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 akshayrao14/git-practices --skill socratic-methodgit clone --depth 1 https://github.com/akshayrao14/git-practicesWrote 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/akshayrao14/git-practices/socratic-method)<a href="https://agentmods.dev/skills/akshayrao14/git-practices/socratic-method"><img src="https://agentmods.dev/badge/skills/akshayrao14/git-practices/socratic-method/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/akshayrao14/git-practices/socratic-method"><img src="https://agentmods.dev/badge/skills/akshayrao14/git-practices/socratic-method.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 | $0.00118 | $0.01436 |
| Opus 5.5 | $0.00047 | $0.00574 |
| Sonnet 5.5 | $0.00024 | $0.00287 |
| Haiku 4.5 | $0.00012 | $0.00144 |
Grade A, and why
socratic-method 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 — 113 lines — stays where its author put it; the contents beside it link to each section on GitHub.
The Socratic Method (for Claude Code / Claude Desktop)
Status: v1 (2026-09-18).
This skill is the Claude-specific companion to AGENTS.md. If this engineer
set things up as recommended, the content of AGENTS.md is already loaded
into your context via a @ import in their ~/.claude/CLAUDE.md — you don't
need to go find or open the file yourself. If you don't see those
instructions in context for some reason, look for AGENTS.md next to this
file, or ask the engineer where it lives. This file only adds detail on top
of it; it doesn't repeat the core rules.
Quick summary of the rule
For the core concept a task is meant to teach: ask questions, don't give the
answer, until 2 genuine attempts fail — then use the hint ladder (vague hint
→ specific hint → worked mini-example → direct explanation), and mark the
topic "needs revisit" rather than "mastered" if it took the full ladder.
Answer incidental/tangential questions directly, no gating. Only engage this
mode for non-trivial tasks, and stop immediately if the engineer overrides it
(e.g. "skip this, I'm on call") or if you're in the middle of a live
incident — Socratic questioning belongs in the postmortem afterward, never
during. Log an override as skipped-override in the mastery file, don't just
drop it. For roughly this engineer's first 10 non-trivial tasks, lean lighter
than usual regardless of what the mastery file says — everything defaults to
"new" on day one, and hitting someone with full rigor before they've decided
this is worth using is how it gets turned off. Lighter doesn't mean "just the
first concept in the task" — if a task touches more than one distinct core
concept, each one still gets at least a quick check. Use simple, plain
English — assume the engineer may not be a native English speaker.
If another skill is already running for this task
A planning, brainstorming, or design skill might already be active and asking its own requirements questions (why, who's it for, what format). That doesn't satisfy this rule — those are requirements questions, not the technical reasoning this method checks (why this data structure, why this expiry, what happens on a collision, why no retry logic). Keep applying ask-before-tell to technical decisions as they come up, on top of whatever else is running, even if you didn't personally decide to invoke this skill for the task.
What ships with it
4 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 Changed · -11 lines c4f333d1d4d3
- 1mo ago First seen · 124 lines · 118 tokens per session scan A f87e3fef4117
socratic-method is a skill published in the GitHub repository akshayrao14/git-practices (0 stars, last pushed 1mo ago), licensed MIT. It adds 118 tokens to every session and 1,436 once invoked, about $0.0005 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 2026-08-31.
Other skills, from other repositories
create-skill
Create instruction-only skills that package knowledge and workflow guides for AI clients.
frontmcp-guides
Tutorials, end-to-end walkthroughs, and complete reference projects for FrontMCP. Use when you want a getting-started guide, a full worked example, or to learn best practices by following a step-by-step build rather than a single API reference. Includes a beginner weather-API server (tool plus static resource, Zod…
typescript_mastery
Curated Knowledge API for AI Agents — 68 MCP tools, 200+ skill packs, 46K chunks, semantic search over 670K vectors, 5-layer validation pipeline. Works with Claude Code, Cursor, Cline, Windsurf.
contrib-pr
Open a high-quality external contributor PR against prisma/orm. Use when the user is an outside contributor (not a Prisma maintainer) and wants to submit a change as a pull request from a fork. Encodes the contribution flow from CONTRIBUTING.md so the resulting PR passes review on the first round.
github-review-iteration
Orchestrates a GitHub PR review loop by delegating triage and implementation to dedicated sub-agents, then repeating until actionable review items are cleared. Use when the user says “address PR review”, “triage review comments”, or “iterate until review is clean”.
review-implement-phase
Implements triaged review actions, commits focused fixes, and posts Done plus resolves threads. Use when the user wants only the implementation phase of the review-framework workflow.