claude

bmad-evals

BMAD methodology with cross-context persistence harness. Run stories across context windows with /brun, cancel with /bstop. Includes eval framework for testing AI agent performance.

0 on GitHubby Innocraft Systemsv2.0.0MITupdated 9 months agodevelopment
/

Plugin bmad-evals from marketplace innocraft-marketplace in innocraft-systems/innocraft-plugin. Commands read from the repo's manifest — 1 month ago.

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

What it installs

Slash commands (10)

  • /bmad-evals:brun

    Run BMAD story with cross-context persistence

  • /bmad-evals:bstop

    Stop BMAD story harness

  • /bmad-evals:eval-cancel

    Cancel active BMAD-Evals loop

  • /bmad-evals:eval-help

    BMAD-Evals plugin help and documentation

  • /bmad-evals:eval-init

    Initialize BMAD-Evals suite from BMAD stories or scratch

  • /bmad-evals:eval-report

    Generate comprehensive eval report with metrics

  • /bmad-evals:eval-run

    Run BMAD-Evals loop with grading and iteration tracking

  • /bmad-evals:eval-task-add

    Add a new eval task with graders

  • /bmad-evals:sprint-run

    Run all stories in sprint automatically with cross-context persistence

  • /bmad-evals:sprint-stop

    Stop the active sprint runner

Subagents (3)

  • eval-analyst

    Analyzes eval results and provides insights for improvement

  • eval-grader

    LLM-based grader subagent for evaluating agent outputs against rubrics

  • eval-orchestrator

    Orchestrates multi-task eval suites and manages evaluation flow

MCP servers (1)

  • serena

    runs: uvx --from git+https://github.com/oraios/serena serena start-mcp-server --project-root ${workspaceFolder}

Hooks (4)

  • Stop

    ${CLAUDE_PLUGIN_ROOT}/hooks/sprint-runner-hook.sh

  • Stop

    ${CLAUDE_PLUGIN_ROOT}/hooks/bmad-story-hook.sh

  • Stop

    ${CLAUDE_PLUGIN_ROOT}/hooks/eval-stop-hook.sh

  • PostToolUse

    ${CLAUDE_PLUGIN_ROOT}/hooks/transcript-capture.sh

View source on GitHub

More from innocraft-systems/innocraft-plugin

All 10 plugins →

neon

claude

Complete Neon serverless PostgreSQL integration - Drizzle ORM, serverless driver, ephemeral databases, Neon Auth, unified SDK, MCP server, and vector/RAG with hybrid search

7 skills · 11 commands · 4 agents · 1 MCP server

0

kenya-payments

claude

Complete Kenya payments integration - Kopokopo (K2 Connect), Safaricom Daraja (M-Pesa), Pesapal API 3.0, and Intasend. STK Push, B2C, C2B, webhooks, bank payouts.

4 skills · 4 commands · 1 agent

0

convex

claude

Complete Convex backend development - functions (queries, mutations, actions), database (schema, indexes), Convex Auth, file storage, scheduling, and real-time reactive backends

1 skill · 6 commands · 1 agent

0

design-system

claude

Premium design system enforcement with Firecrawl inspiration capture. Extract design tokens from sites, align components to design system, generate CSS/Tailwind configs. Anti-AI-slop patterns.

6 commands · 2 agents

0

kra-etims

claude

KRA eTIMS (Electronic Tax Invoice Management System) integration for Kenya tax compliance. OSCU/VSCU integration, invoice submission, stock management, item classification.

3 skills · 1 command · 1 agent

0

meta-business

claude

Meta Business Suite integration - Facebook Pages and Instagram Business posting, scheduling, analytics. Post photos, videos, carousels, reels, and track engagement.

3 skills · 1 command · 1 agent

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

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

cli-anything

claude

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

5 commands

HKUDS/CLI-Anything 58,665

agent-browser

claude

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

12 skills

vercel-labs/agent-browser 50,373

Open Code Review

codex

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 bmad-evals?

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 plugins10 plugins