Getting it into your agent
This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.
/plugin marketplace add Emasoft/claude-plugins-validation/plugin install claude-plugins-validationWrote 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.
[](https://agentmods.dev/commands/emasoft/claude-plugins-validation/cpv-batch-validate)<a href="https://agentmods.dev/commands/emasoft/claude-plugins-validation/cpv-batch-validate"><img src="https://agentmods.dev/badge/commands/emasoft/claude-plugins-validation/cpv-batch-validate/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/commands/emasoft/claude-plugins-validation/cpv-batch-validate"><img src="https://agentmods.dev/badge/commands/emasoft/claude-plugins-validation/cpv-batch-validate.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00078 | $0.02593 |
| Opus 5.5 | $0.00031 | $0.01037 |
| Sonnet 5.5 | $0.00016 | $0.00519 |
| Haiku 4.5 | $0.00008 | $0.00259 |
Grade A, and why
cpv-batch-validate 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 1mo 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.
How it starts
The opening of the file, as written. The whole thing — 273 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/cpv-batch-validate — Validate every plugin in a marketplace, in parallel
For users who manage a fleet of plugins (a marketplace, a list of
project folders, or a Git org), /cpv-validate-plugin on each one
in turn is slow AND quietly burns context every time the user
re-loads the same handful of validators. /cpv-batch-validate
delegates each plugin to its own cpv-plugin-validator-agent subagent in
parallel — one fresh haiku context per plugin, all dispatched
from a single main-session message. Total main-session cost is
~3-4K tokens for any batch size; per-plugin work happens out-of-band
in the subagent contexts.
Input grammar (TRDD-3dcbb37c §1):
| Shape | Example |
|---|---|
| Single plugin (local) | ./my-plugin |
| Single plugin (URL) | https://github.com/owner/plugin or owner/plugin |
| Marketplace (local) | ./marketplace-root |
| Marketplace (URL) | https://github.com/owner/marketplace-repo |
| List on CLI | ./a ./b ./c (whitespace-separated) |
| List in file | @/tmp/inputs.txt (one spec per line, # comments OK) |
| Comma-separated | ./a,./b,./c |
URL inputs are cloned into ${TMPDIR}/cpv-batch-input-<uuid>/;
marketplace inputs enumerate .claude-plugin/marketplace.json and
clone every plugin referenced. All temp clones are cleaned up
automatically when the batch finishes.
You are the orchestrator
You — the model running THIS turn — orchestrate the batch from the
main session. You do NOT validate anything yourself. You delegate to
N parallel cpv-plugin-validator-agent subagents via the Agent tool, each in
batch_validate mode.
Critical rules:
- NEVER scan plugin contents yourself. Even if the resolver surfaces 17 plugins, you read ZERO source files.
- NEVER print findings inline. The agents write per-plugin status JSONs; the orchestrator just aggregates them into a status table.
- NEVER use
AskUserQuestion. Plain-text prompts only.
Step 0 — Resolve arguments
The user supplies:
- A target spec (required; first positional argument — accepts every shape from the table above).
- Optional
--max-parallel N(default 8, cap 16).
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.
- 1mo ago First seen · 273 lines · 78 tokens per session scan A b7b5b0617247
cpv-batch-validate is a command published in the GitHub repository Emasoft/claude-plugins-validation (4 stars, last pushed 3d ago), licensed MIT. It adds 78 tokens to every session and 2,593 once invoked, about $0.0003 per session on Opus 5.5. 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.
Other commands, from other repositories
prototype
You are building a proof-of-concept for the current Grainulator sprint. Read CLAUDE.md for sprint context and claims.json for existing research claims.
qa-changes
This skill should be used when the user asks to "QA a pull request", "test PR changes", "verify a PR works", "functionally test changes", or when an automated workflow triggers QA validation of code changes. Provides a structured methodology for setting up the environment, exercising changed behavior, and reporting…
verify
Run repository verification using the verification-loop skill.
constraints
A command for defining a project's quality standards through a short interview and a written CONSTRAINTS.md file. It records checks, thresholds, exceptions, and commands for enforcing them.
modernize-transform
Transform one legacy module to the target stack — idiomatic rewrite with behavior-equivalence tests.
test-coverage
Analyze test coverage and identify the highest-value gaps to fill.