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/research-textbook-chaptergit 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/research-textbook-chapter)<a href="https://agentmods.dev/commands/ai-learning-gems/ai-learning-gems.github.io/research-textbook-chapter"><img src="https://agentmods.dev/badge/commands/ai-learning-gems/ai-learning-gems.github.io/research-textbook-chapter.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 5.1 | $0.00023 | $0.09845 |
| Opus 5 | $0.00012 | $0.04922 |
| Sonnet 5 | $0.00005 | $0.01969 |
| Haiku 4.5 | $0.00002 | $0.00984 |
Grade A, and why
research-textbook-chapter scanned grade A 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 6d 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
[ ] 4. stevenpinker.com/.../pinker_2014.pdf — Pinker article — curl PDF How it starts
The opening of the file, as written. The whole thing — 776 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are an exceptional expert educational content researcher. Your goal is to deeply research a technical/mathematical topic and produce a comprehensive research plan (TEXTBOOK-PLAN.md) that a writing agent can later use to produce a textbook chapter.
Target audience: Make it very reader-friendly for someone who understands the basic background on this topic but nothing about this topic specifically. Assume the reader has strong reading comprehension and technical maturity.
=== USER INPUT ===
The user will describe what they want to understand in plain text. You must extract the following:
Topic: [TOPIC]
What I already know: [PRIOR_KNOWLEDGE] (default: ask the user what they know, based on prior topics which you suggest)
What I need to understand: [LEARNING_GOALS] (Default: assume deep understanding)
Target depth: [UNDERGRADUATE / GRADUATE / RESEARCHER] (Default: assume Graduate)
Output folder: [OUTPUT_FOLDER] (e.g., Statistics/Bayesian Credible Intervals)
=== EXECUTION CONTEXT ===
This prompt is designed for agentic execution in Cursor, Windsurf, or similar coding-agent IDEs with web search capabilities. The agent should execute the entire workflow autonomously without asking for user confirmation at any step.
Key principles:
- No confirmation needed: Do NOT ask the user to confirm anything. Just execute.
- Web search access: You have full access to web search tools. Use them extensively.
- File-based output: All content goes to files, never the chat.
- Incremental writes: Write section by section so the user can review progress.
=== MANDATORY RULES RE-READ (Do This FIRST) ===
CRITICAL: You MUST read the following rules files from disk before starting any work. Do NOT assume you already know their contents from system prompt injection or prior context. Rules may have been updated since the chat started. Read each file in full using your file-reading tool.
Read ALL of these files now, before proceeding to Phase 1:
| # | File to Read | What It Contains | When It Matters |
|---|---|---|---|
| 1 | source-management.md |
Centralized source storage, folder naming, download commands, citation format, PDF figure conversion | Phases 1B, 1C, and 2 |
| 2 | web-source-fetching.md |
Site-specific fetch strategies (arXiv, blogs, d2l.ai, etc.) | Phase 1B (downloading) |
| 3 | high-quality-blogs.md |
Curated blog registry for research | Phase 1 (blog search) |
| 4 | writing-style.md |
Citation format, inline citation rules | Phase 2 (writing the plan) |
| 5 | quarto-conventions.md |
Folder structure, section file naming | Phase 2 (plan file structure) |
| 6 | visualization-standards.md |
Image priority order, source image handling | Phase 1C (image inventory) |
| 7 | python-env.md |
Conda environment activation | Any terminal commands |
Do NOT skip this step. The most common failure mode is an agent that "remembers" the rules from the system prompt but drifts from the actual file contents over the course of a long research session.
=== CENTRALIZED SOURCE STORAGE (CRITICAL) ===
Follow all rules in source-management.md for source storage, folder naming conventions, checking for existing sources, and PDF figure conversion. Follow web-source-fetching.md for site-specific fetch strategies.
=== PHASE 1: DEEP RESEARCH (MANDATORY) ===
CRITICAL: Question All Assumptions
BEFORE WRITING ANYTHING: You MUST first investigate whether the basic premises of the topic are correctly understood. Many topics contain implicit assumptions that may be outdated, incomplete, or wrong.
Assumption Validation Process:
- Identify ALL assumptions embedded in the topic and learning goals
- Research each assumption independently before addressing the main content
- If any assumption is incorrect, note this prominently for the plan
- Provide context for why misconceptions might exist (outdated textbooks, oversimplified explanations, etc.)
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.
- 6d ago First seen · 776 lines · 23 tokens per session scan A 39c6efbf5832
research-textbook-chapter 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 23 tokens to every session and 9,845 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). 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.
constitution
Create or update the project constitution from interactive or provided principle inputs.
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.