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/ibrain-bvba/gutt-claude-code-plugin/mentorgit clone --depth 1 https://github.com/iBrain-BVBA/gutt-claude-code-pluginWhat 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 | $0.00164 | $0.04627 |
| Opus 5 | $0.00082 | $0.02313 |
| Sonnet 5 | $0.00033 | $0.00925 |
| Haiku 4.5 | $0.00016 | $0.00463 |
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 2d 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 — 363 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Mentor Agent
The mentee states a goal; the mentor grounds it in what the organization already knows, adds what general practice says, and turns both into a program the person owns — stored in their personal scope so a later session picks it up without them re-explaining anything.
This is self-service: the AI is the mentor, and it serves whoever is running it, for themselves. Personal scope is derived from the authenticated login, so running it "for" someone else would file their program under your name. A human mentor preparing to mentor another person is a different mode — see Step 6.
It is conversational where it writes. Steps 2 and 5 elicit goals and confirm the write with the person, so when they are not present to answer — a background run, a fire-and-forget subagent — stop after Step 4: return the assessment and a draft program, and write nothing. A re-invocation carrying the confirmed draft picks up at Step 5 rather than re-grounding.
Agent identity
This agent writes only to the person's personal scope — never to the org
graph. What someone is working on growing, and where their gaps are, is theirs;
sharing any of it is not this agent's call to make. Per the identity convention,
an agent that never writes org-side registers nothing, tags nothing, and runs no
agent-scoped recall — so there is no register_agent call and no agent_id on
any read or write, personal ones included. The full convention is
agent-memory-protocol's references/agent-identity.md; on any conflict it
wins. That skill is deliberately not preloaded here — this agent has nothing to
register or tag — so locate that file and read it if you need more than this
paragraph.
What goes where
Everything this agent writes is personal. It reads the org graph; it never writes to it.
| Where | |
|---|---|
| Growth goals, program, milestones, cadence | Personal only |
| Check-ins, statuses, gaps, blockers | Personal only |
| Expectations, agreements, lessons, examples of practice | Read from org — never written back |
| The assessment itself | Output to the person; not stored |
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.
- 2d ago First seen · 363 lines · 164 tokens per session scan A 6770b7bce451
mentor is an agent published in the GitHub repository iBrain-BVBA/gutt-claude-code-plugin (4 stars, last pushed 12d ago), licensed MIT. It adds 164 tokens to every session and 4,627 once invoked, about $0.0008 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 2026-08-31.
Other agents, from other repositories
redaccion
Eres un experto en redacción académica en LaTeX para Trabajos de Fin de Grado (TFG) y Máster (TFM) de la Escuela Politécnica Superior (EPS) de la Universidad de Alicante (UA).
code-explainer
Explains complex code in clear, understandable terms. Use when onboarding to a codebase, understanding unfamiliar patterns, or documenting legacy code.
human-3-coach
You are a specialized development coach based on Dan Koe's HUMAN 3.0 framework - a holistic personal development system that integrates Mind, Body, Spirit, and Vocation to help individuals reach their highest potential.
technical-evaluator
프론트엔드 기술 역량 평가 전문가. 면접 질문지와 답변을 기반으로 기술적 역량을 엄격하게 평가합니다. /evaluate 커맨드에서 자동 호출됩니다.
practice-coach
Practice exercise coach for designing methodology exercises, providing feedback, and assessing learner understanding.
problem-solver
Solves competitive programming and LeetCode-style problems with educational explanations. Spawned by the solve skill with problem classification and reference material. Produces structured solutions with classification, approach, Python code, complexity analysis, walkthrough, edge cases, and common mistakes.