メニュー
Portable autonomous BMALPH planning for Codex. Use when the user wants specs from a short task description and expects the current AI session to orchestrate BMALPH subagents without human interaction.
Codex または Claude でインストール この Prompt をコピーして Codex、Claude、または他のアシスタントに貼り付けると、Skill ページを確認してインストールできます。
SOC 職業分類に基づく
Systematically retrieve and address PR code review comments using make pr-comments. Use when handling code review feedback or addressing PR comments.
Codex entrypoint for post-implementation BMAD FR/NFR review gates. Use after a PR, feature, or bugfix has BMAD specs and must be checked against every functional requirement, non-functional requirement, expanded quality dimension, Wikipedia system quality attribute, generated positive/negative/ edge test case, automated test and CI coverage expectation, flaky-test risk, whole-codebase impact surface, manual-test expectation, GitHub review comments and requested-changes state, and CI check before completion.
Run a BMAD spec-driven post-implementation review gate. Use after implementing a GitHub PR, feature, bugfix, or task with BMAD specs to verify every FR/NFR, pinned NonFunctionals.com NFR category, expanded quality dimension, Wikipedia system quality attribute, positive/negative/edge test case, automated test and CI coverage expectation, flaky-test risk, whole-codebase impact surface, manual test expectation, QA best practice, GitHub review comments and requested-changes state, and CI check before completion.
Design LLM-powered modules with Clean Architecture boundaries, SOLID, DRY, KISS, and provider-agnostic ports/adapters. Use when adding prompt workflows, model/provider clients, tool orchestration, AI review automation, agent skills, or other LLM-backed capabilities.
advanced elicitation. Use when the user asks about advanced elicitation.
adversarial review. Use when the user asks about adversarial review.
| name | bmad-autonomous-planning |
| description | Portable autonomous BMALPH planning for Codex. Use when the user wants specs from a short task description and expects the current AI session to orchestrate BMALPH subagents without human interaction. |
Use this skill from the current Codex session. Do not rely on repo-local bash
wrappers, make targets, or other launcher automation for the planning flow.
The canonical planning contract lives in
.claude/skills/bmad-autonomous-planning/SKILL.md. This wrapper is only the
Codex-specific handoff.
This wrapper requires local BMALPH assets under _bmad/, which this repository intentionally keeps out of git.
If _bmad/ is missing in a fresh clone or workspace, run make bmalph-setup first.
If BMALPH is already installed and you need to restore local files or reapply this repository's planning artifacts under specs/, rerun make bmalph-setup.
After the local BMALPH assets are available:
bmalph skill wrapper, _bmad/COMMANDS.md, and the resolved
BMAD config file first..claude/skills/bmad-autonomous-planning/SKILL.md.autonomous/<timestamp>-<task-slug>/.analystcreate-briefcreate-prdcreate-architecturecreate-epics-storiesimplementation-readiness_bmad/COMMANDS.md when available.model: gpt-5.4 and
reasoning_effort: xhigh. Do not use gpt-5.4-mini for stage ownership in
this workflow.For each subagent, name the BMALPH command first and provide only the backing workflow or agent files required by that command. Do not hand off raw workflow-file paths without the command context.
Minimal Codex trigger example:
Use the bmad-autonomous-planning skill to plan a new user-profile enrichment feature for the user service. Follow the repository's BMALPH autonomous planning skill, work in the current session, keep the flow fully autonomous, and run each planning subagent on gpt-5.4 with xhigh reasoning.
The finished bundle should include:
research.mdproduct-brief.mdproduct-brief-distillate.md when usefulprd.mdarchitecture.mdepics.mdimplementation-readiness.mdrun-summary.mdOptional GitHub issue or specs-only PR work happens only after the planning bundle is complete and only when the user explicitly asks for it.