Files
bmad-autonomous-development/skills/bad/assets/module.yaml
stephenleo 303af472f9 feat: initial release of BAD — BMad Autonomous Development v1.0.0
Standalone BMad module that orchestrates fully autonomous parallel
multi-agent pipelines through the full story lifecycle (create → dev →
review → PR), driven by the sprint backlog and dependency graph.

- Every step runs in a dedicated subagent with a fresh context window
- Harness-agnostic: detects Claude Code, Cursor, Copilot, etc. at setup
- Configurable models, timers, CI, and merge behaviour per harness
- Self-registering via assets/module-setup.md

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
2026-04-05 12:49:27 +08:00

42 lines
1.5 KiB
YAML

code: bad
name: "BMad Autonomous Development"
description: "Orchestrates parallel BMad story implementation pipelines — automatically runs bmad-create-story, bmad-dev-story, bmad-code-review, and commit/PR in batches, driven by the sprint backlog and dependency graph"
module_version: "1.0.0"
module_greeting: "BAD is ready. Run /bad to start. Pass KEY=VALUE args to override config at runtime (e.g. /bad MAX_PARALLEL_STORIES=2)."
header: "BAD — BMad Autonomous Development"
subheader: "Configure the autonomous development pipeline for this project.\nHarness-specific settings (models, rate limit thresholds, timer support) are detected automatically from your installed harnesses."
max_parallel_stories:
prompt: "Max stories to run in a single batch"
default: "3"
result: "{value}"
worktree_base_path:
prompt: "Root directory for git worktrees (relative to repo root)"
default: ".worktrees"
result: "{value}"
auto_pr_merge:
prompt: "Auto-merge batch PRs sequentially after each batch?"
default: false
run_ci_locally:
prompt: "Skip GitHub Actions and run CI locally by default?"
default: false
wait_timer_seconds:
prompt: "Seconds to wait between batches before re-checking PR status"
default: "3600"
result: "{value}"
retro_timer_seconds:
prompt: "Seconds before auto-running retrospective after epic completion"
default: "600"
result: "{value}"
context_compaction_threshold:
prompt: "Context window % at which to compact/summarise context"
default: "80"
result: "{value}"