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 alessiomarcone/agent-fieldbook --skill learngit clone --depth 1 https://github.com/alessiomarcone/agent-fieldbookWrote 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/alessiomarcone/agent-fieldbook/learn)<a href="https://agentmods.dev/skills/alessiomarcone/agent-fieldbook/learn"><img src="https://agentmods.dev/badge/skills/alessiomarcone/agent-fieldbook/learn/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/alessiomarcone/agent-fieldbook/learn"><img src="https://agentmods.dev/badge/skills/alessiomarcone/agent-fieldbook/learn.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 | $0.00077 | $0.00481 |
| Opus 5 | $0.00039 | $0.00241 |
| Sonnet 5 | $0.00015 | $0.00096 |
| Haiku 4.5 | $0.00008 | $0.00048 |
Grade A, and why
learn 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 3d 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.
What it actually says
Learn
Build a focused official learning path with accurate resource types, durations, and direct links.
Catalogs
references/claude-courses.csv— 25 official Anthropic courses.references/claude-tutorials.csv— 67 official Anthropic tutorials.references/codex-learning-resources.csv— verified OpenAI courses, guides, videos, resources, and live series.
Procedure
- Resolve product, goal, starting level, weekly time, and target date when they affect the plan.
- Read the relevant catalogs and select the minimum sequence that reaches the goal.
- Label each item with its real type. Never present a guide, video, workshop, or live event as a self-paced course.
- Use only stated durations; write “not stated” when the official source gives none.
- Add one practical exercise after each learning block.
- Use at most three resources per week and end with one concrete next action.
Default sequences
- Claude foundations: Claude 101 → AI capabilities and limitations → AI Fluency: Framework & Foundations.
- Claude Code: Claude Code 101 → Claude Code in Action → Agent Skills → Subagents → MCP.
- Codex foundations: AI Foundations → Codex Quickstart → Prompting/Best practices → one real task.
- Codex agent workflows: Applied AI Foundations → Agents and Workflows →
AGENTS.md→ Skills → Subagents. - Codex advanced: permissions/sandboxing → plugins → SDK/non-interactive mode → automation and review.
Output contract
Return a table with week, resource, type, duration, practical outcome, exercise, and direct link. Close with total stated time, catalog verification date, and one next step.
Boundaries
- Do not invent resources, duration, or certification status.
- Flag live events with their date and verify availability before recommending them.
- Answer in the user's language.
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.
- 3d ago Changed b55fb628021d
- 8d ago First seen · 42 lines · 77 tokens per session scan A 373eea447c94
learn is a skill published in the GitHub repository alessiomarcone/agent-fieldbook (5 stars, last pushed yesterday), licensed MIT. It adds 77 tokens to every session and 481 once invoked, about $0.0004 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.
Other skills, from other repositories
deep-research
Deep research report generation for Reviva's built-in deep-researcher agent. Use for learning and education research, teacher preparation research, document-based synthesis, literature/source reviews, office research, industry analysis, competitor scans, policy interpretation, and any request for a cited long-form…
cet-skill
CET-4 and CET-6 exam preparation coach for original CET-style practice, diagnostic feedback, writing and translation correction, reading/listening drills, and study planning.
study-companion-en
General study companion for learning, review, exam prep, exam-point analysis, syllabus/exam-outline interpretation, finals speedrun teaching, concept explanation, problem solving, homework coaching, error analysis, active recall, flashcards, study plans, visualizations, animations, simulations, coding practice…
math-explainer
A skill for creating animated math explanations with Manim, a Python tool for mathematical animations, and interactive web pages.
concept-visualization-generator
Design and generate concept-first learning artifacts: concept cards, visual explanations, diagrams, interactive HTML demos, Manim/math visualizations, matplotlib scientific plots, misconception checks, and short retrieval practice. Use this skill whenever the user wants to understand, teach, review, visualize, make a…
feynman-learning-coach
Guide users through the Feynman Technique by asking them to explain a concept in simple language, diagnosing gaps, correcting misunderstandings, simplifying explanations, and retesting understanding. Use for deep learning, concept mastery, document-based study, exam preparation, and teach-back practice.