mentor-init

mentor-init is a skill for Claude Code, Codex from hcsum/dont-let-me. It costs 73 tokens per session (1,909 once invoked), scanned A, original, MIT.

A guided interview for creating or revising a mentor profile: a file describing your goals, practical constraints, and habits you want to avoid.

In plain words
What is it for?
Use it to set up the mentor profile, revise its sections, rewrite a goal, add an item to your avoid list, or create a profile when none exists.
Why use it?
It turns vague intentions into a written profile that the mentor add-on can use in later sessions.

Skill for Claude CodeCodex

Written for Claude Code and Codex: ${CLAUDE_PLUGIN_ROOT} variable, but also reads ~/.codex or $CODEX_HOME. Also seen: reads .claude/ paths; mentions Codex; $skill-name invocation.

Runs only inside its plugin — its command needs a path that Claude Code sets for a plugin’s own hooks and for nothing else. Install the plugin, not this.

Part of the mentor plugin — 3 skills, 2 commands, 1 hook shipped together

Good fit Use it to set up the mentor profile, revise its sections, rewrite a goal, add an item to your avoid list, or create a profile when none exists.

Compare 6 skills from other repositories ↓
Install

Getting it into your agent

This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.

Claude Code
/plugin marketplace add hcsum/dont-let-me
Claude Code
/plugin install mentor

Made for: Claude Code, Codex.

Or install mentor, the plugin that ships this one along with the rest of its 3 skills, 2 commands, 1 hook.

Wrote 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.

agentmods badge for mentor-init

README.md
[![agentmods](https://agentmods.dev/badge/skills/hcsum/dont-let-me/mentor-init/github.svg)](https://agentmods.dev/skills/hcsum/dont-let-me/mentor-init)
Your own site
<a href="https://agentmods.dev/skills/hcsum/dont-let-me/mentor-init"><img src="https://agentmods.dev/badge/skills/hcsum/dont-let-me/mentor-init/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.

agentmods 80×15 button for mentor-init

Your own site · 80×15
<a href="https://agentmods.dev/skills/hcsum/dont-let-me/mentor-init"><img src="https://agentmods.dev/badge/skills/hcsum/dont-let-me/mentor-init.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 73 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,909 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00073 $0.01909
Opus 5 $0.00036 $0.00955
Sonnet 5 $0.00015 $0.00382
Haiku 4.5 $0.00007 $0.00191

Measured 9d ago against content hash e4091317b921, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

mentor-init 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 9d 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.

skills/mentor-init/SKILL.md · 165 lines

How it starts

The opening of the file, as written. The whole thing — 165 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Interview the user to build their mentor profile, then write it to the profile path named in the mentor context injected at session start ($MENTOR_HOME when set, otherwise ~/.mentor/profile.md, or an existing ~/.claude/mentor/ or ~/.codex/mentor/ directory).

If that file already exists, read it first and offer to revise section by section rather than starting over.

How to run the interview

One question at a time. Do not present a form or list all three sections at once — that produces three shallow answers. Ask, react to what they said, follow up if it's vague, then move on.

Push back on vagueness. The plugin is worth nothing if the inputs are aspirational. Be warm about it, but don't accept a goal you couldn't verify or a weakness that flatters them.

Keep it under fifteen minutes. Two sharp goals and three honest don't-let-me entries beat a complete but hollow file. If they're getting impatient, write what you have — the profile is meant to be edited later, not finished today.

Budget the attention. People arrive with a fixed amount of patience, and the expensive section is the second one — the don't-let-me list. Spend the budget interrogating goals and they'll be answering in single words by the time you reach the part worth having. The third section is deliberately the cheap one, so running low by then costs nothing. Say this in your opening: three sections, the middle one is where the work happens, the last one is quick.

Concretely: at most two rounds of push-back per goal. If it's still vague after the second, stop asking and write two or three sharpened versions yourself for them to pick from. Producing is expensive; reacting is cheap. Move on.

Offer choices as choices. When you've narrowed something to a small set — candidate phrasings of a goal, "is this its own goal or part of that one", the three shapes an avoidance usually takes — use the question tool rather than listing options in prose and hoping they type back a number. Reserve free text for what only they can supply: the goals themselves, what they abandoned, what stopped them. That raw material is the whole input; never turn it into a menu.

Read the full file on GitHub · 165 lines

Changes

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.

  1. 9d ago First seen · 165 lines · 73 tokens per session scan A e4091317b921

Subscribe to this mod's changes

mentor-init is a skill published in the GitHub repository hcsum/dont-let-me (12 stars, last pushed 1mo ago), licensed MIT. It adds 73 tokens to every session and 1,909 once invoked, about $0.0004 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.

Related

Other skills, from other repositories

i-have-adhd

Shape output for a reader with ADHD: lead with the next action, number multi-step work, restate state across turns, suppress tangents, give specific time estimates, make wins visible. Invoke with /i-have-adhd; stays on until "stop adhd mode".

ayghri/i-have-adhd · 62 tokens

pickup

Resume work on this project after an interruption or at the start of a new session: show recent wins, what was being done, the next action, and open decisions, in that order, then stop. Trigger only on an explicit /squirrel:pickup invocation, or an explicit request to resume or pick up this project's past work at the…

thgMatajs/squirrel-mode · 124 tokens

digest

Restructure a rambling ticket, email, pasted note, file, or Jira issue - prose the user received - into the fixed digest brief (TL;DR, Next action, Breakdown, Priority). Trigger on an explicit /squirrel:digest invocation, or an explicit request to digest or restructure a named piece of prose into that brief. An…

thgMatajs/squirrel-mode · 188 tokens

init

Run the squirrel-mode calibration interview: seven one-at-a-time multiple-choice questions that build the user's personal response-formatting profile. Only for an explicit /squirrel:init invocation.

thgMatajs/squirrel-mode · 35 tokens

stash

Record one durable memory in the user's cross-project hoard: a correction, a decision with its reasoning, a bug and its fix, or a fact worth keeping. Only for an explicit /squirrel:stash invocation.

thgMatajs/squirrel-mode · 44 tokens

my-adhd-caveman

Self-contained output mode: ADHD actable structure (action first, numbered steps, one next action, one-line progress) plus caveman diction (drop fluff/articles, fragments, fewer tokens). Use when the user says "adhd-caveman", "my-adhd-caveman", or invokes /my-adhd-caveman. Needs no other skills.

SteinsFu/my-adhd-caveman · 83 tokens