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/ayhammouda/mentor/claude-mdgit clone --depth 1 https://github.com/ayhammouda/mentorWrote 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/ayhammouda/mentor/claude-md)<a href="https://agentmods.dev/instructions/ayhammouda/mentor/claude-md"><img src="https://agentmods.dev/badge/instructions/ayhammouda/mentor/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 | $0.00764 | $0.00764 |
| Opus 5 | $0.00382 | $0.00382 |
| Sonnet 5 | $0.00153 | $0.00153 |
| Haiku 4.5 | $0.00076 | $0.00076 |
Grade A, and why
mentor 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 5d 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.
This is a copy
92% identical to mentor AGENTS.md — 6 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
How it starts
The opening of the file, as written. The whole thing — 57 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md
This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository.
What This Is
Mentor is a Claude skill (SKILL.md with YAML frontmatter) that generates docs-first mentorship compasses for technical topics. It runs on Claude.ai and Claude Code, and relies on current source lookup to verify resource URLs and freshness.
The intended behavior is direction-setting, not tutorial generation:
- read this documentation first
- check this page next
- inspect this repo or artifact for a pattern
- notice this concept before moving on
- avoid this rabbit hole for now
Repository Structure
SKILL.md- The skill definition. This is the primary artifact. All behavior rules, output format, source ranking, and anti-patterns live here.references/schema.json- JSON Schema contract for machine-readable compass output.examples/- Gold-standard example outputs that demonstrate correct behavior:example-output-rust.md- broad topic with user backgroundexample-output-cloud-run.md- broad topic, default assumptionsexample-output-terraform-modules.md- narrow topic, compressed compassexample-output-react-server-components.md- clarification trigger + fast-moving topic
evals/evals.json- 10 test cases with machine-gradable assertions covering structure, source quality, mode variety, dedup, content, clarification, personalization, freshness, time constraints, weak-docs handling, schema compliance, and tutorial-drift guards.scripts/validate.mjs- Dependency-free validation harness for schema, eval, example, and drift checks.TESTING.md- Test strategy and validation notes.
How the Artifacts Relate
SKILL.md is the source of truth. The schema, examples, docs, and evals must stay consistent with it:
- If you change the output format in
SKILL.md, updatereferences/schema.json. - If you change decision rules, update affected examples and eval assertions.
- If you change resource modes, update schema enums and every example.
- If you change public positioning, update
README.mdandCONTRIBUTING.md. - If you add or change behavior contracts, update
scripts/validate.mjswhen the rule can be checked statically.
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.
- 5d ago First seen · 57 lines · 764 tokens per session scan A 3583e2217a77
mentor CLAUDE.md is an instructions file published in the GitHub repository ayhammouda/mentor (9 stars, last pushed 2mo ago), licensed MIT. It adds 764 tokens to every session, about $0.0038 per session on Opus 5. A static security scan graded it A with 0 findings. It is 92% identical to mentor AGENTS.md, differing in 6 lines, and is treated as a copy.
Other instructions, from other repositories
ultimate-seo-geo AGENTS.md
Instructions for mykpono/ultimate-seo-geo, covering ultimate seo + geo — llm-agnostic seo agent, 0. before you start, routing index, when not to run a full audit and audit context: internal vs. competitive.
ultimate-seo-geo copilot-instructions.md
Instructions for mykpono/ultimate-seo-geo, covering ultimate seo + geo — copilot instructions, how to use, key capabilities, quick start and reference files.
ultimate-seo-geo GEMINI.md
Instructions for mykpono/ultimate-seo-geo, covering ultimate seo + geo — gemini cli context, instructions, key commands, install dependencies first and run all individual checks.
ilana AGENTS.md
Instructions for Ferousco-dev/ilana, covering agents.md, 1. installing ìlànà, the install, in full, about the ilana command and if symlinks are not possible.
anki-card-skill GEMINI.md
Gemini CLI instructions for gong1414/anki-card-skill, a project described as: AI-powered Anki flashcard generator — works as a skill/plugin for Claude Code, Cursor, Copilot CLI, Gemini CLI, Codex & OpenCode. Exports to .tsv/.apkg with HTML formatting, hierarchical tags, and CJK support.
workingclass AGENTS.md
AGENTS.md instructions for workingclass-ai/workingclass, covering repository agent instructions, how to use the skill and validation.