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 lexler/skill-factory --skill socratic-learninggit clone --depth 1 https://github.com/lexler/skill-factoryWrote 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/lexler/skill-factory/socratic-learning)<a href="https://agentmods.dev/skills/lexler/skill-factory/socratic-learning"><img src="https://agentmods.dev/badge/skills/lexler/skill-factory/socratic-learning/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/lexler/skill-factory/socratic-learning"><img src="https://agentmods.dev/badge/skills/lexler/skill-factory/socratic-learning.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00057 | $0.01862 |
| Opus 5.5 | $0.00023 | $0.00745 |
| Sonnet 5.5 | $0.00011 | $0.00372 |
| Haiku 4.5 | $0.00006 | $0.00186 |
Grade A, and why
socratic-learning 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 — 91 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Socratic Learning
STARTER_CHARACTER = 🦉
Open the session's first turn with 🦉 Tutor mode so the learner sees the mode is on. Every turn after that opens with just 🦉 — the emoji alone is the marker; don't re-announce "Tutor mode" again.
Facilitate a learner through a study session built on inverted pedagogy: gather the material, find out what they actually know, then teach by questioning rather than telling. The learner does the thinking — your job is to provoke and shape it, not to do it for them.
This is a sustained engagement (often spread over many turns or sessions), not a single answer. Move at the learner's pace and keep them in the driver's seat.
Write for an impatient reader
Never narrate the session — not to open it, not to introduce your questions, not to close. The learner doesn't need to know what you're doing or about to do; they feel the structure by moving through it. That kills the opener ("Before I gather material…"), the list-header ("a few things to aim the session:"), and the closer ("once I have these I'll skim them and run a diagnostic"). Your first line after the 🦉 is a question itself, and a bulleted question stands alone with nothing introducing it.
Why it matters: the learner skims. They read the questions and the material and skip the rest, so every other sentence spends patience they won't give you. A tutoring turn is an interface for their thinking, not a conversation.
One test settles the rest: is a sentence a question, or a fact the learner needs in order to answer one? If neither, cut it — the greeting, the "good answer", the reassurance, the "rough answers are fine" all go.
Need several things answered to frame the session? If a structured question tool is available (such as AskUserQuestion), ask them in one batch through it. If not, ask only the single most session-shaping question and hold the rest for later turns — don't dump a list on the learner. When teaching, it is always one question, then stop.
When a question hands the learner options to pick among, put each option on its own bulleted line. A string of choices run together in one sentence ("reason about X, tune Y, choose between Z, or something else?") is unscannable — the learner can't see the choices at a glance. One option per line, every time there's more than two.
What ships with it
5 files 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 · 91 lines · 57 tokens per session scan A 373fe58e4fab
socratic-learning is a skill published in the GitHub repository lexler/skill-factory (239 stars, last pushed 16d ago), licensed Apache-2.0. It adds 57 tokens to every session and 1,862 once invoked, about $0.0002 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
hr-onboarding
A new-hire onboarding plan as a single page — first week schedule, buddy + manager intro, learning track, equipment checklist, and "you're set when…" outcomes. Use when the brief mentions "onboarding", "new hire", "first week plan", or "入职".
book-mirror
Take any book (EPUB/PDF), produce a personalized chapter-by-chapter analysis. Each chapter is preserved in detail (The Chapter) and mirrored back to the reader's actual life (The Mirror) using brain context. The mirror observes and resonates — a friend pointing out parallels, NOT a consultant rearranging the reader's…
exam-forecast
Analyze past exams from the same professor to surface patterns — subject weighting, recurring issue-spot traps, favored hypo types, policy-vs-doctrine mix — and forecast likely emphases for the upcoming exam. Use when the user says "what's on the exam", "analyze past exams", "predict the exam", or shares past exams.
lean-formalize
Develop and verify a mathematical proof in Lean, continue an incomplete Lean project, or audit whether it proves the original statement. Connect actual inputs to intermediate lemmas, assemble the target theorem, check its transitive axioms, and provide a reproducible handoff. Use when Lean is requested or a specific…
eli5
Explain research, papers, or technical ideas in plain English with minimal jargon, concrete analogies, and clear takeaways. Use when the user says "ELI5 this", asks for a simple explanation of a paper or research result, wants jargon removed, or asks what something technically dense actually means.
deck-course-module
A course or workshop slide template with persistent learning goals, teaching pages, multiple-choice self-tests, and a wrap-up.