tutor-done

tutor-done is a skill for Claude Code from Flagrare/llm-tutor. It costs 120 tokens per session (3,128 once invoked), scanned B, original, MIT.

A closing command for an llm-tutor learning topic. It records the topic as complete, calculates experience points from your first attempts, and asks for feedback.

In plain words
What is it for?
Use it to complete a topic, award XP based on how much help you needed, run the thumbs and targeted feedback flow, and record that feedback.
Why use it?
It gives you a defined way to finish a session and preserves what happened. The feedback questions also help the project collect responses about the tutoring experience.

Skill for Claude Code

Written for Claude Code: $CLAUDE_PLUGIN_ROOT variable. Also seen: names the AskUserQuestion tool.

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 llm-tutor plugin — 12 skills, 1 hook shipped together

Good fit Use it to complete a topic, award XP based on how much help you needed, run the thumbs and targeted feedback flow, and record that feedback.

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 Flagrare/llm-tutor
Claude Code
/plugin install llm-tutor

Made for: Claude Code.

Or install llm-tutor, the plugin that ships this one along with the rest of its 12 skills, 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 tutor-done

README.md
[![agentmods](https://agentmods.dev/badge/skills/flagrare/llm-tutor/tutor-done.svg)](https://agentmods.dev/skills/flagrare/llm-tutor/tutor-done)
Your own site
<a href="https://agentmods.dev/skills/flagrare/llm-tutor/tutor-done"><img src="https://agentmods.dev/badge/skills/flagrare/llm-tutor/tutor-done.svg" alt="Measured on agentmods" height="20"></a>
Per session 120 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 3,128 The whole file, excluding the scripts and references it only reads on demand.
Security scan B 1 finding. 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 $0.00120 $0.03128
Opus 5 $0.00060 $0.01564
Sonnet 5 $0.00024 $0.00626
Haiku 4.5 $0.00012 $0.00313

Measured 7d ago against content hash 96f2a12ab856, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade B, and why

tutor-done scanned grade B with 1 finding 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 7d 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.

Strips warnings and disclaimersmediumAnti-refusal

Omitting safety caveats hides risk from the user and is a common jailbreak preamble.

If not substantive (skipped/short): no extra reward. Don't punish, don't lecture.
plugins/llm-tutor/skills/tutor-done/SKILL.md · 316 lines

How it starts

The opening of the file, as written. The whole thing — 316 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Tutor Done

This skill closes an active tutoring topic — the pair to /tutor-start. It calculates the XP earned, marks the topic complete in state.json, runs the two-step feedback flow (thumbs + targeted rotating question), and credits the user with cycles rewards for engaging.

The feedback flow is the load-bearing piece. Per the design decisions doc (D4), feedback is rewarded to fix the "users skip it" problem, with anti-gaming guards (symmetric thumbs reward, substantive-answer guard for the targeted question, daily cycles cap).


XP rubric (per-concept)

XP is awarded per concept based on the first_attempt field — the user's first interaction with that concept during the session.

first_attempt XP awarded Reasoning
"success" 30 Solved it on the first try. Earned mastery signal.
"needed_hint" 15 Used the hint ladder; learned something but with scaffolding.
"needed_reveal" 5 Needed the canonical answer revealed. Still engaged, still some learning.
null 0 Concept was never attempted (probably skipped during calibration). No XP.

A typical 6-concept topic where the user gets most concepts first-try and needed one hint earns ~150 XP. The numbers are tunable in this rubric — adjust here if the felt-pacing turns out wrong.


Step 0 — Resolve the target topic

STATE="$CLAUDE_PLUGIN_ROOT/scripts/state.sh"

0a. Subject resolution

If the user provided an argument (e.g., /tutor-done python-decorators), use that as the slug.

If no argument, find the active topic:

ACTIVE=$(bash "$STATE" get '[.topics | to_entries[] | select(.value.status == "in_progress") | .key]')

If the active list is empty:

"No topic in progress. Run /tutor-status to see what you've started, or /tutor-start <subject> to begin one."

Exit cleanly.

If exactly one in-progress topic, use that slug.

If multiple in-progress topics, ask:

"Multiple topics in progress: [list]. Which one are you closing? (Type the slug, e.g. python-decorators.)"

Read the full file on GitHub · 316 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. 7d ago First seen · 316 lines · 120 tokens per session scan B 96f2a12ab856

Subscribe to this mod's changes

tutor-done is a skill published in the GitHub repository Flagrare/llm-tutor (5 stars, last pushed 3mo ago), licensed MIT. It adds 120 tokens to every session and 3,128 once invoked, about $0.0006 per session on Opus 5. A static security scan graded it B with 1 finding (strips warnings and disclaimers). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Related

Other skills, from other repositories

learning-and-development

Builds capability — skills gaps, career frameworks, training that transfers to the job, and internal mobility. Use this to design a career ladder, close a capability gap, decide whether to build or hire a skill, structure onboarding into a role, or work out why training keeps failing to change anything.

cbrock84/headcount · 64 tokens

quiz-me

Quiz the user on root cause and intended fix BEFORE writing any non-trivial code, then verify comprehension of every change after. Use when the user asks for a bug fix, refactor, or feature and wants to stay technically sharp instead of vibe-coding. Also use when the user says "quiz me", "don't let me vibe code", or…

emanzurv/quiz-me-skill · 82 tokens

Ask a Senior

A senior engineer who refuses badly-formed questions and gives hints, never code. Use when the user runs /ask-a-senior, or asks to turn on senior mode.

egorus1/ask-a-senior · 40 tokens

ai-trend-tracker

Answers questions about AI/ML news, tool launches, research papers, and learning resources (free courses, certificates, YouTube channels, podcasts, newsletters, learning paths) by searching the live web first and returning a cited, dual-layer (ELI5 + technical + honest verdict) explanation tailored to the user's role…

Unnati-23/ai-trend-tracker · 168 tokens

enablement-course

Assemble an internal AI enablement course for a company's own employees, sized to where they actually are rather than where a vendor deck assumes they are. Produces the session plan, per-session content and exercises, a facilitator guide for a non-expert, and a way to tell whether it worked. Builds on the tech stack…

enalbenerraw/blanewarrene · 81 tokens

coaching-mode

Use when the user wants to coach someone — a report, peer, or mentee — through a problem rather than solve it for them. Trigger phrases include "coach me through how to talk to [report]", "I want to help [name] figure out X without telling them what to do", "let me practice a coaching conversation", "GROW conversation…

shwetank/bettersense · 0 tokens