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 skills/emasoft/claude-plugins-validation/cpv-semantic-validation-skillnpx skills add Emasoft/claude-plugins-validation --skill cpv-semantic-validation-skillgit 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/skills/emasoft/claude-plugins-validation/cpv-semantic-validation-skill)<a href="https://agentmods.dev/skills/emasoft/claude-plugins-validation/cpv-semantic-validation-skill"><img src="https://agentmods.dev/badge/skills/emasoft/claude-plugins-validation/cpv-semantic-validation-skill.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 | $0.00050 | $0.01250 |
| Opus 5 | $0.00025 | $0.00625 |
| Sonnet 5 | $0.00010 | $0.00250 |
| Haiku 4.5 | $0.00005 | $0.00125 |
Grade A, and why
cpv-semantic-validation-skill 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 yesterday.
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 — 126 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Semantic Validation Skill
Deep AI analysis. Opus 1M, ~10-50× tokens of script validation.
Overview
7 quality pillars + 3 conditional security pillars → Semantic Grade (A-F).
HARD SEPARATION — USER CHOICE. Programmatic (/cpv-validate-plugin, 0 tokens) catches 95%+ via regex and surfaces CANDIDATES via INFO — never escalates. Semantic (this skill, opt-in via /cpv-semantic-validation, thousands–millions tokens) handles the 5% residue: ambiguous injection, shadow features, subtle MCP-description injection. Most projects publish-ready with programmatic alone. Never default-on.
Prerequisites
- Python 3.12+ with
pyyaml,uvpackage manager, target skill/agent path
Instructions
- Run baseline via launcher (alias
skill) — see references/launcher-invocation.md. Direct invocation refused.The one-liner · Why the launcher is mandatory · Direct invocation (development only)
- Read SKILL.md / agent .md
- Evaluate 7 pillars + applicable conditional security pillars
- Write report →
$MAIN_ROOT/reports/cpv-semantic-validator-agent/<YYYYMMDD_HHMMSS±HHMM>-<slug>.md - Return
[DONE] Grade: X. Report: <filepath>
Output
- Grade: A-F. Criteria: Pass/Partial/Fail per pillar. Report:
$MAIN_ROOT/reports/cpv-semantic-validator-agent/<ts±tz>-<slug>.md. Bothreports/andreports_dev/gitignored.
Error Handling
- If script validation fails CRITICAL → semantic skipped. Fix structure first.
- Invalid path → report error, exit.
Examples
/cpv-semantic-validation ./skills/my-skill/
/cpv-semantic-validation ./agents/my-agent.md
Token Optimization
Opt-in only. Baseline first. Write report to disk; return grade + filepath.
Conditional Pillar: Channel MCP Server Source-Code Security
Runs only when plugin.json.channels is non-empty AND plugin ships MCP server source.
Load channel-source-security:
- Why This Pillar Exists
- Scope
- Source-Language Support
- Deterministic Prefilter Helper
- Rule 1 — Inbound Sender Gating (CRITICAL)
- Rule 2 — Permission-Relay Capability Gate (CRITICAL)
- Rule 3 — Room/Chat-ID-Only Gating (MAJOR)
- Rule 4 — PASSED
- Opus Prompt Template
- Integration With the A-F Rubric
- Report Format
What ships with it
7 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
- references/agent-rule-checks.md 30 KB
- references/channel-source-security.md 16 KB
- references/concealment-and-multilingual-rules.md 7.5 KB
- references/exfil-and-autonomy-rules.md 5.0 KB
- references/launcher-invocation.md 1.7 KB
- references/mcp-and-capability-rules.md 5.1 KB
- references/prompt-injection-rules.md 10 KB
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.
- yesterday First seen · 126 lines · 50 tokens per session scan A 2c5a07002446
cpv-semantic-validation-skill is a skill published in the GitHub repository Emasoft/claude-plugins-validation (4 stars, last pushed 2d ago), licensed MIT. It adds 50 tokens to every session and 1,250 once invoked, about $0.0003 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 2026-09-03.
Other skills, from other repositories
skill-authoring
Guide creating Claude Code skills with TDD and persuasion principles. Use for new skill development.
plugin-review
Review plugin quality with tiered checks and dependency scoping. Use for PR and pre-release audits.
aap-lint
Skill "aap-lint" from automateyournetwork/netclaw, covering ansible lint operations, mcp server, available tools (9), key concepts and workflow: pre-deployment playbook validation.
doctor
OrchestKit doctor for health diagnostics across manifest integrity, hook configuration, skill validation, agent frontmatter, MCP server connectivity, CC version compatibility, and permission rules. Reports issues with severity levels and auto-remediation suggestions. Validates component counts, detects orphaned…
skill-author
Package and validate an existing skill draft for AutoVault when its frontmatter, resources, capabilities, or admission result need review.
doc-claim-validator
Validate that claims in documentation match codebase reality. Extracts verifiable assertions (file paths, commands, function references, behavioral claims, dependencies) from markdown docs and checks them against the actual project. Use after code changes, before releases, or when docs feel untrustworthy.