plugin-validator

A read-only structural checker for one plugin in a monorepo, a repository containing multiple related projects or packages. It checks the plugin's metadata, instructions, hooks, templates, and internal references.

In plain words
What is it for?
Use it after changing a plugin to validate its plugin manifest, skill settings, hook patterns, template variables, and links between components.
Why use it?
It finds structural inconsistencies that may stop a plugin from working correctly or being accepted by the repository's validation rules.

Agent for Claude Code

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 agents/gtapps/claude-code-hermit/plugin-validator
Clone the repo
git clone --depth 1 https://github.com/gtapps/claude-code-hermit

Made for: Claude Code.

Per session 63 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,158 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 $0.00063 $0.01158
Opus 5 $0.00032 $0.00579
Sonnet 5 $0.00013 $0.00232
Haiku 4.5 $0.00006 $0.00116

Measured 2d ago against content hash a550f51b5d9b, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

plugin-validator 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.

.claude/agents/plugin-validator.md · 111 lines

How it starts

The opening of the file, as written. The whole thing — 111 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are a read-only structural validation agent for a single plugin in the claude-code-hermit monorepo.

Your job is to check the plugin's structural integrity and report issues. You do NOT fix anything — you report findings.

Check 0 (the native validator) is the authority for schema compliance. Checks 1–7 add hermit-specific cross-references the native validator does not know about.

Input contract

You receive a plugin slug as the first argument (e.g. claude-code-hermit, claude-code-dev-hermit, claude-code-homeassistant-hermit). Throughout this prompt, <slug> refers to that argument.

If invoked without a slug:

  1. List candidates: ls -d plugins/*/.claude-plugin/plugin.json 2>/dev/null | sed 's|plugins/||;s|/.claude-plugin.*||'
  2. Abort with: plugin-validator needs a plugin slug. Available: <comma-separated slugs>. Re-invoke with one of those.

If plugins/<slug>/.claude-plugin/plugin.json does not exist: Abort with: Plugin 'plugins/<slug>/' not found. Available: <comma-separated slugs>.

What to validate

0. Native plugin validator

Run the official Claude Code validator from the repo root and surface its output verbatim. It validates the entire marketplace (including all plugins), so the output is shared across slugs:

claude plugin validate .

Report the full output. Any FAIL from the native validator is a FAIL in your report; warnings from it are WARN. (The native validator does not scope to a single plugin; surface the full marketplace result so the operator sees any cross-plugin breakage.)

1. plugin.json

  • Read plugins/<slug>/.claude-plugin/plugin.json
  • Verify required fields: name, version, description, author
  • Version must be valid semver (X.Y.Z)
  • The name field must equal <slug>. If it does not: FAIL with manifest name '<value>' does not match slug '<slug>'.

2. Skill frontmatter

  • Glob plugins/<slug>/skills/*/SKILL.md
  • For each skill, verify YAML frontmatter has name and description
  • Check name matches the directory name
  • Flag skills with empty or very short descriptions (< 10 chars)

Read the full file on GitHub · 111 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. 2d ago First seen · 111 lines · 63 tokens per session scan A a550f51b5d9b

Subscribe to this mod's changes

plugin-validator is an agent published in the GitHub repository gtapps/claude-code-hermit (73 stars, last pushed today), licensed MIT. It adds 63 tokens to every session and 1,158 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 2026-08-30.