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-projectnpx skills add Flagrare/llm-tutor --skill tutor-projectgit 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-project)<a href="https://agentmods.dev/skills/flagrare/llm-tutor/tutor-project"><img src="https://agentmods.dev/badge/skills/flagrare/llm-tutor/tutor-project.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 | $0.00082 | $0.00909 |
| Opus 5 | $0.00041 | $0.00454 |
| Sonnet 5 | $0.00016 | $0.00182 |
| Haiku 4.5 | $0.00008 | $0.00091 |
Grade A, and why
tutor-project scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 6d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 81 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Tutor Project
A thin wrapper around /tutor-codebase that uses the user's current working directory as the path. Use this when you want to tutor on whatever you're already inside — no need to type a path.
This skill does not duplicate /tutor-codebase's logic. It resolves CWD as the codebase path and follows the same procedure that lives in skills/tutor-codebase/SKILL.md.
When to use this vs /tutor-codebase
/tutor-project— tutor on the directory you're currently in/tutor-codebase <path>— tutor on a different directory (e.g., a repo you've cloned but aren'tcd-ed into)
The slug format and aspect handling are identical in both skills.
Procedure
Step 0a — Resolve CWD
ABS_PATH=$(pwd)
Validate it's a directory you can read. (It almost certainly is — you're already in it — but check defensively.)
Step 0b — Resolve aspect
If the user provided an argument (e.g., /tutor-project 'how requests flow'), use that as the aspect.
If not, default to "overview" per locked decision C2.
Step 0c — Compute slug
Per locked decision B2: slug = "{basename-of-PWD}-{aspect-slug}".
REPO_BASENAME=$(basename "$ABS_PATH")
ASPECT_SLUG=$(printf "%s" "$ASPECT" | tr '[:upper:]' '[:lower:]' | sed 's/[^a-z0-9-]/-/g' | sed 's/-\+/-/g; s/^-\|-$//g')
SLUG="${REPO_BASENAME}-${ASPECT_SLUG}"
Step 1 onward — Follow /tutor-codebase's steps
With $ABS_PATH, $ASPECT, and $SLUG resolved, follow steps 0d–6 from /tutor-codebase/SKILL.md exactly. The flow is identical from this point: resume-check → explore the codebase → generate path → charge cycle → calibrate → position on path → hand off to persona.
Do not re-implement the exploration, path generation, calibration, or handoff logic here. Read tutor-codebase/SKILL.md as your source of truth for those steps.
Hard rules
Same hard rules as /tutor-codebase — they all apply unchanged:
- One thing at a time (don't read 30 files in one batch)
- Cap exploration at ~10 file reads
- Don't summarize the codebase during exploration — that's not what the user asked for
- Never reveal canonical solutions during calibration
- Cycle charged exactly once per (codebase, aspect) pair (the existing-topic resume check in /tutor-codebase's Step 0e handles this)
- Refuse on too-broad scope
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.
- 6d ago First seen · 81 lines · 82 tokens per session scan A 8ad25d5ddf2f
tutor-project is a skill published in the GitHub repository Flagrare/llm-tutor (5 stars, last pushed 3mo ago), licensed MIT. It adds 82 tokens to every session and 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 2026-08-31.
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…
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…
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…