Getting it into your agent
There is no command for this one: it runs only inside a plugin, and the catalogue could not identify which plugin ships it. The source is linked below.
Wrote 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/moonlight-lupin/agent-skills/claude-plugin-converter)<a href="https://agentmods.dev/skills/moonlight-lupin/agent-skills/claude-plugin-converter"><img src="https://agentmods.dev/badge/skills/moonlight-lupin/agent-skills/claude-plugin-converter/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/skills/moonlight-lupin/agent-skills/claude-plugin-converter"><img src="https://agentmods.dev/badge/skills/moonlight-lupin/agent-skills/claude-plugin-converter.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 | $0.00021 | $0.03457 |
| Opus 5 | $0.00010 | $0.01729 |
| Sonnet 5 | $0.00004 | $0.00691 |
| Haiku 4.5 | $0.00002 | $0.00346 |
Grade A, and why
claude-plugin-converter scanned grade A with 1 finding 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 11d 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.
Runs shell commandslowCapability
Expected in a hook, worth knowing in a rule or an instructions file.
**Only convert plugins from sources you trust.** The converter reads shell commands, Python hooks, and MCP server configurations from the source plugin and reproduces them in the Hermes output. Converted hooks may execut How it starts
The opening of the file, as written. The whole thing — 246 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Claude Plugin Converter
Convert a Claude Code plugin (.claude-plugin/plugin.json manifest + components) into a self-contained, installable Hermes plugin (plugin.yaml + __init__.py + bundled skills/hooks).
When to Use
- User wants to use a Claude Code plugin with Hermes Agent
- User says "convert this Claude plugin" or "make this work with Hermes"
- User provides a Claude plugin directory, git URL, or marketplace reference
Overview
Two-phase workflow:
- Discovery — analyze the Claude plugin, report what can/can't be converted
- Conversion — generate a complete Hermes plugin directory the user can install with
hermes plugins enable <name>
The output is a single self-contained Hermes plugin — skills, hooks, and MCP config all bundled inside one ~/.hermes/plugins/<name>/ directory. Not scattered artifacts.
⚠️ Security & Trust Boundary
Only convert plugins from sources you trust. The converter reads shell commands, Python hooks, and MCP server configurations from the source plugin and reproduces them in the Hermes output. Converted hooks may execute shell commands from the source plugin via subprocess.run(..., shell=True, ...).
Before enabling a converted plugin:
- Review
hooks.py— inspect everysubprocess.runcall and_CMD_*variable for dangerous commands - Review
__init__.py— check what's registered (tools, hooks, slash commands) - Review
mcp_config.yaml— verify MCP server commands and env vars are safe - Review
MANUAL_STEPS.md— understand what the converter couldn't automate
Do not blindly convert and enable plugins from untrusted GitHub repos or marketplaces without reviewing the generated output first.
Phase 1: Discovery
Run the analysis script:
python3 {SKILL_DIR}/scripts/analyze.py <claude_plugin_dir> --output <output_dir>/analysis.json
The script reads .claude-plugin/plugin.json and all component directories, producing structured JSON with convertibility assessments for each component.
What ships with it
4 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.
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.
- 11d ago First seen · 246 lines · 21 tokens per session scan A b361025f9f50
claude-plugin-converter is a skill published in the GitHub repository moonlight-lupin/agent-skills (62 stars, last pushed 4d ago), licensed MIT. It adds 21 tokens to every session and 3,457 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it A with 1 finding (runs shell commands). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
SoloFlow
A meta-skill that silently watches your workflows and automatically generates reusable Hermes skills from them.
hermes-tweet
Use Xquik in Hermes Agent for public X research, monitoring, thread summaries, creator discovery & approved actions. Not affiliated with X Corp. Use when the user requests X data or a named action. Trigger with "search X", "monitor X", "post tweet", or "X trends".
image
Create or optimize marketing images, social graphics, product mockups, banners, cover art, listing visuals, brand assets, image prompts, WebP files, and OG images.
video
Plan and produce video with available AI tools or programmatic frameworks. Use for video prompts, avatars, explainers, demos, templates, pipelines, and generation.
content-research-writer
Research, outline, draft, cite, and revise articles, reports, tutorials, newsletters, and case studies with traceable sources and preserved voice.
content-analysis
Analyze articles, documents, videos, podcasts, and transcripts for arguments, evidence, themes, assumptions, contradictions, insights, and unanswered questions.