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 instructions/mathisk2095/jko-claude-plugins/claude-mdgit clone --depth 1 https://github.com/mathisk2095/jko-claude-pluginsWrote 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/instructions/mathisk2095/jko-claude-plugins/claude-md)<a href="https://agentmods.dev/instructions/mathisk2095/jko-claude-plugins/claude-md"><img src="https://agentmods.dev/badge/instructions/mathisk2095/jko-claude-plugins/claude-md.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 | $0.00531 | $0.00531 |
| Opus 5 | $0.00266 | $0.00266 |
| Sonnet 5 | $0.00106 | $0.00106 |
| Haiku 4.5 | $0.00053 | $0.00053 |
Grade A, and why
jko-claude-plugins CLAUDE.md 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 — 58 lines — stays where its author put it; the contents beside it link to each section on GitHub.
jko-claude-plugins
Multi-CLI plugin marketplace with specialized skills and commands.
Project Structure
myClaudeSkills/
├── .github/plugin/marketplace.json # GitHub Copilot CLI marketplace manifest
├── .claude-plugin/marketplace.json # Claude Code marketplace manifest
├── plugins/
│ ├── swiftui/ # SwiftUI expert plugin
│ ├── rust/ # Rust expert plugin
│ ├── esp32-cpp/ # ESP32 C++ firmware plugin
│ ├── python-backend/ # Python backend plugin
│ ├── dotnet-backend/ # .NET backend plugin
│ └── dead-code/ # Dead code detection plugin
Installing This Marketplace
# Register as a marketplace for local development
claude plugin marketplace add /Users/john/Repos/myClaudeSkills
# Then install any plugin from the local checkout
claude plugin install <plugin-name>@jko-claude-plugins
After publishing or updating the GitHub-hosted marketplace, end users should use:
claude plugin marketplace add johnkozaris/jko-claude-plugins
claude plugin install <plugin-name>@jko-claude-plugins
Or load a single plugin for one session:
claude --plugin-dir /Users/john/Repos/myClaudeSkills/plugins/<plugin-name>
Local Iteration
- In Claude Code, run
/reload-pluginsafter installing, enabling, disabling, or updating plugins in the current session. - In GitHub Copilot CLI, reinstall a local plugin after edits because installed plugins are cached.
Conventions
- Plugin names: kebab-case
- Keep GitHub Copilot CLI component paths in
.github/plugin/plugin.json; when both manifest styles exist, Copilot reads the.github/plugin/*manifests. - Keep
.claude-plugin/plugin.jsonmetadata-only unless Claude needs non-default paths; Claude Code can use default discovery forskills/,commands/, andhooks/without duplicating those component paths. - One type per file in skills
- Skills: lean SKILL.md (1,500-2,000 words), detailed references/ on-demand
- Commands: instructions FOR Claude, not messages to user
- Always use
${CLAUDE_PLUGIN_ROOT}for portable paths - Skill descriptions: third-person with specific trigger phrases
- Skill bodies: imperative form (verb-first)
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 · 58 lines · 531 tokens per session scan A 42307e183653
jko-claude-plugins CLAUDE.md is an instructions file published in the GitHub repository mathisk2095/jko-claude-plugins (3 stars, last pushed 6d ago), licensed MIT. It adds 531 tokens to every session, about $0.0027 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 instructions, from other repositories
jko-claude-plugins CLAUDE.md
Claude Code instructions for johnkozaris/jko-claude-plugins, covering jko-skills, project structure, installing this marketplace, register as a marketplace for local development and then install any plugin from the local checkout.
director-mode-lite copilot-instructions.md
Copilot instructions for claude-world/director-mode-lite: This is a Shell/Markdown toolkit for Claude Code Director Mode. Keep shell scripts POSIX-compatible where possible. Markdown files are the primary deliverable.
cc-thingz AGENTS.md
AGENTS.md instructions for alexei-led/cc-thingz, covering cc-thingz — coding companion, build, writing agent/skill instructions, agents and platform coverage.
openalgo-claude-plugin CLAUDE.md
Instructions for marketcalls/openalgo-claude-plugin, covering openalgo marketplace - claude code plugin marketplace, repository structure, philosophy: unified trading api for indian markets, working with this repository and adding a new skill.
cc-thingz CLAUDE.md
Claude Code instructions for alexei-led/cc-thingz, a project described as: Portable skills, agents, hooks, and Pi extensions for Claude Code, Codex CLI, Copilot, Cursor, Grok, and Pi.
vscode buildNext.instructions.md
Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).