Skip to main content
command CX Codex

certify — Claude Code command: quality certification with a badge

Runs PluginEval at deep depth and hands a quality badge to a skill or plugin directory.

Install into Claude Code · Plugin marketplace All methods and platforms ↓
/plugin marketplace add wshobson/agents
/plugin install plugin-eval@claude-code-workflows
Open on GitHub

What certify does

certify runs PluginEval at deep depth and assigns a quality badge. Point it at a skill directory and deep depth covers the static layer plus the experimental LLM judge and Monte Carlo layers. Point it at a plugin directory and only the static layer runs.

That split matters for your quota. A skill costs 55 model calls on your Max plan. A plugin directory costs none.

Run it from plugins/plugin-eval: uv run plugin-eval certify {argument} --output markdown. The path argument is required, so a bare call fails. You also need uv on the machine.

What it helps with

  • badge a skill after a deep quality pass
  • run static analysis on a plugin directory without spending model calls
  • produce a PluginEval report as markdown
  • keep skill checks and plugin checks apart so quota lasts

Example prompts for the agent

  • Run certify on the skills/my-skill directory
  • Certify the plugin in plugins/my-plugin and output markdown
  • Do a deep pass on this skill and assign the badge

How to install certify

1Plugin marketplace

/plugin marketplace add wshobson/agents
/plugin install plugin-eval@claude-code-workflows

2Manually: put the files in place

.claude/commands/certify.md

Call it with /certify. For all projects use ~/.claude/commands/

Questions about certify

How do I install certify in Claude Code?

Add the marketplace with /plugin marketplace add wshobson/agents, then install the plugin with /plugin install plugin-eval@claude-code-workflows. The command file lands at .claude/commands/certify.md.

What does certify do?

It runs PluginEval at deep depth and assigns a quality badge. Skills get the static layer plus the LLM judge and Monte Carlo layers; plugin directories get static only.

How many model calls does a certification take?

A skill directory makes 55 model calls through your Max plan. A plugin directory makes none.

Source text

certify.md · MIT
---
description: Full quality certification with badge
argument-hint: <path>
---

Run PluginEval at deep depth and assign a quality badge. For a skill directory, deep depth runs the static layer plus the experimental LLM judge and Monte Carlo layers. For a plugin directory, only the static layer runs.

For a skill, this makes 55 model calls through your Max plan. For a plugin directory, it makes none.

## Running

```bash
cd plugins/plugin-eval
uv run plugin-eval certify {argument} --output markdown
```

© Seth Hobson · MIT · wshobson/agents

Similar slash commands

All slash commands for Agent setup: memory, context, orchestration →

From the same set432

The whole set →
python-scaffold This command builds a Python project skeleton for FastAPI, Django, a library, or a CLI. Use it when the project needs uv, type hints, tests, and development tooling. CX Codex ★ 41,823repo stars verify-receipt Checks an Ed25519-signed receipt and reports whether its contents still match the signature. Use it for a single protect-mcp receipt file. CX Codex ★ 41,823repo stars audit-chain Checks the Ed25519 signature on every receipt in receipts.jsonl and reports the lines that fail. Useful before a release or a security audit. CX Codex ★ 41,823repo stars eval Evaluates a plugin or skill directory using static checks and an LLM judge. Spots anti-patterns and scores quality up to 100 points. CX Codex ★ 41,823repo stars ai-review This AI-assisted command reviews diffs for security, performance, architecture, and testing issues. Use it when a pull request needs structured feedback. CX Codex ★ 41,823repo stars slo-implement This command helps define SLOs, choose SLIs, set error budgets, and plan burn-rate alerts. Use it when a service needs measurable reliability targets. CX Codex ★ 41,823repo stars monitor-setup A slash command that scaffolds Prometheus metrics, Grafana dashboards, distributed tracing and log aggregation for your service. CX Codex ★ 41,823repo stars multi-platform Orchestrates cross-platform feature work across web, mobile, and desktop environments. It structures API contracts, design systems, and shared logic through dedicated subagents. CX Codex ★ 41,823repo stars

Project sponsors

Companies that keep this analytics open
Gold sponsor

Impressions, clicks and code copies — open statistics. We keep the numbers public for the same reason NeBlask itself is public. Become a sponsor