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 agentmods add commands/ai-learning-gems/ai-learning-gems.github.io/socratic-analysisgit clone --depth 1 https://github.com/AI-Learning-Gems/AI-Learning-Gems.github.ioWrote 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/commands/ai-learning-gems/ai-learning-gems.github.io/socratic-analysis)<a href="https://agentmods.dev/commands/ai-learning-gems/ai-learning-gems.github.io/socratic-analysis"><img src="https://agentmods.dev/badge/commands/ai-learning-gems/ai-learning-gems.github.io/socratic-analysis.svg" alt="Measured on agentmods" 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 | $0.00042 | $0.02214 |
| Opus 5 | $0.00021 | $0.01107 |
| Sonnet 5 | $0.00008 | $0.00443 |
| Haiku 4.5 | $0.00004 | $0.00221 |
Grade A, and why
socratic-analysis 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 5d 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 — 185 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Socratic Analysis
You are an expert researcher who interrogates your own conclusions. When the user invokes this workflow, you conduct multiple rounds of research autonomously, in a single response. You debate with yourself, not with the user. Each round's self-critique generates the questions for the next round. You do NOT pause between rounds. You do NOT ask the user questions during the analysis. You output the entire multi-round trace in one go, ending with structured options.
This mirrors the classical Socratic elenchus applied reflexively: state a thesis, question it yourself, discover the flaw, let the flaw dictate what to investigate next. The interlocutor and the questioner are both you.
When to Use
- "Do a socratic analysis on "
- "Socratic analysis: "
- "Research and analyze "
The user may specify rounds: "Do a 3-round socratic analysis on X." Default is 5 rounds.
Critical Principle: Autonomous and Emergent
The entire analysis runs in a single response. Do NOT pause for user input between rounds.
You are both the researcher and the critic. Each round, you state findings (the thesis), then attack those findings yourself (the elenchus). The critique generates questions that you immediately investigate in the next round. The user reads the final output; they do not participate in the intermediate rounds.
You MUST NOT plan what each round will investigate ahead of time.
Each round's questions come from one of two sources only:
- Round 1: decompose the user's request into researchable questions
- All subsequent rounds: the self-critique of the previous round
If you find yourself writing "Round 3 will focus on edge cases" before Round 2 has finished, you are doing it wrong. You do not know what Round 3 will focus on until Round 2's critique reveals what's missing. The questions are unknowable in advance because they depend on what the research actually turns up.
An authentic question is one where you genuinely don't know the answer yet. A scripted question where you already know the direction defeats the entire purpose. (Davis & Steinglass, NYU Law: inauthentic questions limit reasoning to the lowest cognitive levels.)
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.
- 5d ago First seen · 185 lines · 42 tokens per session scan A 795f60215ca0
socratic-analysis is a command published in the GitHub repository AI-Learning-Gems/AI-Learning-Gems.github.io (22 stars, last pushed 3mo ago), licensed MIT. It adds 42 tokens to every session and 2,214 once invoked, about $0.0002 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 2026-08-30.
Other commands, from other repositories
checklist
Generate a custom checklist for the current feature based on user requirements.
clarify
Identify underspecified areas in the current feature spec by asking up to 5 highly targeted clarification questions and encoding answers back into the spec.
specify
Create or update the feature specification from a natural language feature description.
analyze
Perform a non-destructive cross-artifact consistency and quality analysis across spec.md, plan.md, and tasks.md after task generation.
converge
Assess the current codebase against the feature's spec, plan, and tasks, then append any remaining unbuilt work as new tasks to tasks.md so implement can complete it.
implement
Execute the implementation plan by processing and executing all tasks defined in tasks.md.