claude

momentum

Agentic engineering practice — rules, agents, quality gates, and workflow automation across projects

0 on GitHubby Steve Holmesv0.35.1Apache-2.0updated 5 days agodevelopment
/

Plugin momentum from marketplace momentum in iamsteveholmes/momentum. Commands read from the repo's manifest — 4 days ago.

This plugin runs code on your machine — its hooks fire automatically on events like tool use. The exact commands are listed below; read them before installing.

What it installs

Skills (38)

  • agent-builder

    Tier 2 agent composer: base body + constitution + manifesto → composed agent + routing entry in momentum/agents.json. Invoked by sprint-dev for change_type:agent stories. Also user-invocable.

  • agent-guidelines

    Discovers project stack, researches breaking changes, consults on recommendations, generates path-scoped rules and reference docs.

  • build-scanner

    Scans project build files to detect technology stack, versions, and dependencies.

  • rules-auditor

    Audits existing .claude/rules/ and CLAUDE.md for current technology guideline coverage.

  • source-pattern-scanner

    Analyzes source code patterns to identify languages, frameworks, and conventions.

  • test-config-scanner

    Detects testing frameworks, configuration, and test patterns in the project.

  • architecture-guard

    Detects pattern drift against architecture decisions. Read-only enforcer. Invoked by Impetus — do not invoke directly.

  • assessment

    Guided product state evaluation. Spawns parallel discovery agents, validates findings with the developer, and produces a structured ASR document.

  • avfl

    Adversarial Validate-Fix Loop — multi-agent validation catching errors, hallucinations, and quality issues via parallel lenses and iterative fix.

  • consolidator

    AVFL consolidator. Merges, cross-checks, deduplicates, and scores validator findings.

  • fixer

    AVFL fixer. Applies validated findings as corrections and produces a complete fixed artifact.

  • avfl-merge-review

    AVFL merge-review sub-skill — invoked by the avfl-merge-review Workflow. Do not invoke directly.

  • validator-adv

    AVFL Adversary validator. Intuitive, holistic, pattern-aware quality validation.

  • validator-enum

    AVFL Enumerator validator. Systematic, section-by-section quality validation.

  • build-guidelines

    Builds gen-2 composed specialist agent files (base body + manifesto) and Tier 1 constitution. Run before sprint to bake guidelines in.

  • canvas

    Launch the Momentum Cycle live dashboard (Hono+Bun, port 3456). Checks if running, starts if not; opens http://localhost:3456 in the viewer pane.

  • code-reviewer

    Non-interactive bmad-code-review adapter for conduct. Accepts a single story diff, drives adversarial bug-hunt in report-only mode, normalizes surviving findings to the canonical schema with stakes_class populated, and returns the finding stream to the Conductor. Invoked by the Conductor — do not in

  • conductor

    In-session sprint build orchestrator — per-story pipelines, AVFL-on-merge, E2E, single end-gate. No story-count cap.

  • constitution-builder

    Builds Tier 1 domain-knowledge constitution for KB-backed agents. Accepts write_mode: in_place_skill | composed_agent_file | standalone_constitution.

  • create-story

    Creates a new Momentum story (from an epic) or enriches an existing slug-stub in place — change-type classification, injected EDD/TDD guidance, AVFL validation. Use when creating or fleshing out a Momentum story.

  • decision

    Capture strategic decisions from assessments or research. Walk findings, record adopt/reject/defer, write a linked SDR document.

  • dev

    Pure implementer — resolves a story, delegates to bmad-dev-story, emits an implementation-complete + file_list signal. Spawned by the Conductor (worktree, merge, and cleanup are the Conductor's). Not user-invocable.

  • epic-breakdown

    Enumerating missing stories for an epic end to end. Use when the developer wants to enumerate stories needed to ship an epic.

  • epic-grooming

    Epic grooming — unified epic taxonomy, value analysis, orphan resolution, and epics.json maintenance.

  • feature-status

    Deprecated. Use /momentum:canvas instead. This stub outputs a deprecation message and halts.

  • impetus

    Impetus — Momentum practice orchestrator. Session orientation, sprint intelligence, and workflow dispatch. Use when developer invokes /momentum.

  • intake

    Capture a story idea from conversation into the backlog as a stub — fast context preservation without the full create-story pipeline.

  • manifesto-builder

    Drafts an agent's diagnostic-table manifesto from the project KB, then requires human curation of symptom wording before writing it to disk.

  • plan-audit

    Audits the active plan for spec impact, classifies trivial vs. substantive, and writes a Spec Impact section before plan mode exits.

  • quick-fix

    Single-story fix -- define, specify, implement, validate, and merge in one streamlined flow.

  • refine

    Backlog hygiene — planning artifact drift detection, status mismatches, stale-story triage, and batch approval.

  • research

    Deep research pipeline with parallel subagents, Gemini CLI triangulation, AVFL corpus validation, and provenance tracking.

  • retro

    Sprint retrospective — transcript audit engine (dynamic Workflow), story verification, findings document, and sprint closure.

  • sprint-dev

    Sprint execution — dependency-driven story development, post-merge AVFL, and team review.

  • sprint-manager

    Sole writer of stories/index.json and sprints/index.json — validates state transitions, activates sprints, manages epic membership.

  • sprint-planning

    Sprint planning — story selection, team composition, Gherkin specs, and visual companion plan gate for developer sign-off.

  • triage

    Dedup gate + batch-classify observations into five classes, enrich ARTIFACTs, batch-approve, delegate to intake/decision or queue.

  • upstream-fix

    Traces quality failures upstream to spec, rule, or workflow root cause. Proposes fixes at the right level.

Slash commands (18)

  • /momentum:agent-guidelines
  • /momentum:architecture-guard
  • /momentum:avfl
  • /momentum:code-reviewer
  • /momentum:conduct
  • /momentum:create-story
  • /momentum:dev
  • /momentum:epic-breakdown
  • /momentum:epic-grooming
  • /momentum:feature-status
  • /momentum:impetus
  • /momentum:plan-audit
  • /momentum:quick-fix
  • /momentum:research
  • /momentum:sprint-dev
  • /momentum:sprint-manager
  • /momentum:sprint-planning
  • /momentum:upstream-fix

Subagents (6)

  • analyst

    Universal analyst base body. Owns assessment records, analysis docs, and requirements analysis. Composed with project-specific context by agent-composition-pipeline.

  • dev

    Implements a single story per its spec. Pure implementer spawned by the Conductor — delegates implementation to bmad-dev-story and returns implementation-complete output with files changed.

  • e2e-validator

    Behavioral validator for Momentum Team Review. Reads verification-harness.json and assembled-surface routing (change_type as inference fallback) to execute the correct verification method per story. Replaces Gherkin-only validation with method-polymorphic contracts. Spawned during Team Review phase.

  • qa-reviewer

    Per-story QA verifier spawned during stage 2 of the conduct build phase. Routes on the story's frozen verification contract (verification_method, harness_profile) and EXECUTES it — invoking, triggering, running, driving, or (document-review only) inspecting — never degrading to diff-only review. Cla

  • researcher

    Universal researcher base body. Owns research docs, synthesis briefings, and investigation reports. Unconditioned — agent-composition-pipeline layers project context on top. Spawned by orchestrators for research and knowledge-investigation tasks.

  • ux

    UX designer base body — owns UX specs, wireframes, design docs, and UX requirements. Spawned by orchestrators for UX-related document creation and review work.

Hooks (3)

  • PostToolUse

    bash -c 'LOCAL="$CLAUDE_PROJECT_DIR/.claude/momentum/hooks/lint-format.sh"; GLOBAL="$HOME/.claude/momentum/hooks/lint-format.sh"; if [ -f "$LOCAL" ]; then exec bash "$LOCAL" "$CLAUDE_TOOL_INPUT_FILE_P

  • PreToolUse

    bash -c 'LOCAL="$CLAUDE_PROJECT_DIR/.claude/momentum/hooks/file-protection.sh"; GLOBAL="$HOME/.claude/momentum/hooks/file-protection.sh"; if [ -f "$LOCAL" ]; then exec bash "$LOCAL"; elif [ -f "$GLOBA

  • Stop

    bash -c 'LOCAL="$CLAUDE_PROJECT_DIR/.claude/momentum/hooks/stop-gate.sh"; GLOBAL="$HOME/.claude/momentum/hooks/stop-gate.sh"; if [ -f "$LOCAL" ]; then exec bash "$LOCAL"; elif [ -f "$GLOBAL" ]; then e

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

context7

claudecodex

Up-to-date documentation lookup. Pull version-specific documentation and code examples directly from source repositories into your coding agent's context.

1 MCP server

upstash/context7 64,709

Build powerful, stateful CLI interfaces for any GUI application using the cli-anything harness methodology.

5 commands

HKUDS/CLI-Anything 58,665

Automates browser interactions for web testing, form filling, screenshots, and data extraction

12 skills

vercel-labs/agent-browser 50,373

Use Alibaba Open Code Review from local Codex.

2 skills

alibaba/open-code-review 50,068

slidev

claude

Claude Code skill for creating and presenting Slidev slidedecks

1 skill

slidevjs/slidev 49,452

Maintain momentum?

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