cpv-agent

A direct command for sending a free-form Claude Code plugin request to a general CPV worker. CPV is a toolkit for checking, fixing, creating, publishing, and managing plugins.

In plain words
What is it for?
Use it for plugin-quality tasks such as validation, security scanning, fixes, cache optimization, creation, publishing, marketplace migration, or installed-plugin management.
Why use it?
It removes the need to choose the right specialized tool yourself. The worker interprets the request and routes it to the relevant workflow.

Command

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 commands/emasoft/claude-plugins-validation/cpv-agent
Clone the repo
git clone --depth 1 https://github.com/Emasoft/claude-plugins-validation
Per session 73 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 504 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 $0.00073 $0.00504
Opus 5 $0.00036 $0.00252
Sonnet 5 $0.00015 $0.00101
Haiku 4.5 $0.00007 $0.00050

Measured 2d ago against content hash 7ee4b8648b12, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

cpv-agent 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 2d 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.

commands/cpv-agent.md · 38 lines

What it actually says

/cpv-agent — free-form CPV worker (direct dispatch)

$ARGUMENTS is a free-form plugin-quality request. Hand it verbatim to the claude-plugins-validation:cpv-agent subagent, which reads the intent-to-action map in cpv-the-skills-menu and autonomously routes the request to the right CPV skill, agent, or script, running the whole job in its own isolated context (so the verbose per-file work never enters this session).

This is the direct-slash shortcut to the same worker the main menu reaches via its A — Ask the agent row. Use it when you already know you want the CPV agent and do not want to open the menu first.

Workflow

  1. If $ARGUMENTS is empty, ask the user what CPV task they want, then stop.
  2. Otherwise dispatch ONE claude-plugins-validation:cpv-agent subagent via the Agent tool, passing $ARGUMENTS as the task. The default target is the current plugin unless the request names another path or GitHub URL. For substantive or multi-file work the subagent may itself fan out to specialised CPV work agents (cpv-plugin-fixer-agent, cpv-cache-optimizer-agent, and the like).
  3. Relay the subagent's final one-line result and the path to the report it wrote under reports/.

Notes

  • The cpv-agent subagent is also dispatchable directly by other agents as subagent_type: claude-plugins-validation:cpv-agent — this command only adds the user-facing /cpv-agent slash surface on top of that existing agent.
  • For one bounded edit prefer cpv-spark-agent; for an interactive numbered menu use /cpv-main-menu.
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. 2d ago First seen · 38 lines · 73 tokens per session scan A 7ee4b8648b12

Subscribe to this mod's changes

cpv-agent is a command published in the GitHub repository Emasoft/claude-plugins-validation (4 stars, last pushed 4d ago), licensed MIT. It adds 73 tokens to every session and 504 once invoked, about $0.0004 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.