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 skills add paulbaranowski/wild-horses --skill creategit clone --depth 1 https://github.com/paulbaranowski/wild-horsesWrote 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/paulbaranowski/wild-horses/create)<a href="https://agentmods.dev/skills/paulbaranowski/wild-horses/create"><img src="https://agentmods.dev/badge/skills/paulbaranowski/wild-horses/create.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 5.1 | $0.00053 | $0.02897 |
| Opus 5 | $0.00026 | $0.01448 |
| Sonnet 5 | $0.00011 | $0.00579 |
| Haiku 4.5 | $0.00005 | $0.00290 |
Grade A, and why
create scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 8d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 280 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Create a Claude Code Plugin Marketplace
Scaffold a complete Claude Code plugin marketplace in the current repository.
Arguments: "$ARGUMENTS"
Phase 1: Gather Information (you do this — interactive)
Step 1: Marketplace name
If a marketplace name was provided in $ARGUMENTS, use it. Otherwise, ask the user:
What would you like to name your marketplace? (This becomes the brand in install commands, e.g.
/plugin install my-plugin@<marketplace-name>)
Normalize the name: lowercase, hyphen-separated, no spaces. If you had to normalize it, tell the user what you changed.
Step 2: Owner name
Check git config for user.name. If not available, ask the user.
Step 3: Existing skill to import?
Ask the user:
Do you have an existing SKILL.md or plugin you'd like to import into this marketplace?
- If yes, provide the path to the skill or plugin directory
- If no, I'll create an empty marketplace you can add plugins to later
If the user provides a path:
- Read the file/directory at that path
- If it's a SKILL.md, extract the skill name and description from frontmatter
- If it's a plugin directory (has
.claude-plugin/plugin.json), read the plugin manifest - Use this information to create the first plugin entry in the marketplace
- Copy or reference the skill into the proper
plugins/<name>/skills/<name>/structure
If the user says no (or skips):
- Create an empty marketplace with no plugins — the
pluginsarray in marketplace.json will be empty
Step 4: Check for conflicts
Before creating anything:
- If
.claude-plugin/marketplace.jsonalready exists, warn the user and ask if they want to overwrite or abort - If
CLAUDE.mdalready exists, tell the user you'll append marketplace conventions rather than overwrite
Step 5: Confirm the plan
Present a summary and ask for confirmation:
Marketplace: <name>
Owner: <owner>
Import: <skill/plugin name or "none — empty marketplace">
Files to create:
.claude-plugin/marketplace.json
CLAUDE.md (create or append)
plugins/<plugin-name>/... (only if importing a skill)
What ships with it
1 file 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.
- 8d ago First seen · 280 lines · 53 tokens per session scan A 7ae6e2968f50
create is a skill published in the GitHub repository paulbaranowski/wild-horses (11 stars, last pushed 20d ago), licensed MIT. It adds 53 tokens to every session and 2,897 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.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…
next-partial-prefetching-adoption
Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…
chronicle
Analyze Copilot session history for standup reports, usage tips, session search, and session reindexing. Use when the user asks for a standup, daily summary, usage tips, workflow recommendations, wants to search or find past sessions by keyword/file/PR, wants to reindex their session store, or asks about deleting…