ansonphong/meta-dev - Seite 2

meta-overlord

Run meta-overlord in Codex. Trigger: meta-overlord.

Quellsprache: Englisch

meta-planner

Run meta-planner in Codex. Trigger: meta-planner.

Quellsprache: Englisch

meta-probe

Run meta-probe in Codex. Trigger: meta-probe.

Quellsprache: Englisch

meta-repair

Run meta-repair in Codex. Trigger: meta-repair.

Quellsprache: Englisch

meta-review-batch

Run meta-review-batch in Codex. Trigger: meta-review-batch.

Quellsprache: Englisch

meta-review-design

Run meta-review-design in Codex. Trigger: meta-review-design.

Quellsprache: Englisch

meta-security

Run meta-security in Codex. Trigger: meta-security.

Quellsprache: Englisch

meta-sweep

Run meta-sweep in Codex. Trigger: meta-sweep.

Quellsprache: Englisch

meta-ux

Run meta-ux in Codex. Trigger: meta-ux.

Quellsprache: Englisch

meta-version

Run meta-version in Codex. Trigger: meta-version.

Quellsprache: Englisch

meta-visual-critique

Run meta-visual-critique in Codex. Trigger: meta-visual-critique.

Quellsprache: Englisch

opus-execute

Run opus-execute in Codex. Trigger: opus-execute.

Quellsprache: Englisch

plan

Write and save a self-contained implementation plan for a fresh agent. Use for plan requests, medium changes, or implementation planning before code.

Quellsprache: Englisch

runbook

Coordinate related plans through a campaign runbook.

Quellsprache: Englisch

sonnet-execute

Run sonnet-execute in Codex. Trigger: sonnet-execute.

Quellsprache: Englisch

diagnose

Diagnose a focused failure and preserve evidence.

Quellsprache: Englisch

harden

Stress-test a plan before execution.

Quellsprache: Englisch

review

Review a scoped change through the shared protocol.

Quellsprache: Englisch

changelog-engine

Batch engineering changelog. Append entries during work, cut on demand or auto-threshold, draft release post, pair with version bump.

Quellsprache: Englisch

design-eval

Design quality rubric scoring — evaluates implementation against design doc on 4 dimensions

Quellsprache: Englisch

dod-contract

Generate definition-of-done contracts from task descriptions. Output structured acceptance criteria, test plan, rollback strategy, and blast radius.

Quellsprache: Englisch

headless-worker

Patterns for headless Claude execution via claude -p --output-format json. Tool allowlist tiers, env inheritance, model override for Sonnet routing.

Quellsprache: Englisch

plan-validation

Judgment-based plan quality checks — cross-reference integrity, dependency ordering, contract completeness, terminology consistency

Quellsprache: Englisch

repair-loop

Attempt auto-fix with 3-attempt cap, smallest-fix-first strategy, failure dossier to inbox. Use when verify step fails.

Quellsprache: Englisch

sniff-test

Grug-brain sniff test for plans AND code — detect over-engineering, complexity demons, vague tasks, and bad practices in plans/specs (primary) or code (secondary). Report-only, never edits. Invoked as /sniff-test. By default sniffs the subject under…

Quellsprache: Englisch

version-manager

Multi-repo, context-aware versioning. Declarative config, semver/calver/custom strategies, follows cascades, atomic version_files updates.

Quellsprache: Englisch

waterfall-tracking

Stand up and maintain a visible stage-level task list for the /meta-dev 6-stage waterfall. Use in autopilot/walk runs so the user can walk away and watch Brainstorm→Design→Plan→Harden→Execute→Review progress live. Stage granularity only — never mirrors…

Quellsprache: Englisch