Comprehensive validation, management, and standardization suite for Claude Code plugins and marketplaces. Includes 190+ validation rules, plugin lifecycle management, marketplace operations, health checks, security auditing, GitHub repo validation, plugin/marketplace repo scaffolding, and standardization tooling.…
General-purpose CPV worker. Receives a free-form plugin-quality request and autonomously routes it to the right claude-plugins-validation skill, agent, or script, then executes the whole job in an isolated context. Dispatch it for "use CPV to " or "read the CPV skills menu and pick what is needed" — validate…
Self-sufficient cache-optimization WORK agent dispatched by the cpv-main-menu (menu-tree §3.3 cache rows) or by the /cpv-batch-caching-audit and /cpv-batch-caching-optimize commands. Accepts EITHER a pre-existing cache-audit report path OR a plugin/project path via the dispatcher's block. Runs the full validate → fix…
CPV doctor WORK agent invoked by the /cpv-main-menu main-session orchestrator (Diagnose category). The orchestrator renders the "Diagnose what?" first-contact menu and collects per-action follow-up; this agent receives a structured block with the resolved mode and targetpath and runs the matching diagnostic recipe.…
Self-sufficient marketplace fix WORK agent dispatched from the /cpv-main-menu flow after a menu choice is made. Accepts either a validation report OR a marketplace repo path via the dispatching menu's block. Runs validate → fix → re-validate in a loop until the marketplace is clean (zero CRITICAL/MAJOR/MINOR/NIT and…
Creates new Claude Code plugin or marketplace repositories from scratch with full CI/CD pipeline, git hooks, and standard file structure, then publishes and watches GitHub CI to green before declaring done. Use when user wants to create a new plugin, scaffold a repo, or set up a new marketplace hub.
Security devitalization WORK agent. Accepts a security report OR a plugin path via the dispatching menu's block, and converts execution-class findings into PROVABLY-INERT data — passing CPV's security gate by neutralizing each threat's executable shape, NEVER by suppressing a rule or relaxing --strict. Refuses to…
Deep diagnostic auditor for Claude Code plugins. Goes beyond validateplugin (structure-only) by ALSO running all 5 external security scanners, the pipeline-staleness checks, the cross-platform compliance checks, the marketplace-registration probe, and the cached-vs-GitHub sync probe. Returns a structured diagnosis…
Self-sufficient fix WORK agent. Accepts a validation report OR a plugin path via the dispatching menu's block and runs validate → fix → re-validate in a loop until the plugin is clean (zero CRITICAL/MAJOR/MINOR/NIT and zero publish-blocking WARNINGs). Loads the cpv-fix-validation, cpv-canonical-pipeline, and…
Security leaks-and-hardening WORK agent. Takes a security report OR a plugin path and fixes LEAK + MISSING-SAFEGUARD findings without breaking functionality — passing CPV's security gate by REMOVING exposed secrets and IMPLEMENTING missing safeguards, NEVER by suppressing a rule. Redacts secrets (runtime-reading the…
Autonomous plugin management agent for installing, validating, and maintaining Claude Code plugins. Use when user asks to: install/uninstall plugins, validate plugin quality, check plugin health, search for plugins by type, manage marketplaces, or perform bulk plugin operations.
Lightweight validation agent that runs scripts and returns compact summaries. Does NOT fix issues or perform semantic analysis — use cpv-plugin-fixer-agent and cpv-semantic-validator-agent for those. A thin script-launcher (per TRDD-82e836dc): the entire workflow is Bash + Read + 1-2 lines of summary, no analysis.…
Deep AI-driven semantic analysis agent for skill and agent quality. Evaluates description triggering, instruction clarity, example quality, and workflow completeness — things scripts cannot check. Use only via /cpv-semantic-validation (explicit opt-in; 10-50x token cost).
Lightweight skill validation agent that runs scripts and returns compact summaries. Does NOT fix issues or perform semantic analysis — use cpv-plugin-fixer-agent and cpv-semantic-validator-agent for those. A thin script-launcher (per TRDD-82e836dc): the entire workflow is Bash + Read + 1-2 lines of summary, no…
CPV's bundled lightweight implementation agent — focused fixes, quick tweaks, file creations, code changes inside a CPV workflow. Use for short-context dispatches from CPV menus and orchestrators where the task is bounded (one file or one symbol) and TDD-grade rigor would be overhead. Launch many in parallel for…
Direct free-form entry to the general-purpose CPV worker. Pass any plugin-quality request as arguments and it routes to the right CPV skill, agent, or script and runs the whole job in an isolated context — validate, scan, fix, optimize cache, create, publish, migrate a marketplace, manage installed plugins, or update…
Fan out cpv-cache-optimizer-agent across every plugin in a marketplace, a list of plugins, or a single plugin. Accepts local paths and GitHub URLs. One cpv-cache-optimizer-agent per plugin running in batchaudit mode (read-only — Phase 1 of the cache pipeline). Detects the seven prompt-cache-invalidation patterns…
Fan out cpv-cache-optimizer-agent across every plugin in a marketplace, a list of plugins, or a single plugin and APPLY the cache-invalidation fixes (CA-01..CA-07). Accepts local paths and GitHub URLs. One cpv-cache-optimizer-agent per plugin in batchfix mode (Phase 1 audit + Phase 2 fix + Phase 3 re-validate; Phase 4…
Parallel fix for one OR many plugins. Single-plugin inputs run the existing per-shard protocol (one cpv-plugin-fixer-agent per shard of findings). Marketplace / list / URL inputs run a per-plugin fan-out (one cpv-plugin-fixer-agent per plugin; each fixer may internally shard its own findings). Accepts local paths…
Maximum-coverage same-turn scan + fix. One cpv-plugin-fixer-agent per plugin reads each source file ONCE and runs validate + security + caching audit + caching optimize + verify-FPs + fix — all inline. Each per-file scan triggers every applicable checker; confirmed-real findings are fixed; confirmed-FPs are skipped.…
Same-turn diagnose + fix across a fleet of project folders. One cpv-doctor-agent per project scans the requested scope + verifies findings + applies obvious fixes inline (NIT and CRITICAL auto; MAJOR / MINOR auto when the recipe is safe). LOCAL paths only — URL inputs are CRITICAL errors. Default 8 parallel agents per…
Read-only diagnostic across a fleet of project folders. One cpv-doctor-agent per project diagnoses the requested scope — user (/.claude/), project ( /.claude/), local ( /.claude/settings.local.json), or full (all three + cross-scope conflict checker). LOCAL paths only — URL inputs are CRITICAL errors because the…
Apply fixes for scope-aware doctor findings across a fleet of project folders. One cpv-doctor-agent per project in batchscopefix mode handles the requested scope (user / project / local / full). LOCAL paths only — URL inputs are CRITICAL errors. Default 8 parallel agents per main-session message, cap 16.
Fan out security-only validation across every plugin in a marketplace, a list of plugins, or a single plugin. Accepts local paths and GitHub URLs. One cpv-plugin-validator-agent agent per plugin (mode batchsecurityaudit) running only the security checker — five external scanners (cc-audit, tirith, trufflehog, semgrep…