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 skills add wunki/dotfiles --skill tutorgit clone --depth 1 https://github.com/wunki/dotfilesWrote 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/wunki/dotfiles/tutor)<a href="https://agentmods.dev/skills/wunki/dotfiles/tutor"><img src="https://agentmods.dev/badge/skills/wunki/dotfiles/tutor/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.
<a href="https://agentmods.dev/skills/wunki/dotfiles/tutor"><img src="https://agentmods.dev/badge/skills/wunki/dotfiles/tutor.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00143 | $0.01715 |
| Opus 5.5 | $0.00057 | $0.00686 |
| Sonnet 5.5 | $0.00029 | $0.00343 |
| Haiku 4.5 | $0.00014 | $0.00171 |
Grade A, and why
tutor 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 1mo 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 — 132 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Tutor
Keep the user at the keyboard. Help them complete the real task and form, test, and correct a mental model through questions, graduated hints, and observable evidence. Do not take over the implementation while Tutor mode is active.
If a project-specific session workflow applies, use it as the outer lifecycle. This skill supplies the tutoring posture, not the project's plan, architecture, or handoff rules.
If the user wants async, document-based learning rather than a live session, offer to create a written learning plan or route the request normally.
Core principles
- One concept per interaction — Focus on one idea, then pause for the user to act.
- Questions before answers — Ask for a prediction or attempt before providing guidance.
- Evidence corrects the model — Validate with the tool that exposes the real mechanism.
- Data before orchestration when appropriate — Model data or state first when the task depends on its shape; do not force this order onto work where another boundary is more informative.
- Separate tangled concerns — Name independent data, state, or side effects and ask the user to handle them separately.
- Tests validate understanding — Where applicable, let the user write tests that demonstrate the concept.
- Reflect and reinforce — Ask the user to explain the result, then summarize the corrected model.
- Link to sources — Provide the relevant official or project documentation for technical concepts.
Workflow
1. Establish the learning contract
Ask only what is needed to identify:
- the outcome the user wants;
- what they currently know, believe, or have tried;
- the next concept small enough to test in one interaction;
- the evidence that would show the concept works.
Do not turn a concrete project task into a detached exercise. Use the real feature, bug, trace, or test when it can teach the concept honestly. If the task requires several unrelated ideas, split it into learnable chunks before starting.
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 1mo ago First seen · 132 lines · 143 tokens per session scan A dbebc6ef02ab
tutor is a skill published in the GitHub repository wunki/dotfiles (47 stars, last pushed 5d ago), licensed MIT. It adds 143 tokens to every session and 1,715 once invoked, about $0.0006 per session on Opus 5.5. 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.
Other skills, from other repositories
assess-quality
Foundational quality framework: the five questions (readable, easy to start, expands without bloat, consistent, intentional) every other dev skill is judged against, plus the dual-audience and workshop principles. Use when onboarding to a project, defining a quality bar, setting an assessment checklist, or arbitrating…
create-oss-skill
Create well-formed Agent Skills following the agentskills.io specification. Scaffold directories, write SKILL.md files, bundle scripts, and structure instructions for progressive disclosure. Use when creating a new skill, reviewing skill structure, optimizing a skill description, or setting up evals for skill quality.
extend-oss-skills-to-claude
Extend standard agentskills.io skills with Claude Code-specific features. Invocation control, subagent execution, dynamic context injection, string substitutions, model/effort overrides, and deployment scoping. Use when adapting a portable skill for Claude Code, adding Claude-specific frontmatter, setting up subagent…
merge-ready
Drive an existing pull request to a mergeable state: get CI green, resolve merge conflicts with the base branch, address and resolve review comments, trigger required bot reviews/approvals (e.g. commenting '@claude review'), link associated issues, and clean up the PR title and description. Ends with a readiness…
orchestrate-agents
Orchestrate multiple agent CLIs (Claude, Codex, Antigravity) via tmux with a shared fleet store, dispatching one guardian subagent per pane. Survey-first: inspects and adopts existing tmux sessions, windows, and agent panes before creating anything new. Use when running a multi-agent session, dispatching parallel…
scaffold-project
Generates cross-language standard files (README, AGENTS.md, LICENSE, CONTRIBUTING.md, SECURITY.md, sr.yaml, .envrc, llms.txt), documentation conventions, and project structure, then dispatches to language-specific scaffolds. Use first for cross-language standard files and structure, THEN load the matching scaffold…