agents

Work a feature's ticket DAG in parallel — one orchestrator fans independent frontier tickets out to parallel worker agents and integrates them on the feature branch until the feature ships. Use when a ticketed feature has independent frontier tickets, the user says "dispatch" or wants tickets worked in parallel, or when another skill routes parallel frontier work here.

Which mx skill or flow fits the current situation — a router over the mx workflow.

Run commands in tmux whenever they run long or need eyes on them — anything expected to take more than ~30–60s (training runs, ML experiments, builds, servers), anything worth observing mid-run (progress logs, monitoring output), and anything interactive (sudo prompts, REPLs, wizards), locally or on a remote host. Always reach for this instead of a fire-and-forget Bash call in those cases — the human can attach and step in at any time.

Break a plan, spec, or the current conversation into a set of tracer-bullet tickets, each declaring its blocking edges, published per the tracker conventions — ticket files with blocked-by edges, or native blocking links on a real tracker.

Review and update Claude Code's auto-approved command allowlist based on Bash commands that triggered permission prompts in recent sessions.

Turn the current conversation into a spec and publish it to the project issue tracker — no interview, just synthesis of what you've already discussed.

File-based issue tracker conventions — how specs, tickets, and small tasks live in agent/tasks/ and how to publish, fetch, claim, and retire them. Use when publishing or fetching a spec/ticket/task, picking work from the frontier, or when another skill says "publish to the issue tracker".

Scan recent Claude Code sessions and classify unfinished work for resuming

Review an existing GitHub PR with full codebase context — fetches the PR and drives code-review against its merge-base. Use when the user asks to review a PR (incoming, a collaborator's, or an already-pushed one).

Create a curated session summary for continuation, for another agent to pick up.

Reference for writing and editing skills well — the vocabulary and principles that make a skill predictable.

Review the changes since a fixed point (commit, branch, tag, or merge-base) along three axes — Correctness (does it break anything?), Standards (repo coding standards plus a smell baseline), and Spec (does it match what the originating task/issue asked for?). Runs the axes as parallel sub-agents and reports them side by side. Use when the user wants to review a branch, work-in-progress changes, or asks to "review since X".

Second opinion from a different model (OpenAI Codex). Use when exploring different design choices (more diversity with heterogenous models), debugging hard problems, or when the user wants a second perspective, you want second perspective, are stuck, ...

Build and sharpen a project's domain model. Use when the user wants to pin down domain terminology or a ubiquitous language, record an architectural decision, or when another skill needs to maintain the domain model.

Implement a piece of work based on a spec or set of tickets.

Scan a codebase for deepening opportunities, present them as a visual HTML report, then grill through whichever one you pick.

Whole-repo audit for over-engineering: a ranked list of what to delete, simplify, or replace with stdlib/native equivalents. Use when the user says "find bloat", "audit for over-engineering", "what can I delete from this repo", or invokes /mx:bloat-audit. One-shot report; applying the cuts is a separate, later decision.

Shared vocabulary for designing deep modules. Use when the user wants to design or improve a module's interface, find deepening opportunities, decide where a seam goes, make code more testable or AI-navigable, or when another skill needs the deep-module vocabulary.

A relentless interview to sharpen a plan or design, which also creates docs (ADRs and glossary) as we go.

Interview the user relentlessly about a plan or design until reaching shared understanding, resolving each branch of the decision tree. Use when user wants to stress-test a plan, get grilled on their design, uses the "grill" trigger phrase, or when you want to ensure an accurate, shared mental model of a plan or design.

Read for preferences on and best practices for setting up a Python project.

Test-driven development. Use when the user wants to build features or fix bugs test-first, mentions "red-green-refactor", or wants integration tests.

Must read guide on creating/editing CLIs or any Python script that accepts command-line arguments.

Update CHANGELOG.md with notable changes since the last release. Use when preparing a release, updating the changelog, or when the user asks to "update changelog", "write changelog", "prepare release notes".

Remove AI writing patterns from prose. Use when drafting, editing, or reviewing text to eliminate predictable AI tells — throat-clearing, binary contrasts, false agency, adverbs, passive voice, vague declaratives.

Must read guide on creating/editing mermaid charts with valiation tools

Generate a descriptive session name for /rename