convez.ai
MCP ServerDevOps & InfraestruturaIntermediário
real-case

Marvin Toolkit

real-case/marvin-toolkit

Toolkit completo de dev lifecycle para Claude Code com workflows estruturados

Ver no GitHub
BomPluginScore · de 0 a 100

MCP server que integra um ciclo de desenvolvimento completo no Claude Code através de um único plugin. Oferece 60 prompts, 16 ferramentas MCP, 10 agentes e 10 widgets interativos organizados em comandos estruturados para commit, review, segurança, documentação e deploy de código.

Instalação

$npx convez-ai real-case/marvin-toolkit

1 comando no terminal: detecta o formato do repositório (marketplace ou plugin avulso) e instala via Claude Code. Requer Node 18+ e o Claude Code instalado.

Métricas

Estrelas
0
Forks
0
Acompanhando
0
Saúde
100%
Último commit
há 3 dias
Versão
v0.38.0
Issues abertas
6
Contribuidores
4

Casos de uso

  • Automatizar fluxo de commit com validações de segurança e credenciais
  • Executar análises de segurança e refatoração de código assistidas
  • Orquestrar pipeline de tarefas e board visual para gestão de projeto
  • Gerar documentação e conformidade durante o desenvolvimento

Veredito

Marvin é uma solução madura e bem documentada que consolida ferramentas essenciais de DevOps em um único MCP server. Destaca-se pela segurança built-in (bloqueio de credenciais, force-push em branches protegidas) e triple entry point (chat, slash command, MCP prompt), apesar de exigir Node.js 20+ e estar fortemente acoplado ao ecossistema Anthropic.

README

A tradução para o português deste README ainda está na fila.

Marvin

Claude Code toolkit for those who don't panic.

CI License: MIT Node.js >= 20

Marvin is a Claude Code plugin that packages the whole development lifecycle as one plugin, one MCP server, and one slash prefix — /marvin:. Install it and you get structured, repeatable workflows for committing, reviewing, securing, documenting, and shipping code, all inside Claude Code. Under the hood it ships 60 prompts, 16 MCP tools, 10 agents, and 10 interactive widgets across seven command groups, built on a TypeScript MCP server that runs on Node.js 20 or later.

Call it your way

Each workflow is authored once at plugins/marvin/skills/<command>/SKILL.md, and three independent entry points reach the same body:

  1. Chat. Describe what you want — commit my changes, сделай коммит — and Claude Code matches the skill by its frontmatter description.
  2. Markdown slash command. Type the terse form, such as /commit or /sec-scan.
  3. MCP prompt. Type the namespaced form, such as /marvin:commit, served by the bundled server.

Pick whichever feels right; they all run the same skill. The architecture tour explains how the three entry points resolve, with diagrams.

Install

Run these two commands inside Claude Code:

/plugin marketplace add real-case/marvin-toolkit
/plugin install marvin@marvin-toolkit

The plugin registers one MCP server named marvin, and its commands appear as /marvin:<group>-<command>. No clone or build step is needed, because the server ships bundled.

Installing also lets Marvin block a shell command. Two hooks arrive with the plugin and are armed with no enablement step: one refuses a commit that skips your local gates (git commit --no-verify) and a force-push or deletion aimed at a protected branch, the other refuses a commit whose added lines carry a credential-shaped string. Everything else runs untouched — a quoted --no-verify in a commit message is not a match, a dry-run push is never blocked, and any internal error allows the command rather than blocking it. To turn them off, set "hooks": { "enabled": false } in .marvin/config.json, or export MARVIN_HOOKS_DISABLED=1 for one session. The configuration reference has the details.

Documentation

  • Getting started — install the plugin, then run the guided /marvin:onboard walkthrough.
  • Usage guide — worked walkthroughs for committing, the task pipeline, the task board, security, and refactoring.
  • Configuration — the .marvin/ working directory, .marvin/config.json, and the MARVIN_* environment variables.
  • Command reference — every /marvin: command with a synopsis and the phrases that invoke it.
  • Architecture — how the plugin is built, with diagrams.

The command groups

Commands follow the pattern /marvin:<group>-<command>, and singletons stay bare. The 60 prompts divide into eight groups:

GroupPurposeCount
(bare)Core developer tools18
adr-*ADR lifecycle6
pr-*Pull-request operations4
task-*Spec-driven task pipeline7
sec-*Security scanners11
refactor-*Code-health family (read, plan, apply)4
audit-*Formal project audit (plan, run one, consolidate)3
track-*Lightweight task tracker7

The tables below give a one-line synopsis per command. The command reference adds the natural-language phrases that invoke each one from chat.

Core developer tools

These are language-agnostic and used by every engineer. 👤 = human-run: the model never auto-triggers these, you invoke them yourself.

CommandDescription
/marvin:onboardGuided first session in this project — every write behind an explicit yes.
/marvin:commitDraft a Conventional Commits message with sensitive-file detection.
/marvin:debugSystematic root-cause analysis with hypotheses.
/marvin:adrDraft an Architecture Decision Record; drafts land proposed.
/marvin:changelogGenerate a changelog from git history.
/marvin:readmeGenerate or update README.md from codebase analysis.
/marvin:migration-plan 👤Plan a migration with risks and a rollback strategy.
/marvin:explainExplain code, architecture, and execution flow.
/marvin:docs-searchSearch and synthesize the project documentation.
/marvin:handoffCapture the session context into .marvin/handoff/ to continue later.
/marvin:handoff-listList the session-continuation handoff documents, newest first.
/marvin:lessonsBrowse the lessons-learned store — search, add, stats, and prune.
/marvin:helpShow the project dashboard and the full command index.
/marvin:dashboardReport the whole-toolbox state at a glance.
/marvin:reportsBrowse every generated .marvin/ report, newest first, with freshness.
/marvin:report-exportExport a report to PDF, print-ready HTML, or a Markdown digest (ADR-0033).
/marvin:widget-previewOpen a widget as a rendered panel with this project's data, on any host (ADR-0034).
/marvin:autopilotDeliver a task to a merge-ready PR through the autonomous pipeline; this session only answers its judgments.

The marvin-guide, marvin-researcher, and marvin-debugger agents support these commands. The plugin also registers two external MCP servers: context7 for library docs and gitmcp for GitHub repository docs.

ADR lifecycle — adr-*

These wrap the full decision-record lifecycle around the bare /marvin:adr create command (ADR-0027). Ratification, rollback, and project-memory sync are reserved for a person, marked below with 👤.

CommandDescription
/marvin:adr-reviewDeeply review one proposed record and return a verdict.
/marvin:adr-accept 👤Ratify proposed to accepted through the readiness gate.
/marvin:adr-auditLint the corpus read-only, with remediation guidance.
/marvin:adr-coverageAnalyze gaps between recorded decisions and the actual stack.
/marvin:adr-supersede 👤Roll a decision back through a paired successor record.
/marvin:adr-sync 👤Regenerate the accepted-decisions digest in CLAUDE.md.

Pull-request lifecycle — pr-*

These cover the pull request from open to merge.

CommandDescription
/marvin:pr-createOpen a PR with a structured description and pre-flight checks.
/marvin:pr-reviewReview a PR and post severity-tagged inline comments.
/marvin:pr-resolveWork through unresolved review threads — fix, push, reply, resolve.
/marvin:pr-mergeMerge a PR, then check out the base branch and pull.

Spec-driven task pipeline — task-*

These separate the human decisions in a spec from the automated execution that follows.

CommandDescription
/marvin:task-startCo-create a spec through a dialogue, then a Definition-of-Ready gate.
/marvin:task-implementExecute a ready spec in the current session.
/marvin:task-verifyRun the quality gates with stack auto-detection.
/marvin:task-deliverCommit and open a PR, gated on verification passing.
/marvin:task-summaryAggregate a finished task into one delivery summary.
/marvin:task-auditLint the spec corpus for consistency; read-only, with remediation notes.

The marvin-tm-writer, marvin-tm-executor, marvin-tm-spec-critic, marvin-tm-diff-critic, and marvin-tm-review-fixer agents support this pipeline.

Security scanners — sec-*

These cover OWASP-aligned scanning, threat modeling, and remediation.

CommandDescription
/marvin:sec-scanRun a comprehensive OWASP Top 10:2025 audit.
/marvin:sec-secretsScan for leaked secrets across code, config, and git history.
/marvin:sec-depsAudit dependencies for CVEs, license risks, and maintenance health.
/marvin:sec-gateRun a fast, diff-scoped pre-commit security check.
/marvin:sec-threat-modelBuild a STRIDE threat model for a feature or system.
/marvin:sec-iacReview Infrastructure-as-Code across Terraform, Kubernetes, and Docker.
/marvin:sec-ciAudit CI/CD pipelines for supply-chain risks.
/marvin:sec-fixGenerate and verify a tested patch for a vulnerability.
/marvin:sec-complianceCheck code against OWASP ASVS at L1, L2, or L3.
/marvin:sec-pentestGenerate an application-specific penetration-testing checklist.
/marvin:sec-reportList the structured scanner findings by severity.

The marvin-auditor agent supports these commands.

Refactoring — refactor-*

These form the code-health family (ADR-0029), split by mutation into read, plan, and apply.

CommandDescription
/marvin:refactor-auditRun a whole-project structural audit into a findings register.
/marvin:refactor-smellsScan a path, module, or diff for smells and anti-patterns.
/marvin:refactor-planSequence selected findings into small, risk-annotated steps.
/marvin:refactor-applyExecute one behavior-preserving step behind the verify gate.

The marvin-refactor-auditor agent supports these commands.

Task tracker — track-*

These drive a lightweight per-project board with interactive forms (ADR-0025). New tasks branch off following the convention <type-prefix>/<seq>[-<tracker>]--<slug>, and committing or opening a PR for a board task goes through the board-aware /marvin:commit and /marvin:pr-create, which pick up the linked task automatically.

CommandDescription
/marvin:track-menuOpen the main menu — every board action, including link-pr and archive.
/marvin:track-newCreate a task — bug, feature, chore, or spike.
/marvin:track-listList the board: all tasks by status, the work-in-progress view, or the tracked tasks linking out.
/marvin:track-showShow one task in full.
/marvin:track-startPick a todo task, branch off, and mark it in progress.
/marvin:track-moveMove a task — to review, done, or any configured status.
/marvin:track-configShow or edit the board configuration.

The board dashboard and command reference stay one call away as /marvin:help track (ADR-0032 records the seven-command surface).

Statuses are project data (ADR-0026): configure your tracker's vocabulary through /marvin:track-config, and the lifecycle commands drive it by role. The configuration reference documents every setting.

Interactive widgets

On an MCP host that supports the Apps widget layer, ten widgets render an interactive panel in addition to the text output (ADR-0024). The panel is additive, so a text-only host shows the same information as text and no command depends on a rich host. The widget-backed commands are /marvin:track-list (which fronts both the board list and the tracked link-out view), /marvin:track-show, /marvin:task-summary, /marvin:sec-report, /marvin:handoff-list, /marvin:dashboard, /marvin:help, and /marvin:reports, and /marvin:autopilot shows its run as a status card at least every five minutes (ADR-0051).

Development lifecycle

The core, pr-*, and sec-* commands map onto the everyday flow from planning a change to shipping it.

flowchart LR
  Plan --> Code --> Review --> Secure --> Document --> Ship
PhaseCommands
Planadr, migration-plan
Codedebug, explain, docs-search, refactor-*
Reviewpr-review, refactor-smells
Securesec-scan, sec-secrets, sec-deps, sec-gate
Documentreadme, changelog
Shipcommit, pr-create, pr-resolve, pr-merge

Layer the track-* tracker on top of any of these for day-to-day tracking, and run /marvin:dashboard to see the whole toolbox's state at a glance.

Architecture decisions

Decisions with long-lived consequences are recorded as ADRs under docs/adr/. The two pre-consolidation ADRs, covering the source format and the MCP-first stance, were retired in the publication cut, and their still-relevant rationale is folded into 0001, 0013, and 0018.

ADRDecisionStatus
0001Single-plugin consolidation under one /marvin: prefixAccepted
0002Tool-backed verification gateAccepted
0003Tool-backed Definition-of-Ready gateAccepted
0004Traceable spec contract and gate reorderingAccepted
0005Portable, host-adaptive spec contractAccepted
0006All subagents on Opus; economy via deterministic toolsAccepted
0007Unified .marvin/ working directoryAccepted
0008MCP-door plugin-resource resolutionAccepted
0009Config-first gate resolution for verifyAccepted
0010Tool-backed contract-seal verificationAccepted
0011Tool-backed scope-allowlist gateAccepted
0012Tool-backed delivery gateAccepted
0013Self-contained committed server bundleAccepted
0014Distribution and release model (git tag to GitHub Release; no npm)Accepted
0015verify shell-execution trust boundaryAccepted
0016Bundled external MCP dependencies (context7, gitmcp)Accepted
0017Adversarial critic gates in the task pipelineAccepted
0018Three doors and the instrument taxonomyAccepted
0019Branching model: release main, integration dev, changes via PRsAccepted
0020Root-cause analysis as the marvin-debugger agentAccepted
0021Tool-backed lessons-learned feedback loopAccepted
0022Numeric-prefixed spec filenamesAccepted
0023Unified pr-* pull-request command familyAccepted
0024MCP Apps widget layer: data-first staging and shared data contractsAccepted
0025Kanban goes board-only; git ops fold into the commit and pr-create skillsAccepted
0026Configurable status model: statuses are project data, roles stay closedAccepted
0027Tool-backed ADR lifecycleAccepted
0028Lessons v2: hygiene surface and recall or capture expansionAccepted
0029Refactoring command family: read, plan, apply under hard railsAccepted
0030Toolbox dashboard and local usage logAccepted
0031Rename the kanban-* command group to track-*Accepted
0032Reduce the track-* surface to seven commandsAccepted
0033Report export is template-only (Claude fills a shipped print template)Accepted
0034A local preview door renders widgets on hosts that cannotAccepted
0035A verification is bound to the tree it verifiedAccepted
0036Acceptance oracles are executed and journalled, not narratedAccepted
0037Spec corpus mechanics are tool-backedAccepted
0038A finding has an identity that survives the next scanAccepted
0039A critic's verdict is a receipt on disk, not a sentence in a transcriptAccepted
0040Enforcement runs before the call, as a plugin hookAccepted
0041A widget-bound tool's text is gated on the client's capabilitiesAccepted
0042Bounded critique, and verification before reviewAccepted
0043Task workflow metrics are a committed per-task series, derived at deliveryAccepted
0044The metrics record is written by two gates, not by proseAccepted
0045By-product files are exempted from a task's scope by project configurationAccepted
0046A spec keeps only the sections a reader uses, and states each fact onceAccepted
0047A feature records one red phase, and the delivery gate reads itAccepted
0048A test_one placeholder is shell-quoted by marvin, not by the template authorAccepted
0049The seal stage reads test_one for a whole file instead of refusing its per-test partsAccepted
0050One calibration file per finished run, not one appended logAccepted
0051The autopilot reports at least every five minutes, as one status cardAccepted
0052The delivery gate checks the contract's declared names against the codeProposed

Contributing

Contributions are welcome. Every change must pass the same quality gates CI runs:

npm run lint              # ESLint over the TypeScript source
npm run format:check      # Prettier
npm run lint:manifests    # marketplace and plugin manifest structure
npm run lint:docs         # ADR coverage and working-directory paths
npm run eval:self-test    # trigger-eval harness guard (no network)
npm run eval:trigger      # mock sweep over every trigger dataset
npm run build             # build every workspace
npm run test              # Node.js native test suites
npm run verify-dist       # committed dist/ matches a fresh build

See CONTRIBUTING.md for the full setup and workflow, and CLAUDE.md for the architecture reference.

Security

If you find a vulnerability, please report it privately, as described in SECURITY.md.

License

MIT © Yurii Anichkin

Ver o original no GitHub

Bom para

Relacionados