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 skills/flagrare/llm-tutor/tutor-startnpx skills add Flagrare/llm-tutor --skill tutor-startgit clone --depth 1 https://github.com/Flagrare/llm-tutorWrote 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/skills/flagrare/llm-tutor/tutor-start)<a href="https://agentmods.dev/skills/flagrare/llm-tutor/tutor-start"><img src="https://agentmods.dev/badge/skills/flagrare/llm-tutor/tutor-start.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 5.1 | $0.00163 | $0.04238 |
| Opus 5 | $0.00081 | $0.02119 |
| Sonnet 5 | $0.00033 | $0.00848 |
| Haiku 4.5 | $0.00016 | $0.00424 |
Grade B, and why
tutor-start 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 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.
Strips warnings and disclaimersmediumAnti-refusal
Omitting safety caveats hides risk from the user and is a common jailbreak preamble.
**Wait for the user's response. One question. Do not lecture.** How it starts
The opening of the file, as written. The whole thing — 327 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Tutor Start
This skill begins a Socratic tutoring journey on a user-supplied topic. It is the load-bearing entry point for the llm-tutor plugin — every other skill (/tutor-done, /tutor-path, /tutor-status, /tutor-resume) operates on state this skill creates.
Explicit invocation only. Do not auto-fire on colloquial phrases like "teach me X" or "explain Y" — those usually mean the user wants a quick answer, not a 30-90 minute dialogue. Trigger phrases are listed in the frontmatter description above.
Step 0 — Pre-checks
Run these via the Bash tool, in order. Treat STATE as a shorthand for the helper script path. The plugin guarantees $CLAUDE_PLUGIN_ROOT is set when this skill is invoked.
STATE="$CLAUDE_PLUGIN_ROOT/scripts/state.sh"
0a. Initialize state (idempotent)
bash "$STATE" init
This creates state.json if it doesn't exist; no-op if it does.
0b. Refill cycles if a day has passed (defensive — hook should have done this)
bash "$STATE" refill-cycles
0c. Read cycles balance
CYCLES=$(bash "$STATE" get .user.cycles)
If $CYCLES < 1, stop here. Print the user-facing message verbatim:
"Out of cycles — they refill once per day. Run
/tutor-statusto see when next refill is due, or come back tomorrow. (Earning more cycles today is possible via feedback on completed topics, see/tutor-done.)"
Exit the skill cleanly. Do NOT proceed to path generation.
0d. Resolve the subject
If the user provided an argument (e.g., /tutor-start "python decorators"), use that as the subject.
If no argument was provided, ask via free text (NOT AskUserQuestion — subjects are open-ended):
"What do you want to be tutored on? Be specific. Good: 'Python decorators' / 'how Suspense works in React' / 'how auth works in this repo'. Too broad: 'Python' / 'web dev' / 'AI'."
If the user names a topic that's clearly too broad (single-word language name, multi-paragraph stack), push back once: "Too broad. Pick a sub-topic or one concrete question." Do NOT proceed with a too-broad subject.
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 · 327 lines · 163 tokens per session scan B e436768b4aaa
tutor-start is a skill published in the GitHub repository Flagrare/llm-tutor (5 stars, last pushed 3mo ago), licensed MIT. It adds 163 tokens to every session and 4,238 once invoked, about $0.0008 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.
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.
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…
explain-code-slice
Use this skill when the user wants a code path, flow, pipeline, request lifecycle, trace, walkthrough, or part of a system explained step by step from start to finish. Explain where data comes from, what shape it has, who sends it, why it enters the flow, what calls what next, where branches and boundaries happen, how…
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.
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…
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…