Search everything...

Stats

Actions

Available In

Help us improve

Share bugs, ideas, or general feedback.

jm-adk - Claude Code Plugin | ClaudePluginHub

Plugin

jm-adk

Name: jm-adk
Author: javimontano

By JaviMontano

JM Agentic Development Kit — 611 skills (incl. the 30 Claude Certified Architect katas and the Jarvis OS capability pack), 261 agents, 267 commands, safe first-use onboarding, skill scaffolding, local-first workspaces, validation gates, and upgrade-safe GitHub sync.

npx claudepluginhub javimontano/jm-adk-alfa

Popularity

Stars

Above avg

Med: 0·Avg: 264

Installs

Med: 0·Avg: 1

What's Inside

Slash Commands267

/jm-adk:requirements

/requirements

Extract requirements from conversation/documents

/jm-adk:roadmap

/roadmap

Generate prioritized product roadmap

/jm-adk:rollback-strategy

/rollback-strategy

Blue-green, canary, feature flags, database rollback patterns.

/jm-adk:rollback

/rollback

Rollback to previous deployment

/jm-adk:sales-collateral

/sales-collateral

One-pagers, battle cards, ROI calculators, competitive positioning documents.

Agents261

a11y-implementer

/a11y-implementer

WCAG implementation, screen reader testing, ARIA patterns

ab-testing-specialist

/ab-testing-specialist

Hypothesis formulation, statistical significance, sample size calculation, test duration.

accessibility-auditor

/accessibility-auditor

WCAG 2.1 auditing, axe-core, screen reader testing

accessibility-designer

/accessibility-designer

Designs WCAG 2.1 AA compliant patterns including ARIA roles, keyboard navigation, and screen reader support.

accessibility-writing-specialist

/accessibility-writing-specialist

Alt text guidelines, plain language, reading level, inclusive language.

Skills611

ab-testing

/ab-testing

Designs and reviews A/B tests with explicit hypothesis, primary metric, guardrail metrics, variants, sample-size assumptions, duration, stopping rules, instrumentation checks, and decision criteria. [EXPLICIT] Trigger: "ab testing, a/b test, experiment design, split test, hypothesis formulation, statistical significance, sample size calculation, test duration"

accessibility-audit

/accessibility-audit

WCAG 2.1 AA automated scanning with axe-core plus manual checklist for keyboard, screen reader, and contrast

accessibility-design

/accessibility-design

Designs and implements WCAG 2.1 AA accessibility patterns for web applications using native HTML first, targeted ARIA only when needed, keyboard interaction maps, focus management, screen reader semantics, contrast tokens, accessible forms, reduced motion, and inclusive interaction requirements. [EXPLICIT] Trigger: "accessibility", "WCAG", "ARIA", "a11y", "screen reader", "inclusive design"

accessibility-testing

/accessibility-testing

Plan, execute, and report web accessibility tests with axe-core, Playwright/Jest evidence, keyboard scripts, screen reader smoke checks, color contrast validation, and explicit WCAG target scope. [EXPLICIT] Trigger: "accessibility test", "a11y test", "WCAG test", "screen reader", "axe-core", "keyboard accessibility"

accessibility-writing

/accessibility-writing

Rewrite and review content so it is accessible, understandable, inclusive, and safe to publish: alt text, plain language, reading-level estimates, descriptive links, helpful errors, non-sensory instructions, localization, and evidence-backed limits. [EXPLICIT] Trigger: "accessibility writing", "accessible copy", "alt text", "plain language", "inclusive language", "reading level", "descriptive links"

MCP Servers1

workspace-mcp

2 secrets

Google Workspace unified: Gmail, Calendar, Drive, Docs, Sheets, Slides, Forms, Tasks, Contacts (90+ tools)

Stats

Version5.2.0

LanguagePython

Stars2

MaintenanceExcellent

LicenseMIT

Last CommitJun 11, 2026

AddedMar 31, 2026

Actions

View on GitHub View README Plugin Marketplace JSON Homepage

Own this plugin?

Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).

Safety Signals

Caution

Requires secrets

Needs API keys or credentials to function

Uses power tools

Uses Bash, Write, or Edit tools

Help us improve

Share bugs, ideas, or general feedback.

README

JM Agentic Development Kit Alfa

Version: 5.2.0 License: MIT Repository: https://github.com/JaviMontano/jm-adk-alfa

JM-ADK is a local-first agentic development kit for AI-assisted software work. It packages skills, agents, commands, prompts, workspace governance, guardrails, and validation scripts so a developer can scaffold, run, review, and update agentic workflows without mixing versioned kit files with local state.

Component Inventory

The authoritative counts come from python3 scripts/count-components.py.

Component	Count
Skills	601
Agents	261
Commands	267
Prompts	256
Total physical components	1368

Claude Certified Architect Katas

JM-ADK ships the 30 Claude Certified Architect katas as first-class, executable katas-* skills (one per kata) across the 5 exam domains:

Domain	Weight	Katas
D1 · Agentic Architecture	27%	deterministic-agent-loop, pretooluse-guardrails, posttooluse-normalization, hub-and-spoke-isolation, headless-code-review, human-handoff-protocol, adaptive-investigation, multiagent-error-propagation
D2 · Tool Design & MCP	18%	defensive-structured-extraction, mcp-structured-errors, tool-description-quality, mcp-server-configuration, builtin-tool-selection
D3 · Claude Code Config	20%	plan-mode-exploration, hierarchical-claude-memory, path-conditional-rules, custom-commands-skills, session-resume-fork
D4 · Prompt & Structured Output	20%	fewshot-edge-calibration, critical-self-correction, message-batch-processing, validation-retry-feedback, independent-reviewer-multipass, confidence-stratified-sampling, false-positive-criteria
D5 · Context & Reliability	15%	prefix-caching, context-dilution-mitigation, multipass-prompt-chaining, persistent-scratchpad, provenance-preservation

The katas are backed by systemic reliability infrastructure: a policy-driven PreToolUse guard (references/guardrails/tool-policy.json), reliability references (references/reliability/), a structured-annotation schema + headless CI workflow (.github/workflows/validate.yml), a Message Batches runner (scripts/batch/), and QA suites (scripts/qa/). Source inventories live in docs/katas/.

Install

git clone https://github.com/JaviMontano/jm-adk-alfa.git
cd jm-adk-alfa
python3 scripts/count-components.py
python3 scripts/validate-skills.py --strict

After Clone / First Use

Before the first task, diagnose local readiness:

python3 scripts/diagnose-first-use.py --dry-run

If the first user input is only hola, buenas, hey, hello, or empecemos, Alfa should start /jm-adk:first-use instead of beginning technical work. The guided setup asks for goal, project type, stack, preferred runtime, autonomy level, command policy, privacy constraints, workspace area, and output format.

Create local profile state only after review:

python3 scripts/setup-workspace-profile.py --dry-run
python3 scripts/setup-workspace-profile.py --apply

Declare which runtimes you will drive the kit from (validated against the known set: claude-code, claude-desktop, claude-cowork, codex, gemini-cli, antigravity, cursor, windsurf, vscode-copilot):

python3 scripts/setup-workspace-profile.py \
  --runtime claude-code \
  --runtime-targets claude-code,claude-desktop,codex,antigravity \
  --apply

The profile lives in .jm-adk.local.json (schema 2, with preferredRuntime + runtimeTargets) and must remain untracked.

Tool Access (MCP)

The kit ships one MCP server, workspace-mcp (Gmail + Google Workspace, OAuth2). It runs on every supported runtime; the config file and snippet differ per runtime.

python3 scripts/generate-mcp-configs.py --apply   # write references/mcp/*.example
python3 scripts/validate-mcp-config.py            # check wiring is coherent + secret-free

Per-tool × per-runtime wiring (Claude Code, Claude Desktop, Codex, Gemini CLI, Antigravity, Cursor, Windsurf, VS Code): docs/runtime-tool-access-matrix.md. OAuth setup: docs/google-workspace-mcp-setup.md.

User Context Repo

Alfa includes an in-kit context repo at user-context/. It is identified by user-context/.jm-adk-context.json, so it remains recognizable as the user context area regardless of what files the user later adds there.

Use it for durable user background, preferences, memory, curated resources/, and personal-skills/ that should survive across workspaces. It is separate from workspace/, which is task runtime state.

python3 scripts/diagnose-user-context.py --dry-run
python3 scripts/diagnose-personal-skills.py --dry-run
python3 scripts/scaffold-user-context.py --dry-run

Personal context content is ignored by git by default. Only the scaffold, marker, schemas, and docs are tracked.

Local State

Versioned kit files live in the repo. Local runtime state does not.

Tracked:

View full README on GitHub

Similar Plugins

jaan-to

11·

Give soul to your workflow. 58 AI-powered skills across 17 roles — PM, Dev, Backend, Frontend, QA, UX, Data, Detect, WordPress, Release, Security, DevOps, and Core. Spec-to-ship pipeline: scaffold, implement, test, secure, deploy. Features two-phase workflow with human approval, quality-reviewer agent, token optimization, and continuous improvement via LEARN.md system.

v7.7.1

parhumm

dev-team-kit-fv

20·1·

50 specialist skills + 43 slash commands for coding agents — orchestrator, backend, frontend, QA, security, deploy, detective-spec, static-analysis, skill-author, program-router, parallel-dispatcher, blog-publisher, blog-screenshot, canary-deployment, zoom-out, handoff-context, post-deploy-canary-monitor, pattern-conformity, research-prep, context-budget, direct-response-copy, ux-research + spec-driven development, anti-AI writing, memory consolidation, executable YAML pipelines + insights dashboard (v2.18.0, 6 tabs). v2.37.0: absorcao de 7 ebooks Casa do Codigo — skill 50 ux-research (gap real: discovery qualitativo — entrevista, persona baseada em pesquisa, journey map, teste de usabilidade, arquitetura de informacao; antecede PO 01 e UI/UX 02) + 3 policies de XP (pair-programming, continuous-integration, sustainable-pace, ligadas a skill 37) + incrementos cirurgicos: skill 01 ganha Fundamento de Negocio (validacao de hipotese, MVP, monetizacao, AARRR, product-market fit — do Guia da Startup); skill 14 ganha Keyword Research (KEI, intent, cauda longa) + Off-Page/Link Building (do SEO Pratico); skill 07 ganha Infrastructure as Code (provisionamento declarativo, idempotencia, drift — principios do DevOps na pratica traduzidos pra Terraform/Ansible); skill 38 ganha lentes de coesao/acoplamento, seam distribuido (REST/async/RPC, HATEOAS) e camadas (da Introducao a Arquitetura). Livros de Jogos HTML5 Canvas (nicho <2%) descartados por frequencia. v2.36.0: skill 50 direct-response-copy — copy de direct response destilada de 3 ebooks classicos PT-BR: biblioteca de formulas de headline em 20 categorias de gatilho (357 modelos destilados em formulas parametrizadas), 8 gatilhos mentais + storytelling de venda, copy de Instagram (legenda/engajamento). Gate de integridade obrigatorio: sem claim nao-verificavel, sem depoimento fabricado, escassez so real. Complementa a skill 13 (copy de produto): 13 cobre landing/microcopy/brand voice, 50 cobre ads/pagina de vendas/email/social. v2.35.0: auto-skillify (absorcao parcial do activeloopai/hivemind) — hook UserPromptSubmit que a cada N turnos (default 20) injeta checkpoint perguntando se a atividade recente vale virar learned-skill (3 criterios: nao-googleavel, especifico do codebase, custou debugging). Adapta o skillify-via-Haiku do hivemind ao runtime: delega a decisao ao agente da sessao (ja pago) em vez de forkar LLM. Le a contagem do context-turn-counter. O resto do hivemind ja tinhamos: codebase graph=Graphify, semantic search=.index/vault.db, memory compound=memory-curator. v2.34.0: vault de memoria UNIFICADO ao kit — instalar o kit agora CRIA o vault automaticamente (scripts/init-vault.mjs roda no install.sh: cria estrutura logs/architecture/secrets, CLAUDE.md com as regras de escrita, .gitignore protegendo secrets/, git init). Path PORTAVEL via scripts/vault-resolver.mjs: $CLAUDE_MEMORY_VAULT → ~/.claude-memory (novo padrao, vale Windows/Mac/Linux) → D:/claude-memory (legado). Antes o vault era montado a mao e o path hardcoded; agora kit+memoria sao uma coisa so. Idempotente (nao sobrescreve vault existente). v2.33.0: absorcao obsidian-second-brain (memoria AI-first) — policy memory-write-rules.md aplica anti-fabricacao ao VAULT (false-absence: busque exaustivamente antes de afirmar que nao existe nota/decisao — o failure mode mais comum; no-fabrication: TBD para desconhecido; recency markers '(as of YYYY-MM, fonte)' em claims externos; niveis de confianca) + convencao 'For future Claude' (preambulo de 2-3 linhas que o futuro-Claude le em 10s pra decidir relevancia, no skill 31 session-summary) + comando /reconcile-memory (detecta contradicoes no vault — decisoes revertidas/superadas nunca atualizadas — e resolve: mais novo+autoritativo vence com secao ## History, ambiguo vira flag, evolucao marca superseded). v2.32.0: pre-build-gate (UserPromptSubmit hook) leva o 'pare e decida antes de codar' de cada disciplina (que o /auto tem nas fases) para o MODO PASSIVO — detecta intencao de criacao no prompt e injeta o checklist da disciplina certa: acceptance-criteria (defina done antes de implementar), api-contract (formato de erro + status codes antes da 1a rota), schema-integrity (constraints/FK/indices antes do 1o INSERT), ui-design (ancora estetica antes de estilizar), deploy-readiness (healthcheck/env/graceful-shutdown). 4 novas rules path-scoped por disciplina (rules/backend/, rules/database/, rules/frontend/, rules/common/acceptance-criteria.md). v2.31.0: design-aware /auto — fase UI-DESIGN como gate (PLAN→[UI-DESIGN]→BUILD) que invoca skill 02-ui-ux-design e bloqueia build de arquivo visual ate a ancora estetica estar escolhida; rules/frontend/ui-design.md (path-scoped em .css/.tsx/public) proibe o default generico (#4f46e5 indigo + system-ui), forca escolher 1 ancora; coverage config virou gate HARD no /auto; scope inference (app→fullstack) movido pra rules/common para o modo passivo herdar. Validado por bench A/B real (bench/ab/, 3 rounds) que expos UI generica nos 3 bracos. v2.29.0: claim-verifier (PostToolUse — detecta afirmacoes sem evidencia: 'email enviado', 'deploy OK', 'teste passou'; passa livre se ha exit code 0/HTTP 200/query result) + context-turn-counter (UserPromptSubmit — compact a cada 25 turnos, handoff inteligente a cada 50 usando vault de memoria). v2.28.0: /spec-kit (SDD pipeline unificado specify→plan→tasks→implement + Adversarial Verifier inline), /insights (recomendacoes baseadas em telemetria dos hooks), /swarm com Phase 3 Adversarial Verify (Implementor vs Verifier com goals opostos, spec atualizada em real-time). v2.27.0: investigate-first guard (hook PreToolUse que impede a IA de perguntar o auto-descobrivel — gh user, branch, package manager, porta, versao de runtime — manda investigar primeiro) + policy investigate-first. v2.26.0: silent-failure-hunter (16o subagent, review-only: caca catch{} vazio, swallowed errors, fallbacks perigosos, stack traces perdidos, rollback faltando) + skill 49 context-budget (audita peso de contexto carregado por componente) + /context-budget. v2.25.0: rules system path-scoped (`.claude/rules/` com `paths:` glob, inspirado no ECC), bug-fix da allowlist de subagents, 5 skills stub reescritos com profundidade. v2.24.0: curador AUTONOMO de memoria (inspirado no Hermes Agent) — roda async no SessionStart, faz decay/archive/dedup em JS puro sem gastar LLM e delega so a parte semantica ao agente presente. v2.23.0: absorcao addozhang (skill 48 research-prep, Spring Boot playbook, mem9 patterns). v2.22.0: memory curator nudge. v2.21.0: context-cost guards. v2.20.0: skill 47 pattern-conformity. 16 dispatchable subagents.

v2.37.0

felvieira

sprint

2.2k·3·

Autonomous multi-agent development framework with spec-driven sprints and convergent iteration

2mo

v1.0.0

jeremylongshore

faos-quick-flow-solo-dev

18·

🚀 Quick Flow Solo Dev — Elite Full-Stack Developer + Quick Flow Specialist

2mo

v1.0.0

frank-luongt

skilltest

17·

Four-layer test framework for Claude Code plugin skills — structure validation, trigger accuracy, session testing, and skill value comparison

2mo

v0.1.0

danielscholl

forwward-teams

15·

Lean agent skills for building, shipping, strategy, and growth — no context bloat.

2mo

v0.1.0

iankiku

Help us improve

Find plugins for your project

Help us improve

jm-adk

Popularity

What's Inside

Help us improve

Health & Quality

Confidence

README

JM Agentic Development Kit Alfa

Component Inventory

Claude Certified Architect Katas

Install

After Clone / First Use

Tool Access (MCP)

User Context Repo

Local State

Similar Plugins

jaan-to

dev-team-kit-fv

sprint

faos-quick-flow-solo-dev

skilltest

forwward-teams

More by JaviMontano

sa

pqa

plugin-qa

sdd-metodologia

pm

JM Agentic Development Kit Alfa

Component Inventory

Claude Certified Architect Katas

Install

After Clone / First Use

Tool Access (MCP)

User Context Repo

Local State