trigger_phrase and/or refresh frontmatter, let the user choose which to schedule for periodic re-injection via CronCreate. Prevents behavioral drift by keeping core rules and goals fresh in context.

Write trigger phrases from .claude/triggers.json into file frontmatter as model-scoped trigger_phrase fields. Bridges trigger generation (scan) with scheduled injection (zenflow:schedule).

Build a GitHub issue into a PR. User-launched with an issue number — reads the issue, confirms with user, creates branch, implements against acceptance criteria, runs verification, and opens a PR. Every decision surfaces via AskUserQuestion.

Collaborative working session — you and the user are a team exploring, researching, and planning together. When implementation work is needed, create well-structured GitHub issues. The user launches Builder agents to implement and Reviewer agents to verify.

Shed accumulated context mid-session. Writes a knowledge handoff document capturing session state, decisions, observations, and behavioral calibration, then guides the user through /clear and resumption.

Runtime verification using Playwright MCP + proof artifacts. Use when acceptance criteria mention UI behavior, when claiming runtime verification, or when independently verifying a PR's claims. Produces artifact-backed proof — screenshots, DOM snapshots — not prose claims.

Review a PR with structured feedback, independent runtime verification, and pattern recognition. Use when reviewing any PR. Reads the diff, runs a checklist, independently verifies claims, and posts a structured review comment with severity tiers.

Aggregate journal entries to surface patterns — recurring blockers, most-modified files, effective tools, and team velocity trends. Use for retrospectives, standups, or understanding project health.

Use when fixing bugs, errors, or unexpected behavior. Launches parallel diagnostic agents then a specialist to fix. Use for any issue that starts with "X is broken", "X doesn't work", error reports, or failing tests.

Use when executing implementation plans with independent tasks in the current session

Use when you have a written implementation plan to execute in a separate session with review checkpoints

Study the codebase and available agents to generate a zen.local.md config. Run once to onboard a new project, or re-run to update config after adding agents.

Use when you have a spec or requirements for a multi-step task, before touching code

Read recent journal entries. Use when resuming work, checking what was done recently, or reviewing a specific session's history.

End-of-session retrospective — analyze the current session's journal entries and surface actionable insights for future sessions. Use before ending a long session or at natural stopping points.

Open the journal in a browser with the Tokyo Night HTML viewer.

Append a structured journal entry after completing work. Use at the end of any task, feature, bug fix, or session to record what was done, what went wrong, and what was learned.

Validate completed work passes all quality gates (lint, format, tests, docs, journal). Use after finishing implementation tasks to ensure nothing is missed. Fixes failures automatically using subagents.

You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.

Run cross-model comparison — scan files with haiku, sonnet, and opus study agents to see how model size affects trigger phrase generation.

Build a reverse word-to-files index from all stored triggers. Model-aware — builds per-model lookup so agents find triggers matched to their own model.

Study files and generate semantic trigger phrases by spawning a researcher agent that samples model associations and finds convergent patterns. Supports model-specific triggers via --models flag.

Scan prompt files, CLAUDE.md docs, skill definitions, and other documentation to seed trigger phrases — bootstrapping total-recall from existing project knowledge. Supports --models flag for model-scoped triggers.

Create or update project documentation. Use when adding new features, changing architecture, or when docs are missing or outdated. Generates README, ARCHITECTURE, API docs, and guides.

Remove trigger phrases for a file or glob pattern from .claude/triggers.json

Display all stored trigger phrases from .claude/triggers.json