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.
npx agentmods add commands/emasoft/claude-plugins-validation/cpv-pre-install-scangit clone --depth 1 https://github.com/Emasoft/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-pre-install-scan)<a href="https://agentmods.dev/commands/emasoft/claude-plugins-validation/cpv-pre-install-scan"><img src="https://agentmods.dev/badge/commands/emasoft/claude-plugins-validation/cpv-pre-install-scan.svg" alt="Measured on agentmods" 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 | $0.00088 | $0.00834 |
| Opus 5 | $0.00044 | $0.00417 |
| Sonnet 5 | $0.00018 | $0.00167 |
| Haiku 4.5 | $0.00009 | $0.00083 |
Grade A, and why
cpv-pre-install-scan 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 4d 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 — 82 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/cpv-pre-install-scan
Pre-install security gate. Scans an untrusted skill, plugin, or
marketplace before it lands in ~/.claude/plugins/cache/.
What it scans
The scanner runs all of:
- The full CPV security pipeline (27 in-process checks + 5 external scanners when available)
- The MANDATORY native skillaudit rule catalog (50 rules / 486 patterns across 21 threat categories — credential theft, data exfiltration, prompt injection, MCP schema poisoning, A2A attacks, obfuscation, supply-chain, container escape, persistence, crypto theft, etc.)
- Invisible-Unicode / bidi-override detection
- Base64 + hex + Unicode-escape + char-code obfuscation decoders
- Hardcoded-secret detection (GitHub/AWS/Slack/Discord/Telegram/Vercel/npm/PyPI/OpenAI/Anthropic/Google/Stripe tokens, PEM keys, JWTs)
How it works
cpv-pre-install-scan <target>
The target is fetched into ${TMPDIR}/cpv-preinstall-<uuid>/ — a
sandboxed work directory. The scanner runs read-only static
analysis. No target code is executed. When the scan completes
the sandbox is deleted.
Accepted target forms:
| Form | Example |
|---|---|
| Local path | cpv-pre-install-scan /path/to/plugin |
| GitHub URL | cpv-pre-install-scan https://github.com/owner/repo |
| owner/repo slug | cpv-pre-install-scan owner/repo |
| Release URL | cpv-pre-install-scan https://github.com/owner/repo/releases/tag/v1.2.3 |
| Single file URL | cpv-pre-install-scan https://example.com/SKILL.md |
| Local archive | cpv-pre-install-scan plugin.tar.gz |
Exit codes
0— clean. Zero CRITICAL, zero MAJOR findings. Safe to install.1— findings. CRITICAL or MAJOR present. Do NOT install.2— usage error (bad target, fetch failure, etc.).
Iron rule
The skillaudit native scanner runs on EVERY pre-install scan. There
is no CPV_NO_SKILLAUDIT, no --skip-skillaudit, no opt-out. A
missing rule catalog is reported as CRITICAL.
When uncertain matches are detected (e.g. shell-keyword substring in documentation), the scanner DEMOTES them to NIT-level "⚠ (demoted, needs review)" findings instead of silently suppressing them — the downstream security agents triage these for verification.
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.
- 4d ago First seen · 82 lines · 88 tokens per session scan A 26e2847eaece
cpv-pre-install-scan is a command published in the GitHub repository Emasoft/claude-plugins-validation (4 stars, last pushed 2d ago), licensed MIT. It adds 88 tokens to every session and 834 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.
Other commands, from other repositories
git
Git operations with intelligent commit messages and workflow optimization.
checklist
Generate a custom checklist for the current feature based on user requirements.
clarify
Identify underspecified areas in the current feature spec by asking up to 5 highly targeted clarification questions and encoding answers back into the spec.
specify
Create or update the feature specification from a natural language feature description.
analyze
Perform a non-destructive cross-artifact consistency and quality analysis across spec.md, plan.md, and tasks.md after task generation.
converge
Assess the current codebase against the feature's spec, plan, and tasks, then append any remaining unbuilt work as new tasks to tasks.md so implement can complete it.