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 joey-barbier/ClaudeCode-Plugin --skill horka-claude-setupgit clone --depth 1 https://github.com/joey-barbier/ClaudeCode-PluginWrote 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/joey-barbier/claudecode-plugin/horka-claude-setup)<a href="https://agentmods.dev/skills/joey-barbier/claudecode-plugin/horka-claude-setup"><img src="https://agentmods.dev/badge/skills/joey-barbier/claudecode-plugin/horka-claude-setup/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/joey-barbier/claudecode-plugin/horka-claude-setup"><img src="https://agentmods.dev/badge/skills/joey-barbier/claudecode-plugin/horka-claude-setup.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 | $0.00099 | $0.00932 |
| Opus 5 | $0.00049 | $0.00466 |
| Sonnet 5 | $0.00020 | $0.00186 |
| Haiku 4.5 | $0.00010 | $0.00093 |
Grade A, and why
horka-claude-setup 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 10d 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 — 86 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Setup - CLAUDE.md Generator
Scope
Generates CLAUDE.md files only. Does NOT:
- Modify existing project code or configuration
- Install plugins or dependencies
- Set up git repositories
Step 1: Detect Context
- Check for existing CLAUDE.md files:
~/.claude/CLAUDE.md(global),.claude/CLAUDE.md(project),CLAUDE.md(root) - If in a project: detect tech stack from config files (
package.json,pyproject.toml,Cargo.toml,go.mod, etc.) and git conventions from recent commits (git log --oneline -5) - Use detected stack and git conventions as defaults in questionnaire (skip questions already answered by detection)
If existing CLAUDE.md found, ask via AskUserQuestion: replace, augment, or different scope.
- Replace: full questionnaire, overwrite existing file
- Augment: Read existing file, identify covered sections, ask only about missing/uncovered topics, use Edit to merge new sections
- Different scope: full questionnaire, write to chosen alternative location
Step 2: Questionnaire
Consult references/questionnaire.md for the full question tables.
Run 3 rounds via AskUserQuestion:
- Profile & Philosophy: usage type, work philosophy, communication style, language
- Workflow: security (common for all profiles) + git/commit conventions for dev or git usage/file organization for PM/writing
- Integration: file headers, context management, output destination, installed plugins
If a question is skipped or answered vaguely ("I don't know", "whatever"), re-ask once with: "This choice affects your CLAUDE.md quality. Here's what each option means: [brief impact of each]". If skipped a second time, apply the (Recommended) default.
Step 3: Generate CLAUDE.md
Consult references/generation-rules.md for section templates, plugin integration, and quality reference.
Key rules:
- Generate ONLY sections relevant to user answers
- Every instruction must be actionable (NEVER, ALWAYS for absolute rules)
- Add contextual qualifiers for non-absolute rules ("For non-trivial changes", "Skip for obvious fixes")
- No filler prose -- bullet points only
- Put critical rules at the top of each section
- Use
##numbered subsections to group 3+ related concerns within a#category - Do NOT duplicate rules already in Claude's system prompt (e.g., "no emojis")
- Keep total length under 100 lines
- Include plugin section if ANY plugins selected
What ships with it
2 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.
- 10d ago First seen · 86 lines · 99 tokens per session scan A d99037391398
horka-claude-setup is a skill published in the GitHub repository joey-barbier/ClaudeCode-Plugin (22 stars, last pushed 2mo ago), licensed MIT. It adds 99 tokens to every session and 932 once invoked, about $0.0005 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…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…
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…