claude

atm-bd-orchestration

Bead-driven phase orchestration for ATM agent teams: atm-beads, atm-bd-orchestration and sprint-report skills plus the dev-sanity agents they name.

0 on GitHubby randleev0.19.18MITupdated yesterdayworkflow
/

Plugin atm-bd-orchestration from marketplace atm-bd-orchestration in randlee/atm-bd-orchestration. Commands read from the repo's manifest — yesterday.

What it installs

Skills (8)

  • atm-bd-lite

    Lightweight ATM Beads profile with task hooks and QA, without a sanity stage.

  • atm-bd-orchestration

    Bead-driven phase orchestration for the lead. Use when running a phase whose plan is in beads, dispatching from `bd ready` with ATM tasks, and landing it as one gh stack.

  • atm-beads

    Plans written as beads. Use when writing, validating or importing a phase plan into beads, or when pairing an ATM task with its bead (claim, start, close).

  • plan-hardening

    Harden a phase plan in beads before implementation: scope review, critical review and ceremony review, each followed by a planner fix pass, then the plan gate. Use when a phase plan file exists and needs hardening, or when the user asks for /plan-hardening. Runs as a planner with subagents, a planne

  • prompt-rewrite-judge

    Rewrite prompt text for conciseness and clarity with fresh subagents, then have Jev judge each rewrite for dropped, changed or unclear requirements. Use when tightening a prompt, template step or skill rule without losing any requirement.

  • qa-report

    Show the two QA metrics logs (per-round event log and cumulative phase-stats) from .sc/qa-log/.

  • sprint-report

    Generate a sprint status table or dependency DAG from live beads. The DAG HTML is written locally; --view optionally opens Wyvern.

  • sprint-review

    Refresh the phase dependency diagram and write its HTML locally. Optionally view it in Wyvern with --view.

Subagents (10)

  • ceremony-finding-screen

    Screens a QA or plan-review round's findings and flags those whose remedy is an unjustified process artifact, before triage routes them to a developer.

  • ceremony-qa

    Reviews phase and sprint plan docs for process porn and ceremony that does not serve shippable capability; recommends removals only.

  • critical-plan-reviewer

    Performs a hostile late-stage review of hardened plans for architecture mistakes, weak boundaries, false closure, and cross-document ambiguity.

  • dev-sanity

    Check pinned deliverables, reconcile independent reviewers, close, then hand off stacking.

  • flaky-test-qa

    Audits repository tests for flakiness, race conditions, timing dependencies, and nondeterministic behavior through a fenced-JSON contract.

  • parallax

    The work-orchestrator teammate. Runs the lead's routine orchestration of a bead-driven phase so the lead keeps bv, monitoring and rulings; sends the lead only summaries and escalations.

  • plan-scope-reviewer

    Reviews sprint shape, boundary-scoped closure, parallel width, deliverable ownership, early split decisions, and direct sprint-doc consumability before hardening fixes.

  • sanity-stack

    Link one sanity-approved next-top layer under the stack bead lock.

  • sc-sanity-jev

    Jev-assisted dev sanity check of one numbered deliverable at an exact commit; reports whether it is done as JSON. Read-only, no lint, not QA.

  • sc-sanity-llm

    LLM dev sanity check of one numbered deliverable of one closed dev or fix bead at an exact commit; reports whether it is done as JSON. Read-only, no lint, not QA.

View source on GitHub

More from randlee/atm-bd-orchestration

All 2 plugins →

One-label triage from GitHub issues onto beads.

1 skill · 20 agents

0

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

superset

claude

Use Superset to spawn agents, create workspaces, manage tasks, and schedule automations from Claude Code.

14 skills · 1 command

superset-sh/superset 15,548

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

Maintain atm-bd-orchestration?

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 plugins2 plugins