Search everything...

Stats

Actions

Available In

erpaval

Name: erpaval
Author: theagenticguy

By theagenticguy

Autonomous six-phase software development workflow (Explore/Research/Plan/Act/Validate/Compound) with built-in product discovery, research, strategy, planning, and validation skills. Routes complex engineering tasks through classifiers, multi-agent research, generator-critic planning, and persistent lesson storage for iterative improvement across sessions.

npx claudepluginhub theagenticguy/erpaval --plugin erpaval

Popularity

Stars

Top 25%

Med: 0·Avg: 362

Installs

Top 5%

Med: 0·Avg: 1

What's Inside

Agents1

researcher

/researcher

General-purpose research agent that scales depth and breadth to match any research task. Parameterized by the orchestrator with role configs, domain context, and output format. Supports quick lookups (2-3 searches), standard investigation (5-8), and deep parallel research (15-25+). Used by /research, /deep-research, /build-stack, /draft-prd skills and proactively for pre-coding dependency research, library documentation lookups, and agentic AI framework investigation.

Skills11

agent-ux-patterns

/agent-ux-patterns

Agent UX patterns and human-in-the-loop design: Twilio A2H protocol, Levels of Autonomy (L0-L5), inbox pattern, progressive trust, decision journal, gate reviews, autonomous work reports. Six-phase methodology from vague pain point to concrete data model via landscape research and multi-direction brainstorming. Use when the user asks to design agent UX, pick an autonomy level, build a human-in-the-loop flow, structure an agent inbox, design approval gates, or mentions A2H, autonomy level, progressive trust, inbox pattern, approval gate, decision journal, or agentic design. Do NOT use for PRD drafting — use product-discovery. Do NOT use for frontend components — use frontend-design. Do NOT use for building agents with a specific SDK — use claude-agent-sdk, strands-sdk, langgraph-langchain, or mastra-vercel-ai.

customer-research

/customer-research

Customer research and problem framing using the research-design discipline: hypothesis, null hypothesis, MECE questions, methods, findings. Produces Pyramid-base-shaped output ready for downstream composition into PR/FAQs, long-form narratives, or PRDs. Use when the user asks to design user research, run customer interviews, synthesize research findings, frame a problem statement, build a customer journey map, plan a VoC study, or mentions pain-point analysis, research plan, hypothesis testing, customer insights, jobs-to-be-done, or voice of customer.

erpaval

/erpaval

Workflow for autonomous software development with Claude Code. Classifiers route scope, complexity, directory state, and spec readiness before committing to Explore / Research / Plan / Act / Validate, then close the loop with a Compound step that persists lessons to `.erpaval/solutions/` for future sessions. Optional HMW reframing and EARS specification add structured rigor — Claude judges when to run them. Each Act subagent edits its own Markdown task packet section-by-section per the write protocol, and the orchestrator monitors with `wc -l`. Use when the user asks to implement a feature autonomously, build with agents, use ERPAVal, plan and execute a coding task, delegate to subagents, do agent-driven development, extract lessons, recall prior lessons, or mentions autonomous coding workflow or compound engineering.

meta-prompt-optimizer

/meta-prompt-optimizer

Audit and rewrite prompts against Claude Opus 4.7 instruction-following best practices. Produces a scored audit plus a rewritten prompt. Use when the user asks to audit, review, critique, rewrite, improve, optimize, tighten, score, fix, migrate, or draft a prompt — including system prompts, CLAUDE.md files, Claude Code agent definitions, slash commands, SKILL.md files, Jinja2 prompt templates, or tool/parameter descriptions in Pydantic v2 or Zod schemas. Trigger on phrases like "is this prompt any good", "why isn't Claude following this", "why isn't my agent triggering", "my CLAUDE.md is being ignored", "rewrite this for Opus 4.7", "cache hit rate is low on my prompt", "the model keeps picking the wrong tool", or on pasted prompt text asking for feedback. Also trigger on mentions of prompt engineering, prompt best practices, or instruction-following problems. Use this skill whenever the task involves editing, reviewing, or writing the text of a prompt — even if the user doesn't say "prompt".

product-design-shared

/product-design-shared

Shared canonical references for product-design frameworks — Pyramid Principle, Working Backwards, Double Diamond, research design, methodology selection. Consumed by `product-discovery`, `product-strategy`, `working-backwards`, and `customer-research` via `${CLAUDE_PLUGIN_ROOT}/skills/product-design-shared/references/`. Do NOT invoke this skill directly — it has no orchestrator and no templates. Load the upstream skill that owns your task (`product-discovery` for PRD / HMW / EARS, `product-strategy` for Rumelt / Wardley / Minto, etc.) and let it pull from this pool as needed.

Hooks1

Event Hooks

File writes

3 hooks across 3 events

MCP Servers5

Stats

Version1.2.0

LanguagePython

Stars18

Forks1

Copy clicks2

MaintenanceExcellent

LicenseMIT

Last CommitMay 29, 2026

AddedMay 9, 2026

Actions

View on GitHub View README Plugin Marketplace JSON

Own this plugin?

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

Available In

erpaval18

Safety Signals

Caution

Modifies files

Hook triggers on file write and edit operations

External network access

Connects to servers outside your machine

README

ERPAVal

ERPAVal banner

Autonomous software development for Claude Code.

ERPAVal stands for Explore · Research · Plan · Act · Validate — the five-phase loop, plus a sixth Compound phase that writes durable lessons to disk so the next session inherits what this one learned.

Six phases, classifier-driven routing, and a compounding memory layer that makes every session smarter than the last.

A structured workflow for teams of Claude Code agents that build software the way a senior engineer would — if that engineer could run ten of themselves in parallel and actually remember what they learned yesterday.

[!NOTE] ERPAVal has only been tested with Claude Code. It relies on Claude Code's Agent tool, TaskCreate/TaskUpdate/TaskList task system, plugin hooks (SessionStart, PostToolUse, Stop), and ${CLAUDE_PLUGIN_ROOT} path resolution. It will not work with other AI coding tools or generic Claude API integrations.

[!IMPORTANT] Star → Fork → make it your own. ERPAVal is opinionated about coding workflow but agnostic about everything else. The bundle gives you a working flow on day one, but the workflow is designed to absorb your conventions, your team's writing style, your domain's vocabulary. Fork this repo, vendor in your own skills, swap out the ones that don't fit, rewrite the classifier prompts to match how you think. Re-syncing from upstream personal-plugins is intentionally manual — users who fork should diverge.

Install

ERPAVal is a Claude Code plugin. There are two ways to install it.

Option A — Claude Code plugin marketplace (recommended)

Ships everything: skills, agents, hooks, and MCP server config.

In a Claude Code session, run:

/plugin marketplace add theagenticguy/erpaval
/plugin install erpaval@erpaval

Adding a marketplace is lazy — nothing loads until you install. The plugin installs to your user scope (available in every project) by default. To scope it to one project instead, use /plugin install erpaval@erpaval --scope project.

Then enable the plugin and reload so its skills, agents, and hooks activate:

/plugin            # → Installed tab → erpaval → Enable
/reload-plugins

Verify by listing skills:

/help              # /erpaval:* should appear in the namespace

To uninstall:

/plugin uninstall erpaval
/plugin marketplace remove theagenticguy/erpaval

[!NOTE] If /plugin marketplace add reports "not found", update Claude Code to a recent version (v2.1.x or later) and retry.

Option B — `skills.sh` CLI (skills only, multi-agent)

skills.sh is the open agent-skills directory. Its CLI installs the skills to whichever coding agents you have locally — Claude Code, Cursor, Codex, Windsurf, and ~50 others. It does not install the hooks, agents, or MCP server config that the plugin marketplace ships.

npx skills add theagenticguy/erpaval

Use this path if you want ERPAVal's skills available across multiple agents. Use Option A if you want the full Claude Code experience (compounding lessons, validation hooks, the Compound-phase nudge).

Option C — Local development install

To hack on the plugin without going through either:

git clone https://github.com/theagenticguy/erpaval
claude --plugin-dir ./erpaval

The problem

For single-file changes, the basic loop works: give Claude a task, get working code back, ship it. The loop breaks when a task touches multiple modules, depends on unfamiliar APIs, or requires coordinating work across files that reference each other.

It breaks in a second, quieter way: the next session starts from scratch — even though the previous one just spent two hours learning the codebase's peculiarities.

[!IMPORTANT] The failure mode of unstructured AI coding is not broken code. It is plausible code that does not belong, written by an agent that forgot last week's lessons.

ERPAVal fixes both: it front-loads understanding, crystallizes intent into a per-task context packet, hands each implementing subagent a curated briefing, and closes the loop by writing what was learned to disk so future sessions inherit it.

The flow

The high-level shape is a six-phase pipeline gated by mechanical dependency checks, with one deliberate human review at Gate 1.

flowchart LR
  IN([User request]) --> CL[Classifiers]
  CL --> ER[Explore +<br/>Research]
  ER -->|Gate 0| PLAN[Plan]
  PLAN -->|Gate 1<br/>human review| ACT[Act · waves]
  ACT --> VAL[Validate]
  VAL -.->|fail| ACT
  VAL -->|Gate 2| COMP[Compound]
  COMP --> DONE([Done])

View full README on GitHub

Similar Plugins

tool-evaluator

792·1·

Use this agent when evaluating new development tools, frameworks, or services for the studio. This agent specializes in rapid tool assessment, comparative analysis, and making recommendations that align with the 6-day development cycle philosophy. Examples:\n\n<example>\nContext: Considering a new framework or library

8mo

v1.0.0

ccplugins

claude-dev-kit

11·

PRD-driven AI dev team control plane for Claude Code — agents, skills, and a GitHub-first sprint workflow.

v0.1.0

pillip

sprint

2.2k·5·

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

3mo

v1.0.0

jeremylongshore

karimo

183·

Autonomous development methodology: PRD interviews → agent execution → automated review

2mo

v8.2.1

opensesh

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

20·2·

52 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, ui-polish + spec-driven development, anti-AI writing, memory consolidation, executable YAML pipelines + insights dashboard (v2.18.0, 6 tabs). v2.38.0: skill 52 ui-polish absorvida de jakubkrehel/make-interfaces-feel-better (MIT) — 16 principios de acabamento visual (border radius concentrico, alinhamento optico, sombra vs borda, animacoes interrompiveis, split/stagger, saida sutil, animacao contextual de icone com valores exatos, font smoothing, tabular numbers, text wrapping, image outline, scale on press, skip animation on load, will-change moderado, hit area minima); referencia cruzada em skill 12 (motion-design) e skill 02 (ui-ux-design). 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.

v2.38.0

felvieira

erpaval

Popularity

What's Inside

Confidence

README

ERPAVal

Install

Option A — Claude Code plugin marketplace (recommended)

Option B — skills.sh CLI (skills only, multi-agent)

Option C — Local development install

The problem

The flow

Similar Plugins

tool-evaluator

claude-dev-kit

sprint

karimo

jaan-to

dev-team-kit-fv

More by theagenticguy

agentic-skills

plugin-gardener

ERPAVal

Install

Option A — Claude Code plugin marketplace (recommended)

Option B — skills.sh CLI (skills only, multi-agent)

Option C — Local development install

The problem

The flow

Popularity

Health & Quality

More by theagenticguy

agentic-skills

plugin-gardener

Similar Plugins

tool-evaluator

claude-dev-kit

sprint

karimo

jaan-to

dev-team-kit-fv

Option B — `skills.sh` CLI (skills only, multi-agent)

Option B — `skills.sh` CLI (skills only, multi-agent)