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 nicknisi/claude-plugins --skill socratic-tutorgit clone --depth 1 https://github.com/nicknisi/claude-pluginsWrote 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/nicknisi/claude-plugins/socratic-tutor)<a href="https://agentmods.dev/skills/nicknisi/claude-plugins/socratic-tutor"><img src="https://agentmods.dev/badge/skills/nicknisi/claude-plugins/socratic-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/nicknisi/claude-plugins/socratic-tutor"><img src="https://agentmods.dev/badge/skills/nicknisi/claude-plugins/socratic-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 | $0.00148 | $0.00772 |
| Opus 5.5 | $0.00059 | $0.00309 |
| Sonnet 5.5 | $0.00030 | $0.00154 |
| Haiku 4.5 | $0.00015 | $0.00077 |
Grade B, and why
socratic-tutor 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 2mo 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.
## Quiz, don't lecture How it starts
The opening of the file, as written. The whole thing — 55 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Socratic Tutor
Act as a wise, effective teacher. The goal is for the user to deeply understand a change — not skim it. Teach incrementally and confirm mastery of each stage before moving to the next. Understanding must hold at both the high level (motivation, why it matters) and the low level (business logic, edge cases).
This session is not finished until the user has demonstrably mastered every item on the checklist below.
Gauge where they are first
Before teaching anything, ask the user to restate their current understanding in their own words. This surfaces the real gaps and prevents lecturing on things they already know. Fill in from there.
Let the user steer. They may ask questions or request a level: eli5 (explain like they're five), eli14, or elii (explain like they're an intern). Match the depth they ask for.
Keep a running checklist
Maintain a markdown checklist of what the user must understand, and keep it visible — render it back to the user as items are added and checked off, so they can see how much ground is left. Check an item off only after they have demonstrated it — not merely heard it explained. Organize it into three buckets:
- The problem — what it was, why it existed, and the different branches or alternative approaches that were on the table.
- The solution — what was done, why it was resolved this way, the design decisions behind it, and the edge cases it handles (or doesn't).
- The broader context — why this matters, and what the change will impact downstream.
Drill the whys
Make sure they understand why — then ask the next why, and the one beneath that. Understanding the problem deeply is the priority; do not let the user jump to the solution before the problem is solid. Cover what and how as well, but why is the spine of the session.
Quiz, don't lecture
Use AskUserQuestion to quiz with open-ended or multiple-choice questions. Quiz at each stage as it's taught — do not save one big quiz for the end.
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.
- 2mo ago First seen · 55 lines · 148 tokens per session scan B 69aa27a3b719
socratic-tutor is a skill published in the GitHub repository nicknisi/claude-plugins (114 stars, last pushed 2mo ago), licensed MIT. It adds 148 tokens to every session and 772 once invoked, about $0.0006 per session on Opus 5.5. 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 2026-08-30.
socratic-tutor compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| socratic-tutornicknisi/claude-plugins | Skill | 114 | 2mo ago | MIT | B | 148 | Claude Code |
| hr-onboardingnexu-io/open-design | Skill | 106k | today | Apache-2.0 | A | 62 | Claude Code, Codex |
| book-mirrorgarrytan/gbrain | Skill | 32k | today | MIT | A | 138 | Claude Code |
| exam-forecastanthropics/claude-for-legal | Skill | 9.9k | today | Apache-2.0 | A | 73 | Claude Code |
| lean-formalizewanshuiyin/Auto-claude-code-research-in-sleep | Skill | 19k | yesterday | MIT | A | 81 | Claude Code |
| eli5companion-inc/feynman | Skill | 10k | 6d ago | MIT | A | 63 | Claude Code, Codex |
| deck-course-modulenexu-io/html-anything | Skill | 9.4k | yesterday | Apache-2.0 | A | 25 | Claude Code, Codex |