v8.19.3 (2026-07-01, PATCH — arm-classifier: keyword-inferred read-only runs no longer arm [recurring phantom-arm deadlock fix]): a natural-language review/audit/analysis request ('faça revisão adversarial', 'faça uma auditoria', 'análise') was classified FULL/Audit and armed the pipeline-arm-pending marker — but read-only work never opens an exec window, so it hit INLINE_WORK_BLOCKED, aborted, and left an orphan marker that bricked the next task with PIPELINE_NOT_ARMED (observed live in interview-coach 2026-06-30 and 07-01). FIX: lib/pipeline-arm.cjs::writeArmPending now also skips arming for the read-only TYPES (Audit, UX Simulation) when they were INFERRED FROM KEYWORDS (source kw:), while an EXPLICIT --audit/--ux flag stays a deliberate governed run and still arms (preserving the STEP_1_7 direct-entry evidence, v8.16.0). Safe direction per the documented arm trade-off: a missed arm is recoverable (re-invoke); a phantom arm deadlocks. TDD tests/regression/v8.19.3/F1-readonly-types-no-arm (RED 4-fail → GREEN); 2 deliberate v8.7.0 pins updated to the --audit-flag path. Iron Law: only lib/pipeline-arm.cjs + tests/ touched; Gates/Registry UNTOUCHED; no .codex mirror. Suite 252/5 (5 pre-existing Langfuse/env/F4). Lockstep across all version surfaces. v8.19.2 (2026-07-01, PATCH — edit-guard-hook robustness [Cursor-crash hardening, Claude-Code-scoped]): the PreToolUse edit-guard no longer crashes into the opaque external catch ('edit-guard-hook internal error — failing closed') when .pipeline/sessions is present-but-unreadable (a file where a dir is expected → ENOTDIR/EACCES) — getActiveLock + getActiveExecWindow now guard readdirSync and return null instead of throwing, and the CLI external catch surfaces the REAL sanitized error (single-line, printable-ASCII, capped 200) instead of the opaque message, so a genuine failure stays fail-closed but debuggable. Posture UNCHANGED (still deny when the guard cannot evaluate); NO foreign tool-name vocabulary added — cross-runti
Plugin pipeline-orchestrator from marketplace FX-Studio-AI in fernandoxavier02/Pipeline-Orchestrator. 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. The exact commands are listed below; read them before installing.
engineering-principlesPrincipios canonicos de engenharia (SOLID, KISS, DRY, YAGNI, SSOT, Clean Architecture, fail-fast, defensive-at-boundaries). Fonte de regra default quando uma decisao tecnica nao esta coberta pela spec do workflow. Carregada por TODOS os 50 cargos como ultima linha de defesa antes de escalar ambiguid
pipeline-orchestrator-adversarialProtocolo de revisao adversarial (zero-context) com checklists de security, architecture e quality. Usado pelos cargos adversarial-* e final-adversarial-orchestrator.
pipeline-orchestrator-audit-methodMetodo de auditoria de codebase em 4 fases — Intake (inventory), Domain Analyzer (arquitetura + SSOT), Compliance Checker (integrity + security), Risk Matrix (priorizacao + backlog). Usado pelos cargos audit-*.
pipeline-orchestrator-bugfix-methodMetodo cientifico para bug fix — Diagnostic (terrain + hypothesis ranking) → Root Cause (evidence chain) → Fix (TDD via regressao) → Regression Test (suite + adjacent breakage). Usado pelos cargos bugfix-*.
pipeline-orchestrator-classificationClassificacao de tipo de tarefa (Feature, Bug Fix, User Story, Spec, UX, Audit, Adversarial Review) e nivel de complexidade (SIMPLES, MEDIA, COMPLEXA), com regras de roteamento. Usada por task-orchestrator e information-gate.
pipeline-orchestrator-contractsContratos de comunicacao adaptados (GATE_REQUEST, DISPATCH_REQUEST, ORCHESTRATOR_DECISION, etc.) do pipeline-orchestrator original para o modelo Paperclip+Codex (assincrono, ticket-based, comment-driven).
pipeline-orchestrator-iron-lawsIron Laws inalteradas do pipeline-orchestrator original (TDD obrigatorio, ask-first em ambiguidade, self-review, stop rule, evidence-based decisions). Carregada por todos os 50 cargos.
pipeline-orchestrator-spec-protocolProtocolo de spec lifecycle (format-gate, content-review, post-impl-validator) com formato EARS e regras de aceitacao. Usado pelos cargos spec-*.
pipeline-orchestrator-tddImplementacao de TDD (Test-Driven Development) com fase RED obrigatoria antes de GREEN. Usado por todos os cargos executor que escrevem codigo.
pipeline-orchestrator-ux-methodMetodo de UX review — persona matrix + jornadas + WCAG 2.1 AA accessibility + consolidacao com matriz de prioridade. Usado pelos cargos ux-*.
pipeline-orchestrator-vsaVertical Slice Architecture para Feature/User Story pipelines — quebrar feature em slices verticais end-to-end com BDD Gherkin. Usada pelos cargos feature-*.
audit-heavyPrescriptive 9-step audit workflow for COMPLEXA audits (full system, multi-axis, regulatory, security-sensitive). Imported from Pulsar audit workflow per spec §22. Use when audit complexity is heavy or when audit-light auto-escalates at its scope gate. REPORT-ONLY by Iron Law — no code modification
audit-lightPrescriptive 9-step audit workflow for SIMPLES/MEDIA audits (1 area, 1 depth level, single-axis or narrow scope). Imported from Pulsar audit workflow per spec §22. Use when audit complexity is light. REPORT-ONLY by Iron Law — no code modification under any circumstance. Same 9-step structure as audi
auditAudit shortcut — skips task-orchestrator type-classification by pre-fixing task_type=Audit. Same pipeline machinery as /pipeline-orchestrator:pipeline (information-gate, design-interrogator, plan-architect, executor-controller, sanity, Pa de Cal). Invoked manually via `/pipeline-orchestrator:audit [
bugfix-heavyPrescriptive 11-step bug fix workflow for COMPLEXA bugs and production incidents (cross-cutting concerns, persistence, concurrency, multi-user impact, business rules). Imported from Pulsar bugfix workflow per spec §21. Use when complexity classification is heavy or when bugfix-light auto-escalates a
bugfix-lightbugfixfeature-heavyfeature-lightfeaturemeasure-paperclip-fidelitypipelinerefactor-heavyrefactor-lightrefactorreviewspec-audit-onlyspec-designspec-heavyspec-initspec-lightspec-requirementsspec-reviewspec-tasksspecunblockuser-story-heavyuser-story-lightuser-storyux-sim-heavyux-sim-lightux-simvalidate-designvalidate-gapverify-completion/pipeline-orchestrator:brainstormPre-execution preparation pipeline (Kiro-clone integrated). Runs intake → dynamic exhaustive clarification (v6.2+) → alternative-approach brainstorming (v6.2+) → spec lifecycle (init/requirements/validate-gap/design/validate-design/tasks) before optional handoff to /pipeline-orchestrator:pipeline. M
/pipeline-orchestrator:helpCardápio do plugin pipeline-orchestrator: explica os comandos em linguagem simples — o que cada um faz, quando usar, exemplo, e as opções (flags) de cada um. Não executa nada, só exibe o guia.
/pipeline-orchestrator:paperclip-auditDespacha um Audit para os robôs do Paperclip (VPS). Fluxo somente-leitura: intake → domínio → compliance → risco, gerando relatórios técnico e executivo. Classifica complexidade localmente, mostra a árvore em dry-run e pede confirmação antes de criar qualquer cartão.
/pipeline-orchestrator:paperclip-bugfixDespacha um Bug Fix para os robôs do Paperclip (VPS). Classifica complexidade localmente, mostra a árvore em dry-run e pede confirmação antes de criar qualquer cartão.
/pipeline-orchestrator:paperclip-featureDespacha uma Feature para os robôs do Paperclip (VPS). Classifica complexidade localmente, mostra a árvore em dry-run e pede confirmação antes de criar qualquer cartão.
/pipeline-orchestrator:paperclip-hotfixDespacha um Hotfix de emergência para os robôs do Paperclip (VPS). Tipo e complexidade são fixos (Bug Fix / COMPLEXA / Critical) — sem classificação, sem light/heavy. Mostra a árvore em dry-run e pede confirmação antes de criar qualquer cartão.
/pipeline-orchestrator:paperclip-overviewÍndice dos 8 comandos paperclip-* que despacham uma árvore de tarefas para os robôs do Paperclip na VPS. Cada comando classifica localmente, mostra a árvore em dry-run e só cria os cartões após confirmação explícita do usuário.
/pipeline-orchestrator:paperclip-refactorDespacha um Refactor para os robôs do Paperclip (VPS). Classifica complexidade localmente, mostra a árvore em dry-run e pede confirmação antes de criar qualquer cartão.
/pipeline-orchestrator:paperclip-reviewDespacha um Review-Only para os robôs do Paperclip (VPS). Modo standalone de revisão adversarial final sobre mudanças já escritas — sem correções, sem planejamento, sem TDD. Mostra a árvore em dry-run e pede confirmação antes de criar qualquer cartão.
/pipeline-orchestrator:paperclip-specDespacha uma Spec para os robôs do Paperclip (VPS). Classifica complexidade localmente, mostra a árvore em dry-run e pede confirmação antes de criar qualquer cartão.
/pipeline-orchestrator:paperclip-user-storyDespacha uma User Story para os robôs do Paperclip (VPS). Deriva critérios de aceite a partir da narrativa em linguagem natural, classifica complexidade localmente, mostra a árvore em dry-run e pede confirmação antes de criar qualquer cartão.
/pipeline-orchestrator:paperclip-uxDespacha uma UX Simulation para os robôs do Paperclip (VPS). Classifica complexidade localmente, mostra a árvore em dry-run e pede confirmação antes de criar qualquer cartão.
/pipeline-orchestrator:pipelineSingle-command multi-agent pipeline. Auto-classifies tasks, confirms with user, executes in adaptive batches with TDD, context-independent adversarial review with user gates, final adversarial team (3 parallel agents), and Go/No-Go validation. Modes: FULL | DIAGNOSTIC | CONTINUE | REVIEW-ONLY | --fo
/pipeline-orchestrator:self-evalSelf-improvement loop. After a pipeline run, reviews how faithfully it executed step-by-step (from the deterministic e2e-eval), then for each execution glitch PROPOSES a fix — nothing is applied without your approval (approve → fix, reject → record). Accumulates a cross-run evaluation dataset to imp
/pipeline-orchestrator:setup-paperclipConfigura Paperclip (open-source agent orchestration) com o plugin pipeline-orchestrator. Detecta install, cria empresas FX Studio AI + Pipeline Orchestrator, contrata 47 cargos via API, configura adapter claude_local + cwd canonical, instala junctions de skills. End-to-end.
node "${CLAUDE_PLUGIN_ROOT}/.claude/hooks/cleanup-orphan-sentinel-state-hook.cjs"
node "${CLAUDE_PLUGIN_ROOT}/.claude/hooks/pipeline-session-arm-hook.cjs"
node "${CLAUDE_PLUGIN_ROOT}/.claude/hooks/enforcement-surface-verify-hook.cjs"
node "${CLAUDE_PLUGIN_ROOT}/.claude/hooks/force-pipeline-agents.cjs"
node "${CLAUDE_PLUGIN_ROOT}/.claude/hooks/session-lock-hook.cjs"
node "${CLAUDE_PLUGIN_ROOT}/.claude/hooks/pipeline-arm-writer.cjs"
node "${CLAUDE_PLUGIN_ROOT}/.claude/hooks/stop-gate-hook.cjs"
node "${CLAUDE_PLUGIN_ROOT}/.claude/hooks/completion-checklist.cjs"
node "${CLAUDE_PLUGIN_ROOT}/.claude/hooks/session-cleanup-hook.cjs"
node "${CLAUDE_PLUGIN_ROOT}/.claude/hooks/stop-hook.cjs"
node "${CLAUDE_PLUGIN_ROOT}/.claude/hooks/e2e-eval-gate.cjs"
node "${CLAUDE_PLUGIN_ROOT}/.claude/hooks/stop-gate-hook.cjs"
node "${CLAUDE_PLUGIN_ROOT}/.claude/hooks/stop-gate-hook.cjs"
node "${CLAUDE_PLUGIN_ROOT}/.claude/hooks/subagent-stop-commit-hook.cjs"
node "${CLAUDE_PLUGIN_ROOT}/.claude/hooks/corrective-error-signal-gate.cjs"
node "${CLAUDE_PLUGIN_ROOT}/.claude/hooks/langfuse-hook.cjs"
node "${CLAUDE_PLUGIN_ROOT}/.claude/hooks/step-ledger-stamp.cjs"
node "${CLAUDE_PLUGIN_ROOT}/.claude/hooks/human-gate-record.cjs"
node "${CLAUDE_PLUGIN_ROOT}/.claude/hooks/machine-evidence-hook.cjs"
node "${CLAUDE_PLUGIN_ROOT}/.claude/hooks/corrective-dispatch-gate.cjs"
node "${CLAUDE_PLUGIN_ROOT}/.claude/hooks/sentinel-state-autosign.cjs"
node "${CLAUDE_PLUGIN_ROOT}/.claude/hooks/audit-read-counter-hook.cjs"
node "${CLAUDE_PLUGIN_ROOT}/.claude/hooks/audit-read-budget-gate.cjs"
node "${CLAUDE_PLUGIN_ROOT}/.claude/hooks/sentinel-hook.cjs"
node "${CLAUDE_PLUGIN_ROOT}/.claude/hooks/langfuse-hook.cjs"
node "${CLAUDE_PLUGIN_ROOT}/.claude/hooks/dispatch-record-hook.cjs"
node "${CLAUDE_PLUGIN_ROOT}/.claude/hooks/audit-dispatch-marker.cjs"
node "${CLAUDE_PLUGIN_ROOT}/.claude/hooks/parallel-dispatch-gate.cjs"
node "${CLAUDE_PLUGIN_ROOT}/.claude/hooks/step-ledger-gate.cjs"
Claude Code Swiss Army Knife — diagnose, configure, and build your Claude Code environment. Meta-skill /cc with triage menu + 9 specialized skills for context audit, MCP, hooks, agents, prompts, security, setup, and skill building.
11 skills · 1 command · hooks
Intelligent toolchain orchestrator for Claude Code — recommends skills, plugins, MCPs, and agents for any task with dependency-aware ordering. v0.5.1: dependency bump (@huggingface/transformers ^4.0.1 → ^4.1.0) + README polish. v0.5.0: architectural overhaul closing 10-finding audit. Hot-path hook 387→85 lines via lib/advisor-nudge-core extraction; 4 architectural guards CI-enforced (DI-1 module-load purity, DI-2 layered dependency direction, DI-3 manifest version coherence, vault env single source); module-scoped mtime+size cache for embeddings/graph; unified filesystem walker; 812 tests (+24% from 654). BREAKING (restorable): default prompt-length threshold 5→12 chars; restore via ADVISOR_PROMPT_LENGTH=5. Deprecation runway through 0.6.0 for SKILL_ADVISOR_VAULT (use SKILL_ADVISOR_VAULT_PATH) and build-index.inferCategory re-export.
3 skills · 7 commands · 2 agents · hooks
Generates mandatory engineering rules, architecture contracts, anti-pattern catalogs, and validation tests adapted to any project's stack. 6 focused skills: setup, detect-stack, map-architecture, generate-rules, mine-anti-patterns, validate-context.
6 skills · 6 commands
Text-to-speech offline em portugues do Brasil para Claude Code. Hook Stop sintetiza audio do output do agente via Kokoro local (neural, voz feminina pf_dora) com pre-processamento que strippa codigo, paths e markdown antes de virar fala. Sem API key, sem limite (apos setup inicial). Windows 11 + PowerShell 7. Changelog completo em CHANGELOG.md no repo.
Matt Pocock's agent skills for real engineering (grilling, spec/ticket flows, TDD, code review, domain modelling and more).
39 skills
Core skills library for Claude Code: TDD, debugging, collaboration patterns, and proven techniques
15 skills · hooks
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
Build powerful, stateful CLI interfaces for any GUI application using the cli-anything harness methodology.
5 commands
5 skills + 35 modes + Material Passport pipeline. Includes v3.6.7 cross-model audit gate and v3.6.8 generator-evaluator contract.
5 skills · 16 commands · 4 agents · hooks
Automates browser interactions for web testing, form filling, screenshots, and data extraction
12 skills
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.