An entry point for a Socratic mentoring workflow, where the assistant teaches by asking guiding questions. It can show or change the learner's saved teaching profile; the automatic mentoring behavior is handled elsewhere.

Use it to view the current learning profile, change its settings, or check which mentoring rules are active.

It lets users inspect or adjust the mentoring level and mode used by the plugin.

socratic — Skill for Claude Code by VicBa2000

Install

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.

Any agent

npx skills add VicBa2000/socratiskill --skill socratic

Clone the repo

git clone --depth 1 https://github.com/VicBa2000/socratiskill

Made for: Claude Code.

Or install socratiskill, the plugin that ships this one along with the rest of its 2 skills, 3 hooks.

Wrote 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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/vicba2000/socratiskill/socratic.svg)](https://agentmods.dev/skills/vicba2000/socratiskill/socratic)

Your own site

<a href="https://agentmods.dev/skills/vicba2000/socratiskill/socratic"><img src="https://agentmods.dev/badge/skills/vicba2000/socratiskill/socratic.svg" alt="Measured on agentmods" height="20"></a>

Per session 61 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 5,227 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

Origin original No closer match found in the catalogue.

Token cost

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	$0.00061	$0.05227
Opus 5	$0.00030	$0.02613
Sonnet 5	$0.00012	$0.01045
Haiku 4.5	$0.00006	$0.00523

Measured yesterday against content hash 8df7312819cb, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

socratic 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 yesterday.

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.

skills/socratic/SKILL.md · 401 lines

How it starts

The opening of the file, as written. The whole thing — 401 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Socratic (mentor entry point)

This skill is the control panel for the socratiskill plugin. It does not run the socratic logic by itself — that is injected on every turn via the UserPromptSubmit hook. Here the user can inspect and mutate the persistent profile.

Persistent state lives at: ~/.claude/socratic/profile.json.

Path convention (`<plugin-root>`)

Several subcommands below invoke scripts as bun run <plugin-root>/scripts/<name>.ts or bash <plugin-root>/scripts/<name>.sh. When executing these commands, <plugin-root> resolves to the directory two levels above this SKILL.md file. Concretely:

This file lives at <plugin-root>/skills/socratic/SKILL.md.
So <plugin-root>/scripts/foo.ts is ../../scripts/foo.ts relative to this file.

When using Bash to invoke a script, resolve the absolute path by climbing two directories up from this SKILL.md and appending scripts/<name>.

Subcommands

The user invokes /socratiskill:socratic $ARGUMENTS. Dispatch by the first word:

no arguments or status -> Run bun run <plugin-root>/scripts/status.ts and show stdout verbatim. Do NOT reformat it, do not summarize it, and do not add commentary to the autonomy numbers — no congratulation, no softening of a low count, no goals. An honest number the user can act on is the product. Exit 3 = no profile; show stderr verbatim.
on -> Activate the skill: write enabled: true to profile.json. Starting next turn, the UserPromptSubmit hook will inject SOCRATIC CONTEXT and the Stop hook will record telemetry again. Respond:
```
socratiskill: enabled
SOCRATIC CONTEXT will inject on next turn.
```
off -> Deactivate the skill: write enabled: false to profile.json. Hooks remain installed but inject only a short DISABLED silencer (~30 tokens) telling the model to behave as default Claude Code. Instant toggle; does NOT require /reload-plugins or touching settings.json. Respond:
```
socratiskill: disabled
run /socratiskill:socratic on to re-enable.
```

Read the full file on GitHub · 401 lines

Files

What ships with it

14 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.

Changes

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.

yesterday Changed · +11 lines 8df7312819cb
2d ago Changed · -6 lines · +1 tokens per session 03b5674efa56
6d ago First seen · 396 lines · 60 tokens per session scan A 7cbfd4da9191

Subscribe to this mod's changes

socratic is a skill published in the GitHub repository VicBa2000/socratiskill (4 stars, last pushed yesterday), licensed MIT. It adds 61 tokens to every session and 5,227 once invoked, about $0.0003 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.

Claude Code Learning and teaching claude-code-plugin feynman mentor pedagogy programming-education

learn-from-fix

Capture Elixir/Ecto/LiveView lessons and Hex API rules. Use after corrections or when asked to document learning, record a lesson, prevent a fixed mistake, or remember package guidance with --library.

oliver-kriska/claude-elixir-phoenix · 46 tokens

elixir-idioms

OTP/BEAM patterns and Elixir idioms — GenServer, Supervisor, Task, Registry, pattern matching, with chains, pipes. Use when designing processes or debugging BEAM issues.

oliver-kriska/claude-elixir-phoenix · 44 tokens

examples

Provide Phoenix, LiveView, Ecto, OTP, or Oban examples. Use when asked for sample code, a walkthrough, a proper implementation, or expected workflow output. Pair with domain skills. NOT for debugging, direct changes, best-practice advice, or audits.

oliver-kriska/claude-elixir-phoenix · 57 tokens

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.

cbrock84/headcount · 64 tokens

engineering-onboarding

Create an onboarding guide for an engineer joining a team that consumes the design system. Trigger when someone says: onboard new engineer, developer getting started guide, new engineer guide, engineering onboarding, first day for developers, frontend onboarding, or anything about helping an engineer new to the team…

murphytrueman/design-system-ops · 68 tokens

vertical-real-estate

Residential-proptech domain knowledge so architect / pm aren't naive when speccing real-estate products (listings, lead-crm, transaction-coordination, property-mgmt). Codifies MLS/IDX reality, listing status lifecycle + syndication canonical-source, long-cycle lead nurture, transaction-coordination as the high-pain…

avelikiy/great_cto · 99 tokens