claude-plugins-validation

Plugin claude-plugins-validation in Emasoft/claude-plugins-validation. Commands read from the repo's manifest — 21 days ago.

Skills (52)

• cpv-add-component-to-plugin

  Add a new component (skill / agent / command / hook / mcp) to an existing plugin. Use when scaffolding a single component into a plugin without re-running the generator. Used dynamically via cpv-the-skills-menu (TRDD-478d9687).

• cpv-add-dependency

  Add plugin dependencies to a target plugin (explicit --add specs or --from copy from another plugin's plugin.json). Use when adding/copying plugin.json::dependencies entries with atomic rollback on regression. Used dynamically via cpv-the-skills-menu (TRDD-478d9687).

• cpv-add-hook

  Add a new hook entry to hooks/hooks.json in an existing plugin (idempotent — skips duplicate entries; cross-platform-aware). Use when adding a new event-handler that must run identically on Linux/macOS/Windows. Used dynamically via cpv-the-skills-menu (TRDD-478d9687).

• cpv-batch-caching-audit

  Fleet-wide read-only cache audit. Accepts local paths, GitHub URLs, marketplaces, lists, and @listfile shapes. One cpv-cache-optimizer-agent per plugin runs Phase 1 only — detects CA-01..CA-07 prompt-cache invalidation patterns, no fixes. Use when surveying cache-invalidation findings across many pl

• cpv-batch-caching-optimize

  Fleet-wide parallel cache fix. Accepts local paths, GitHub URLs, marketplaces, lists, and @listfile shapes. One cpv-cache-optimizer-agent per plugin runs Phase 1 audit + Phase 2 fix + Phase 3 re-validate; Phase 4 broader refactor SKIPPED (run the cpv-cache-optimizer-agent on a single plugin to opt i

• cpv-batch-fix-protocol

  Schema reference for the /cpv-batch-fix parallel-shard fix protocol — manifest format, status format, planner/aggregator contracts. Use when implementing a new consumer of the batch protocol or extending the planner/aggregator. Used dynamically via cpv-the-skills-menu (TRDD-478d9687) — any CPV agent

• cpv-batch-fix

  Parallel fix for one OR many plugins. Accepts local paths, GitHub URLs, marketplaces, lists, and @listfile shapes. Single-plugin input → per-shard fan-out (v2.91.0 protocol). Marketplace/list input → per-plugin fan-out (one cpv-plugin-fixer-agent per plugin, internal sharding when needed). Use when

• cpv-batch-full-scan-and-fix

  Maximum-coverage same-turn sweep across a marketplace / list / single plugin. Each cpv-plugin-fixer-agent reads every source file ONCE and runs validate + security + caching audit + caching optimize + verify-FPs + fix inline. ~5× cheaper than running the four separate batch skills sequentially. Use

• cpv-batch-scope-diagnose-and-fix

  Same-turn scope-aware diagnose + fix across a fleet of project folders. One cpv-doctor-agent per project scans + verifies + applies obvious fixes inline (NIT, CRITICAL, and safe MAJOR/MINOR auto; unsafe MAJOR/MINOR reported in pending_fixes[]). Cuts per-project token cost ~2× vs running scope-diagno

• cpv-batch-scope-diagnose

  Read-only fleet-wide scope-aware doctor. One cpv-doctor-agent per project diagnoses the requested scope — user (the home .claude tree), project (the project .claude tree), local (settings.local.json), or full (all + cross-scope conflict checker). LOCAL paths only — URL inputs are CRITICAL errors bec

• cpv-batch-scope-fix

  Apply scope-aware doctor fixes across a fleet of project folders. One cpv-doctor-agent per project in batch_scope_fix mode handles the requested scope (user / project / local / full). Auto-applies NIT and CRITICAL fixes; reports MAJOR / MINOR fixes in pending_fixes[] for user approval. LOCAL paths o

• cpv-batch-security-audit

  Fleet-wide parallel security audit. Accepts local paths, GitHub URLs, marketplaces, lists, and @listfile shapes. One cpv-plugin-validator-agent per plugin runs ONLY validate_security (5 external scanners + AI/security rules). Use when checking supply-chain risk across many plugins. Trigger with /cpv

• cpv-batch-validate-and-fix

  Same-turn parallel validate-and-fix across a marketplace / list / single plugin. Each cpv-plugin-fixer-agent reads every source file ONCE — scans + verifies false positives (via v2.100.x AST/JSON/markdown classifier + llm-externalizer with file-range syntax) + fixes inline. ~3× cheaper per plugin th

• cpv-batch-validate

  Fleet-wide parallel validation. Accepts local paths, GitHub URLs, marketplaces, lists, and @listfile shapes. Dispatches one cpv-plugin-validator-agent per plugin (default 8 parallel, cap 16). Use when validating many plugins at once — e.g. every plugin in a marketplace. Trigger with /cpv-batch-valid

• cpv-bump-version

  Bump plugin version and run the full publish pipeline (plugin.json, pyproject.toml, README badge, CHANGELOG, push, release). Use when bumping version + publishing the current plugin via publish.py. Used dynamically via cpv-the-skills-menu (TRDD-478d9687).

• cpv-cache-validation-skill

  Validate plugins / projects against Anthropic's prompt-cache invalidation patterns (CA-01..CA-07). Use when auditing for cache regressions or fixing CA-01..CA-07 findings. Used dynamically via cpv-the-skills-menu (TRDD-478d9687).

• cpv-canonical-pipeline

  Standard files, CI/CD, hooks, and release pipeline for Emasoft Claude Code plugins. Use when creating or auditing plugin repos. Used dynamically via cpv-the-skills-menu — any CPV agent can invoke at runtime (TRDD-478d9687).

• cpv-create-micro-agents-workflow

  Build a ONE-FOR-ALL agent — every skill it needs is listed BY NAME, and each one runs in a SEPARATE subagent (a one-skill-agent with minimal context). Two paths - convert ONE existing agent in place, or generate a plugin-wide RLM launcher plus a TypeScript Workflow coordinator that decomposes a task

• cpv-create-mono-agent

  Build an ALL-IN-ONE agent — one agent that PRELOADS every skill it needs BY NAME in its `skills:` frontmatter and routes to each one from its own body, so it is ready from turn 1 with the whole set in its cached prefix. Works plugin-wide (every non-meta skill) or scoped to ONE existing agent's skill

• cpv-create-plugin

  Create Claude Code plugin or marketplace repos with full CI/CD. Use when scaffolding. Used via cpv-the-skills-menu.

• cpv-deterministic-codemod

  Deterministic codemod CLI — bulk-fix backtick-path to markdown-link, add TOC stubs, dedup blank lines, and other mechanical text transforms (issue 17). Zero LLM cost. Use when mechanical fixes outnumber semantic ones. Used dynamically via cpv-the-skills-menu (TRDD-478d9687).

• cpv-devitalize-threats

  Transformation catalog for converting flagged execution-class security findings into provably-inert data — so a plugin passes CPV's security gate by neutralizing the code's executable shape, never by suppressing a rule or relaxing --strict. Maps each threat shape (live os.system / subprocess(shell=T

• cpv-diagnose-plugin-architecture

  Advisory diagnostic that detects when a Claude Code plugin ships files not needed at runtime — build-only source, dependency trees, dev-only dirs, regenerable build caches — and recommends the existing CPV lean-separation. Use when the user asks 'is my plugin too big', 'what files ship', 'reduce ins

• cpv-evaluate-agent-variants

  Compare an ORIGINAL agent against any subset of its ALL-IN-ONE / ONE-FOR-ALL / PLUGIN-OMNI variants, in two strictly separated tiers — a static cost model that always runs with zero LLM calls, and an opt-in live A/B/C that records only REAL tokens, time and outcomes. Use when the question is whether

• cpv-fix-marketplace-validation

  Maps marketplace validation errors to fix reference files. Used dynamically via cpv-the-skills-menu — any CPV agent can invoke at runtime (TRDD-478d9687). Use when a marketplace validation report has CRITICAL/MAJOR/MINOR/NIT findings from validate_marketplace.py or validate_marketplace_pipeline.py.

• cpv-fix-validation

  Maps CPV validation errors to mechanical per-error fix guides. Use when looking up remediation steps for CRITICAL/MAJOR/MINOR/NIT findings. Architectural migrations are handled by cpv-migrate-marketplace-architecture. Used dynamically via cpv-the-skills-menu (TRDD-478d9687).

• cpv-harden-and-redact

  Catalog for fixing security-scan LEAK and MISSING-SAFEGUARD findings without loss of functionality — redacting secrets (runtime-reading the needed ones from env / GitHub vars / OS keychain) and implementing missing safeguards: safe config parsing, input sanitization, correct launch/deploy parameters

• cpv-link-plugin-marketplace

  Link an existing plugin to an existing marketplace (local or GitHub source). Use when appending an existing plugin to a marketplace.json. Used dynamically via cpv-the-skills-menu (TRDD-478d9687).

• cpv-main-menu-skill

  Routes the /cpv-main-menu Stop-hook menu via scripts/print_menu.py + claude-menu-system. Used dynamically via cpv-the-skills-menu (TRDD-478d9687) — used by the /cpv-main-menu flow. Use when navigating CPV's many commands via a single entry point.

• cpv-marketplace-authoring-contract

  Proactive marketplace.json authoring contract for plugin-touching agents. Use when drafting, modifying, or migrating any marketplace.json. Used dynamically via cpv-the-skills-menu (TRDD-478d9687). Use when drafting, modifying, or migrating any marketplace.json. Apply every sub-rule when emitting ent

• cpv-migrate-marketplace-architecture

  Convert a non-CPV marketplace between Layout A (hub-and-spoke), Layout B (nested-with-discipline), and Layout C (marketplace-in-plugin self-referential). Use when migrating marketplace architecture. Used dynamically via cpv-the-skills-menu (TRDD-478d9687). - marketplace - migration - architecture

• cpv-pack-components

  Pack a folder of standalone components (skill/agent/command/hook/mcp/lsp/monitor/output-style) into a new installable plugin. Use when bundling loose components into a single publishable plugin. Used dynamically via cpv-the-skills-menu (TRDD-478d9687).

• cpv-plugin-management

  Manage Claude Code plugins: install, validate, audit, enable, disable, search, doctor. Use when managing plugin lifecycle. Used dynamically via cpv-the-skills-menu (TRDD-478d9687).

• cpv-plugin-validation-skill

  Validates Claude Code plugins for structural correctness, quality, and marketplace readiness. Use when validating, fixing, migrating, upgrading, or scaffolding a plugin. Used dynamically via cpv-the-skills-menu (TRDD-478d9687). Embeds canonical plugins-reference.md.

• cpv-publish-to-marketplace

  Use when publishing a plugin to a GitHub-hosted marketplace. Used dynamically via cpv-the-skills-menu (TRDD-478d9687). - marketplace - publish - ci-cd - plugin

• cpv-refresh-readme

  Refresh AUTO-* marker blocks in a plugin's README (auto-detected components table). Use when the README's components list has drifted from the filesystem. Used dynamically via cpv-the-skills-menu (TRDD-478d9687).

• cpv-register-mcp

  Register a new MCP server in an existing plugin's .mcp.json (stdio default; supports HTTP transport via --http-url; cross-platform command via Python/Node). Use when adding a new MCP server entry. Used dynamically via cpv-the-skills-menu (TRDD-478d9687).

• cpv-scaffold-agent

  Scaffold a new agent in an existing plugin (creates agents/{NAME}.md with valid frontmatter that passes validate_plugin out of the box). Use when adding a single agent to an existing plugin. Used dynamically via cpv-the-skills-menu (TRDD-478d9687).

• cpv-scaffold-command

  Scaffold a new slash command in an existing plugin (creates commands/{NAME}.md with valid frontmatter that passes validate_plugin out of the box). Use when adding a single slash command to an existing plugin. Used dynamically via cpv-the-skills-menu (TRDD-478d9687).

• cpv-scaffold-skill

  Scaffold a new skill in an existing plugin (creates skills/{NAME}/SKILL.md with valid frontmatter that passes validate_plugin out of the box). Use when adding a single skill to an existing plugin. Used dynamically via cpv-the-skills-menu (TRDD-478d9687).

• cpv-semantic-validation-skill

  Deep AI semantic validation for skills/agents. Use when checking triggering, clarity, examples. Used dynamically via cpv-the-skills-menu (TRDD-478d9687). 10x token cost.

• cpv-setup-github-marketplace

  Use when creating a plugin marketplace or linking plugins to one. Used dynamically via cpv-the-skills-menu (TRDD-478d9687). - marketplace - github - ci-cd - automation - setup

• cpv-setup-marketplace-auto-notification

  Use when configuring a plugin to notify its marketplace after each release so Claude Code can auto-update users. Universal CI recipe for any plugin/marketplace pair. Used dynamically via cpv-the-skills-menu (TRDD-478d9687). - marketplace - notification - ci-cd - github-actions - release

• cpv-setup-plugin-repo

  Create and configure Claude Code plugin GitHub repositories with CI/CD, hooks, and marketplace notification. Use when setting up a new plugin repo. Used dynamically via cpv-the-skills-menu (TRDD-478d9687). - plugin - github - setup - ci-cd

• cpv-show-version

  Show the CPV management tools version. Use when reporting the installed CPV CLI version. Used dynamically via cpv-the-skills-menu (TRDD-478d9687).

• cpv-skill-validation-skill

  Validate skills using 190+ rules from AgentSkills OpenSpec, Nixtla, and Meta-Skill frameworks. Use when validating SKILL.md files or auditing skill quality. Used dynamically via cpv-the-skills-menu (TRDD-478d9687).

• cpv-standardize-plugin

  Audit and fix plugin/marketplace repos to match CPV standards. Use when standardizing or auditing repo structure. Used dynamically via cpv-the-skills-menu (TRDD-478d9687).

• cpv-strip-dev-submodules

  Move dev-only folders or compile source out of a plugin's MAIN repo into a SEPARATE repo referenced by pinned URL + SHA, so the installed plugin stops shipping them. Use when shrinking a plugin install before publishing, or when creating the PUBLIC compile-source repo the ship-only-binary canon requ

• cpv-the-skills-menu-create

  Convert any Claude Code plugin from static agent skill assignment to cpv-the-skills-menu method. Use when migrating a plugin so its agents load operational skills dynamically via the Skill() tool instead of preloading static lists. Trigger with /cpv-the-skills-menu-create or when the user asks to mi

• cpv-the-skills-menu

  Agent-facing à-la-carte menu of every claude-plugins-validation (CPV) skill, agent, and script: classifies a plugin-quality request — validate, security-scan, fix, cache-optimize, create, publish, marketplace, manage, semantic-grade — and routes it to the right tool. Use when a request mentions CPV,

• cpv-validate-plugin-folder

  READ-ONLY full scan of ONE plugin or skill folder — structure and rules, the full security pipeline, secret and sensitive-data leaks, and prompt-cache CA-01..CA-07 findings in a single pass. Nothing in the target is modified. Prints a severity table, the report path, and the exact agent that fixes e

• verification-before-completion

  Use when about to claim work is complete, fixed, or passing, before committing or creating PRs - requires running verification commands and confirming output before making any success claims; evidence before assertions always. Used dynamically via cpv-the-skills-menu, and attached to every agent con

Slash commands (14)

• /claude-plugins-validation:cpv-agent

  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

• /claude-plugins-validation:cpv-batch-caching-audit

  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 batch_audit mode (read-only — Phase 1 of the cache pipeline). Detects the seven prompt-cache-invalid

• /claude-plugins-validation:cpv-batch-caching-optimize

  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 batch_fix mode (Phase 1 audit + Phase 2 fix + Phase 3

• /claude-plugins-validation:cpv-batch-fix

  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). Accep

• /claude-plugins-validation:cpv-batch-full-scan-and-fix

  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

• /claude-plugins-validation:cpv-batch-scope-diagnose-and-fix

  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

• /claude-plugins-validation:cpv-batch-scope-diagnose

  Read-only diagnostic across a fleet of project folders. One cpv-doctor-agent per project diagnoses the requested scope — user (~/.claude/), project (<project>/.claude/), local (<project>/.claude/settings.local.json), or full (all three + cross-scope conflict checker). LOCAL paths only — URL inputs a

• /claude-plugins-validation:cpv-batch-scope-fix

  Apply fixes for scope-aware doctor findings across a fleet of project folders. One cpv-doctor-agent per project in batch_scope_fix 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,

• /claude-plugins-validation:cpv-batch-security-audit

  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 batch_security_audit) running only the security checker — five external scanners (cc-audit, tirith,

• /claude-plugins-validation:cpv-batch-validate-and-fix

  Same-turn validate-and-fix across a marketplace / list / single plugin. One cpv-plugin-fixer-agent per plugin scans + verifies false positives + fixes ALL findings in the same turn — each source file is READ ONCE, not the three times the separate validate → fix → re-validate cycle requires. Cuts per

• /claude-plugins-validation:cpv-batch-validate

  Fan out cpv-plugin-validator-agent agents across every plugin in a marketplace, a list of plugins, or a single plugin. Accepts local paths and GitHub URLs. One validator agent per plugin, dispatched in parallel from a single main-session message (default 8 at a time, cap 16). Returns one consolidate

• /claude-plugins-validation:cpv-main-menu

  Single entry point — Stop-hook menu of every CPV command/skill/agent (validate, fix, create, manage, GitHub, semantic-grade)

• /claude-plugins-validation:cpv-pre-install-scan

  Scan any skill / plugin / marketplace for security threats BEFORE installing it. Runs the MANDATORY native skillaudit scanner (50 rules / 486 patterns) + the full CPV security pipeline in a sandboxed tmp dir — never writes to ~/.claude/plugins/cache/. Use it before `claude plugin install`, before ad

• /claude-plugins-validation:cpv-the-skills-menu-create

  Migrate any Claude Code plugin to cpv-the-skills-menu method — agents declare only one preloaded skill (cpv-the-skills-menu) and pick operational skills dynamically via the Skill() tool instead of preloading static lists. Accepts a local plugin path, a Git URL, an owner/repo slug, a "plugin-in-marke

Subagents (14)

• cpv-agent

  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 <anything>" or "read the CPV skills menu and pick what is

• cpv-cache-optimizer-agent

  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 `<context>` block

• cpv-doctor-agent

  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 `<context>` block with the resolved `mode` and `target_path` and run

• cpv-marketplace-fixer-agent

  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 `<context>` block. Runs validate → fix → re-validate in a loop until the marketplace is clean (zero

• cpv-plugin-creator-agent

  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.

• cpv-plugin-devitalizer-agent

  Security devitalization WORK agent. Accepts a security report OR a plugin path via the dispatching menu's `<context>` 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 rel

• cpv-plugin-diagnoser-agent

  Deep diagnostic auditor for Claude Code plugins. Goes beyond validate_plugin (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 stru

• cpv-plugin-fixer-agent

  Self-sufficient fix WORK agent. Accepts a validation report OR a plugin path via the dispatching menu's `<context>` 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-ca

• cpv-plugin-leaks-preventer-agent

  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 (ru

• cpv-plugin-manager-agent

  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. - cpv-the-skills-men

• cpv-plugin-validator-agent

  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 summar

• cpv-semantic-validator-agent

  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). - cpv-the-skills-menu

• cpv-skill-validation-agent

  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

• cpv-spark-agent

  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

Similar plugins