wm

Show all /code subcommands with one-line descriptions.

Show all /explore subcommands with one-line descriptions.

Show all /test-suite subcommands with one-line descriptions.

Cancel wm flow immediately

Revise spec.md and todos/TODO-N.md so they match what the last commit related to TODO-N actually implemented.

Analyzes codebase implementation details. Call the codebase-analyzer agent when you need to find detailed information about specific components. As always, the more detailed your request prompt, the better! :)

Implements one TODO in isolated worktree.

Implementation agent. Implements medium and complex tasks.

Planning agent — produces `.notes/spec.md` and `.notes/todos/TODO-N.md` files. Workflow defined in `code` skill.

Research teammate — explores codebase, gathers context, saves findings to .notes/. Cannot edit source code.

One entry point for spec writing, implementation, and bug fixing. Default is new (write spec → grill loop → produce notes → author TODO bodies). Other subcommands: verify (audit), revise (sync to shipped), prototype (settle a decision), code-map (diagram), impl (execute one TODO), fix (analyze cause, correct thoughts, fix behavior), help (this page). Invoke as /code <subcommand>.

`/explore <subcommand>`. Pick the route, read its reference, follow it. Default is `docs`. Artifacts live in `<notes-dir>/research/`.

Adversarially verify that an implemented TODO satisfies its spec. Reads `<notes-dir>/todos/TODO-N.md` (Outcome, Changes, Autotest), inspects the real diff/commit, re-runs the Autotest, and writes a `<notes-dir>/verify-TODO-N.md` verdict (PASS | DEVIATES) with a deviation list. Independent of the implementer — the post-implementation half of spec verification. Run after impl, before the user commits (or right after the commit).

Red-Green-Refactor cycle for bug fixes. Before fixing a bug, first write a failing test that reproduces it (Red), then make the minimal change to pass (Green), then clean up the code (Refactor). Use on any bug fix, error correction, failing test repair, or when user says "fix this bug".

One entry point for all testing work. Use when the user wants to design a test strategy (pairwise tiering across unit/integration/manual), enumerate scenarios + a coverage matrix before implementation, audit/score an existing test set for missed cases, apply black-box techniques (equivalence partitioning, boundary values, decision tables, state transition, state-combination), write BDD Given/When/Then scenarios, drive a feature/bug-fix spec-before-code (TDD), test a harness plugin in isolation, or run the verify phase where the user reviews an implementation. Invoke as `/test-suite <subcommand>`.

1 hook across 1 event