claude

bmad-pipeline

BMAD story-delivery pipeline: the run-dev-cycle orchestrator skill that drives BMAD's bmad-build loop story by story and answers its human checkpoints, the three bmad-* agents it uses, the Telegram ask/notify scripts for unattended runs, and a setup-telegram skill to configure them safely.

0 on GitHubby Panit Wechasilv3.1.0updated 2 months agoworkflow
/

Plugin bmad-pipeline from marketplace bmad-pipeline in panitw/engineering-skills. Commands read from the repo's manifest — 1 month ago.

What it installs

Skills (2)

  • run-dev-cycle

    Orchestrate delivery of specified epic(s) or user story(s) through BMAD — one story at a time, driving BMAD''s own bmad-build loop per story and supplying the human side of its checkpoints: an engineering lead that rules on Open Questions, owner escalation, a decision log, a heavy-test cadence and a

  • setup-telegram

    Set up a Telegram bot so Claude Code can send notifications and ask the owner questions during unattended runs. Walks the user through @BotFather, then has them write ~/.claude/telegram.env themselves at a silent prompt — the bot token is never pasted into the chat and Claude never sees it. Use when

Subagents (3)

  • bmad-engineering-lead

    Use this agent as the technical decision authority for the BMAD pipeline — the engineering lead who holds the project's direction and rules on the decisions BMAD's build loop refuses to guess at, keeping implementation in line with the architecture, ADRs, and epics. It also holds the story's scope f

  • bmad-story-builder

    Use this agent to carry one BMAD story through the `bmad-build` skill end to end — plan, implement, review, triage, local commit — pausing at each of the workflow's human checkpoints and asking the orchestrator instead of guessing. Launch it as a background agent and record its agentId: it is resume

  • bmad-story-closer

    Use this agent to close out a BMAD story and leave the BMAD output tree tidy. The build loop already implemented, reviewed and committed the code — this agent owns the record and the housekeeping: it strips agent-written narrative out of sprint-status.yaml back to status values, files or removes the

View source on GitHub

Similar plugins

superpowers

claudecodex

Core skills library for Claude Code: TDD, debugging, collaboration patterns, and proven techniques

15 skills · hooks

obra/superpowers 316,836

Backend API design, GraphQL architecture, workflow orchestration with Temporal, and test-driven backend development

9 skills · 1 command · 8 agents

wshobson/agents 42,461

beads

claudecodex

AI-supervised issue tracker for coding workflows

1 skill · 1 agent · hooks

gastownhall/beads 28,698

MiniMax AI skills library for frontend, fullstack, Android, iOS, shader, GIF sticker, document, presentation, spreadsheet, and multimodal media workflows

18 skills

MiniMax-AI/skills 13,828

worktrunk

claudecodex

Worktrunk is a CLI for Git worktree management, designed for parallel AI agent workflows. This plugin provides configuration guidance (LLM commit messages, project hooks, worktree paths), automatic activity tracking (🤖/💬 indicators in `wt list` showing active Claude sessions), and a `/wt-diff` pane showing each worktree's changes.

2 skills · hooks

max-sixty/worktrunk 12,481

gsd-core

claude

GSD Core is a meta-prompting, context engineering, and spec-driven development system for AI coding agents.

72 skills · 72 commands · 64 agents · hooks

open-gsd/gsd-core 11,494

Maintain bmad-pipeline?

This page updates itself from your repo. Add the badge to your README, or get it Featured to pin it above the organic results with a followed link to your site.

claude & codex pluginslisted