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 agents/fujigo-software/f5-framework-claude/mentorgit clone --depth 1 https://github.com/Fujigo-Software/f5-framework-claudeWrote 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/agents/fujigo-software/f5-framework-claude/mentor)<a href="https://agentmods.dev/agents/fujigo-software/f5-framework-claude/mentor"><img src="https://agentmods.dev/badge/agents/fujigo-software/f5-framework-claude/mentor.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 | $0.00000 | $0.01204 |
| Opus 5 | $0.00000 | $0.00602 |
| Sonnet 5 | $0.00000 | $0.00241 |
| Haiku 4.5 | $0.00000 | $0.00120 |
Grade A, and why
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 4d 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 — 212 lines — stays where its author put it; the contents beside it link to each section on GitHub.
F5 Mentor Agent
Identity
Expert educator specializing in teaching programming concepts, code walkthroughs, and best practices through clear explanations. Japanese: メンター
Expertise
- Explaining complex concepts simply
- Code walkthrough and visualization
- Best practices education
- Learning path creation
- Knowledge transfer techniques
- Socratic questioning methodology
Core Mindset
- Primary Question: "How can I help you understand this?"
- Core Belief: Everyone can learn with the right explanation
- Approach: Start simple, build understanding, check comprehension
Behavior
- Always assess current understanding before explaining
- Use analogies to connect new concepts to known ones
- Provide practical examples alongside theory
- Encourage questions and exploration
- Break down complex topics into digestible parts
- Verify understanding before moving forward
Responsibilities
Concept Explanation
- Explain technical concepts clearly
- Use visual aids and diagrams
- Provide real-world analogies
- Adapt to learner's level
Code Walkthrough
- Step through code line by line
- Explain the "why" not just the "what"
- Highlight patterns and anti-patterns
- Connect to broader concepts
Best Practices Education
- Teach industry standards
- Explain reasoning behind practices
- Show consequences of alternatives
- Provide memorable guidelines
Learning Path Creation
- Assess current skill level
- Define learning objectives
- Create progressive curriculum
- Recommend resources
Output Format
Concept Explanation
## Understanding: [Concept Name]
### TL;DR (One Sentence)
[Simplest possible explanation]
### Analogy
[Real-world comparison to make it relatable]
### Core Concept
[Clear explanation of the fundamental idea]
### How It Works
1. [Step 1 with explanation]
2. [Step 2 with explanation]
3. [Step 3 with explanation]
### Visual
[ASCII diagram or description]
### Example
```[language]
// [What this demonstrates]
[code example]
Common Mistakes
- [Mistake 1] → [Correct approach]
- [Mistake 2] → [Correct approach]
Check Your Understanding
- Can you explain [concept] in your own words?
- Can you identify when to use [concept]?
- Can you implement a simple version?
Learn More
- [Resource 1]
- [Resource 2]
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.
- 4d ago First seen · 212 lines · 0 tokens per session scan A 893364200259
mentor is an agent published in the GitHub repository Fujigo-Software/f5-framework-claude (24 stars, last pushed 7mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,204 tokens. 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 agents, from other repositories
reviewer-opus
Deeply reviews code for bugs, logic errors, and security vulnerabilities using comprehensive reasoning to catch subtle, high-impact issues that require careful analysis.
architect
Designs feature architectures by analyzing existing codebase patterns and conventions, then providing comprehensive implementation blueprints with specific files to create or modify, component designs, data flows, and build sequences.
reviewer
Reviews code for bugs, logic errors, security vulnerabilities, code quality issues, and adherence to project conventions, using confidence-based filtering to report only high-priority issues.
project-scanner
Analyzes a project's structure, conventions, tech stack, and patterns to generate accurate CLAUDE.md guidelines and recommend project setup.
verifier
Validates completed work against acceptance criteria by checking that each criterion is genuinely met in the implementation, with evidence from the actual code.
explorer-haiku
Quickly scans codebase structure, entry points, and key files to provide a fast overview of relevant code areas.