What is wild-horses CLAUDE.md?

A set of project instructions for maintaining Wild Horses, a Claude Code plugin marketplace that catalogs and distributes coding-agent plugins.

Use it when adding or changing marketplace entries, plugins, commands, or skills, including the matching Cursor marketplace files.

It gives agents the repository structure, required files, validation rules, and links to the relevant Claude Code documentation.

How paulbaranowski/wild-horses configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to paulbaranowski/wild-horses. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file

curl -O https://raw.githubusercontent.com/paulbaranowski/wild-horses/main/CLAUDE.md

Clone the repo

git clone --depth 1 https://github.com/paulbaranowski/wild-horses

Made for: Claude Code.

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.

README.md

[![agentmods](https://agentmods.dev/badge/instructions/paulbaranowski/wild-horses/claude-md/github.svg)](https://agentmods.dev/instructions/paulbaranowski/wild-horses/claude-md)

Your own site

<a href="https://agentmods.dev/instructions/paulbaranowski/wild-horses/claude-md"><img src="https://agentmods.dev/badge/instructions/paulbaranowski/wild-horses/claude-md/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.

Your own site · 80×15

<a href="https://agentmods.dev/instructions/paulbaranowski/wild-horses/claude-md"><img src="https://agentmods.dev/badge/instructions/paulbaranowski/wild-horses/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 3,449 This file is loaded in full into every session.

When invoked 3,449 The same file — it is already loaded in full.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

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.

Model	Per session	Once invoked
Fable 5.1	$0.03449	$0.03449
Opus 5.5	$0.01380	$0.01380
Sonnet 5.5	$0.00690	$0.00690
Haiku 4.5	$0.00345	$0.00345

Measured 1mo ago against content hash 5885271a44d3, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

wild-horses 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 1mo 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.md · 150 lines

How it starts

The opening of the file, as written. The whole thing — 150 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Wild Horses - Claude Code Plugin Marketplace

Project Structure

This is a Claude Code plugin marketplace.

.claude-plugin/marketplace.json    -- marketplace catalog (points to plugins)
plugins/harness/                   -- plugin root (commands-based)
  .claude-plugin/plugin.json       -- plugin manifest
  commands/feedback-blockers.md    -- /harness:feedback-blockers
  commands/reasoning-gaps.md       -- /harness:reasoning-gaps
plugins/marketplace/               -- plugin root (skills-based)
  .claude-plugin/plugin.json       -- plugin manifest
  skills/create/SKILL.md           -- /create (marketplace scaffolding)

Key References

Plugin Marketplaces: https://code.claude.com/docs/en/plugin-marketplaces
Creating Plugins: https://code.claude.com/docs/en/plugins
Plugins Reference (schemas, validation, caching): https://code.claude.com/docs/en/plugins-reference
Skills Reference (frontmatter fields): https://code.claude.com/docs/en/skills

Rules

Marketplace Structure

marketplace.json goes in .claude-plugin/ at the repo root. Do NOT add "$schema" — the validator rejects unrecognized keys.
Cursor parity: also ship .cursor-plugin/marketplace.json at the repo root and .cursor-plugin/plugin.json per plugin. Claude hooks stay in hooks/hooks.json (PascalCase, nested); Cursor hooks go in hooks/cursor-hooks.json (camelCase, flat) and are referenced from the Cursor manifest via "hooks": "hooks/cursor-hooks.json". Hook scripts that emit permission decisions must support both Claude (hookSpecificOutput) and Cursor (permission) formats — branch on hook_event_name from stdin.
Each plugin lives in its own directory under plugins/. The plugin's .claude-plugin/plugin.json goes inside that directory, NOT at the repo root.
Skills, agents, commands, and hooks go at the plugin root level, NOT inside .claude-plugin/.
Validate with: claude plugin validate . or /plugin validate .

Repo hygiene

Read the full file on GitHub · 150 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.

1mo ago Changed · +42 tokens per session 5885271a44d3
2mo ago First seen · 150 lines · 3,407 tokens per session scan A 5c584a21293e

Subscribe to this mod's changes

wild-horses CLAUDE.md is an instructions file published in the GitHub repository paulbaranowski/wild-horses (14 stars, last pushed 11d ago), licensed MIT. It adds 3,449 tokens to every session, about $0.0138 per session on Opus 5.5. 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.

Building agents

wild-horses CLAUDE.md next to 6 instructions from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
wild-horses CLAUDE.mdpaulbaranowski/wild-horses	Instructions file	14	11d ago	MIT	A	3,449	Claude Code
vscode buildNext.instructions.mdmicrosoft/vscode	Instructions file	195k	today	MIT	A	9,719	GitHub Copilot
next.js AGENTS.mdvercel/next.js	Instructions file	143k	yesterday	MIT	A	7,461	Codex, OpenCode
langchain AGENTS.mdlangchain-ai/langchain	Instructions file	149k	today	MIT	A	4,680	Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscode	Instructions file	195k	today	MIT	A	5,516	GitHub Copilot
vscode copilot-instructions.mdmicrosoft/vscode	Instructions file	195k	today	MIT	A	3,093	GitHub Copilot
deepseek-harness AGENTS.mddeepseek-ai/deepseek-harness	Instructions file	275k	2d ago	MIT	A	4,313	Codex, OpenCode

wild-horses: Instructions file for Claude Code