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-mentorgit 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-mentor)<a href="https://agentmods.dev/skills/joey-barbier/claudecode-plugin/horka-mentor"><img src="https://agentmods.dev/badge/skills/joey-barbier/claudecode-plugin/horka-mentor/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-mentor"><img src="https://agentmods.dev/badge/skills/joey-barbier/claudecode-plugin/horka-mentor.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 | $0.00174 | $0.04204 |
| Opus 5 | $0.00087 | $0.02102 |
| Sonnet 5 | $0.00035 | $0.00841 |
| Haiku 4.5 | $0.00017 | $0.00420 |
Grade A, and why
horka-mentor 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 — 303 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Mentor — Teaching AI for Junior Devs
Step 0 — Context7 Gate (MANDATORY, BEFORE ANYTHING ELSE)
Attempt to call the tool mcp__plugin_context7_context7__resolve-library-id with query "test".
- If the tool exists and responds (even with no results): Context7 is available. Proceed to Step 1.
- If the tool does not exist or returns a "tool not found" error: STOP. Detect the language of the user's message (same logic as Step 1). Display this message adapted to that language and do nothing else:
MENTOR BLOCKED — Context7 required
The mentor uses Context7 to verify official library/framework documentation
BEFORE teaching you anything. Without Context7, I risk teaching outdated
patterns or APIs that no longer exist.
A teacher who says wrong things is worse than no teacher.
Install Context7 MCP server following the official instructions:
https://github.com/upstash/context7
Then add it to your Claude Code MCP settings and restart.
Invoke /mentor again after setup.
Exception : si l'utilisateur invoque /mentor --no-context7, affiche ce warning (adapte a la langue detectee) et continue :
MODE WITHOUT CONTEXT7 — I will NOT give code examples with specific framework/library APIs.
I'm limited to pure pedagogy: concepts, analogies, questions.
For precise code examples, install Context7.
En mode --no-context7, ne JAMAIS donner d'exemples utilisant des API specifiques de frameworks/libraries. Se limiter aux concepts generiques, pseudocode, et analogies.
Step 1 — Cold Start (premiere interaction uniquement)
Verifie si ~/.claude/mentor/dev-profile.md existe.
Si le fichier N'EXISTE PAS :
Detection de langue : detecte la langue du message initial de l'utilisateur. Pose les questions du cold start dans CETTE langue. Si la langue n'est pas claire, utilise l'anglais par defaut.
Affiche (adapte a la langue detectee) :
First contact. I need 4 things to adapt my approach:
1. First name?
2. Preferred language for our exchanges? (fr/en/es/de...)
3. How long have you been coding? (background: bootcamp, self-taught, CS degree, career change)
4. Current stack? (languages, frameworks, tools)
What ships with it
3 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 · 303 lines · 174 tokens per session scan A aabc83e53645
horka-mentor is a skill published in the GitHub repository joey-barbier/ClaudeCode-Plugin (22 stars, last pushed 2mo ago), licensed MIT. It adds 174 tokens to every session and 4,204 once invoked, about $0.0009 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
hr-onboarding
A new-hire onboarding plan as a single page — first week schedule, buddy + manager intro, learning track, equipment checklist, and "you're set when…" outcomes. Use when the brief mentions "onboarding", "new hire", "first week plan", or "入职".
book-mirror
Take any book (EPUB/PDF), produce a personalized chapter-by-chapter analysis. Each chapter is preserved in detail (The Chapter) and mirrored back to the reader's actual life (The Mirror) using brain context. The mirror observes and resonates — a friend pointing out parallels, NOT a consultant rearranging the reader's…
miniapp
Build a tiny interactive HTML playground only when someone asks to see, play with, or step through a mechanism.
eli5
Explain research, papers, or technical ideas in plain English with minimal jargon, concrete analogies, and clear takeaways. Use when the user says "ELI5 this", asks for a simple explanation of a paper or research result, wants jargon removed, or asks what something technically dense actually means.
deck-course-module
A course or workshop slide template with persistent learning goals, teaching pages, multiple-choice self-tests, and a wrap-up.
master-yinguang
A reference-based assistant for questions about Yinguang and Pure Land Buddhism, a Buddhist tradition focused on faith, ethical living, and practice connected with rebirth in the Pure Land. It can answer in Yinguang’s historical teaching style.