cpv-batch-validate-and-fix

cpv-batch-validate-and-fix is a skill for Claude Code, Codex from Emasoft/claude-plugins-validation. It costs 125 tokens per session (1,308 once invoked), scanned A, original, MIT.

A parallel workflow that validates and repairs every plugin in a marketplace, list, or single-plugin input during one run. Each worker scans the source, checks uncertain findings, applies confirmed fixes, and performs a clean re-check.

In plain words
What is it for?
Use it when you want multiple plugins checked and corrected in the same turn, with write access to their source files.
Why use it?
Running validation, reviewing false positives, and fixing each plugin separately repeats file-reading and review work. This workflow combines those tasks while requiring confirmation before changing reported issues.

Skill for Claude CodeCodex

Part of the claude-plugins-validation plugin — 52 skills, 14 commands, 14 agents, 10 plugins shipped together

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

agentmods
npx agentmods add skills/emasoft/claude-plugins-validation/cpv-batch-validate-and-fix
Any agent
npx skills add Emasoft/claude-plugins-validation --skill cpv-batch-validate-and-fix
Clone the repo
git clone --depth 1 https://github.com/Emasoft/claude-plugins-validation

Made for: Claude Code, Codex.

Or install claude-plugins-validation, the plugin that ships this one along with the rest of its 52 skills, 14 commands, 14 agents, 10 plugins.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for cpv-batch-validate-and-fix

README.md
[![agentmods](https://agentmods.dev/badge/skills/emasoft/claude-plugins-validation/cpv-batch-validate-and-fix.svg)](https://agentmods.dev/skills/emasoft/claude-plugins-validation/cpv-batch-validate-and-fix)
Your own site
<a href="https://agentmods.dev/skills/emasoft/claude-plugins-validation/cpv-batch-validate-and-fix"><img src="https://agentmods.dev/badge/skills/emasoft/claude-plugins-validation/cpv-batch-validate-and-fix.svg" alt="Measured on agentmods" height="20"></a>
Per session 125 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,308 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5.1 $0.00125 $0.01308
Opus 5 $0.00063 $0.00654
Sonnet 5 $0.00025 $0.00262
Haiku 4.5 $0.00013 $0.00131

Measured 5d ago against content hash 8fd611be34e0, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-05, from the pricing page.

Security

Grade A, and why

cpv-batch-validate-and-fix scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 5d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

skills/cpv-batch-validate-and-fix/SKILL.md · 116 lines

How it starts

The opening of the file, as written. The whole thing — 116 lines — stays where its author put it; the contents beside it link to each section on GitHub.

cpv-batch-validate-and-fix

Overview

Same-turn variant of the parallel validate + fix pipeline. Each cpv-plugin-fixer-agent subagent reads every source file ONCE, scans + verifies FPs inline (via the v2.100.x context classifier + llm-externalizer with file-range syntax — minimum-token FP verification), applies confirmed-real fixes, and runs one clean-room re-check.

Same input grammar as cpv-batch-validate. The orchestrator body lives in this plugin's commands/cpv-batch-validate-and-fix.md slash-command file.

Prerequisites

  • claude-plugins-validation plugin installed (provides scripts/print_menu.py — the claude-menu-system bridge — and the cpv-plugin-fixer-agent agent).
  • claude-menu-system plugin installed — the slash command emits the status table via its Stop-hook (through scripts/print_menu.py). Declared as a hard dependency in CPV's plugin.json; print_menu.py fails fast with an install hint if missing (there is no inline fallback renderer — TRDD-4de479a0).
  • LLM Externalizer MCP available (it's the FP verifier for uncertain findings — without it the agent falls back to keeping the finding at the classifier's verdict).
  • Write access to every plugin's tree — this skill MUTATES source files in place.
  • For URL inputs: git on PATH and network access to github.com.

Inputs

See the cpv-batch-validate input table — every shape is supported identically.

Instructions

  1. Confirm the user wants the same-turn variant (faster, narrower visibility) vs the separate-pass pipeline (slower, more intermediate reports). When in doubt, route to cpv-batch-validate + cpv-batch-fix separately.
  2. Invoke the slash command body:
    /cpv-batch-validate-and-fix <user's spec> [--max-parallel N]
    
  3. Each per-plugin agent runs in batch_same_turn_validate_fix mode. The agent reads each source file ONCE, scans + verifies FPs + fixes inline, then runs the final clean-room re-check. The command aggregates the per-plugin status JSONs into a CMS-shaped status-table spec, queued via scripts/print_menu.py; the claude-menu-system Stop hook emits the Unicode-bordered table post-turn via systemMessage (zero token cost — never enters the agent transcript). NEVER print the table inline.
  4. The user gets the final status table (emitted by the Stop hook) + a one-line summary (DONE: plugins=N clean=X fixed=Y partial=Z failed=W. Total FPs verified: F).

Read the full file on GitHub · 116 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 5d ago First seen · 116 lines · 125 tokens per session scan A 8fd611be34e0

Subscribe to this mod's changes

cpv-batch-validate-and-fix is a skill published in the GitHub repository Emasoft/claude-plugins-validation (4 stars, last pushed yesterday), licensed MIT. It adds 125 tokens to every session and 1,308 once invoked, about $0.0006 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Related

Other skills, from other repositories

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

local-ai-agents

Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…

microsoft/ai-agents-for-beginners · 200 tokens

next-cache-components-adoption

Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…

vercel/next.js · 95 tokens

next-cache-components-optimizer

Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…

vercel/next.js · 170 tokens

next-partial-prefetching-adoption

Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…

vercel/next.js · 103 tokens

chronicle

Analyze Copilot session history for standup reports, usage tips, session search, and session reindexing. Use when the user asks for a standup, daily summary, usage tips, workflow recommendations, wants to search or find past sessions by keyword/file/PR, wants to reindex their session store, or asks about deleting…

microsoft/vscode · 72 tokens