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 ManceRayder42/jarvis-os --skill learngit clone --depth 1 https://github.com/ManceRayder42/jarvis-osWrote 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/mancerayder42/jarvis-os/learn)<a href="https://agentmods.dev/skills/mancerayder42/jarvis-os/learn"><img src="https://agentmods.dev/badge/skills/mancerayder42/jarvis-os/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/mancerayder42/jarvis-os/learn"><img src="https://agentmods.dev/badge/skills/mancerayder42/jarvis-os/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 | $0.00121 | $0.00924 |
| Opus 5 | $0.00060 | $0.00462 |
| Sonnet 5 | $0.00024 | $0.00185 |
| Haiku 4.5 | $0.00012 | $0.00092 |
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 9d 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 — 88 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Learn — book & study notes archive
The user is building a personal knowledge repository of what they read and study, one file per book/material, living flat under <hub>/learning/. This skill's job is capturing what they actually say — never inventing content — and keeping the archive tidy enough that it compounds instead of rotting.
The standing rule applies here without exception: when synthesizing notes, do not include anything the user didn't write. No chapter summaries pulled from a book's general reputation, no filled-in gaps. If they haven't told you something, it isn't in the file.
Workflow
1. Identify the book/material
Read <hub>/learning/index.md (create it if missing — see below) to see what's already tracked.
- If the user names the book/material explicitly, or there's exactly one book with status
reading, use it — no need to ask. - If it's genuinely ambiguous (multiple books in progress, or nothing suggests which one), ask: "Which book/material — or a new one?" and list the known titles from the index. Never guess silently.
- New title mentioned → treat as a new book (step 3 creates its file).
2. Append the note
Slug the title (the-lean-startup, atomic-habits, etc.) → <hub>/learning/<slug>.md.
Append under a ## Conclusions section, dated:
### YYYY-MM-DD
<exactly what the user wrote — their words, lightly cleaned up for readability, nothing added>
If the file doesn't have a ## Conclusions section yet, add it.
3. New book — create the file
No existing file for this title → create <hub>/learning/<slug>.md:
---
type: learning
title: <Book Title>
author: <Author, if known — omit the line if not>
status: reading
started: YYYY-MM-DD
updated: YYYY-MM-DD
tags: [learning]
---
# <Book Title>
## Conclusions
Ask for the author if the user didn't mention it and it's not obvious — don't guess a real book's author from memory either; if you're confident from common knowledge, it's still safer to state it as inferred rather than presented as something the user said (keep it out of anything framed as "their words").
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.
- 9d ago First seen · 88 lines · 121 tokens per session scan A cbfeb7791d4d
learn is a skill published in the GitHub repository ManceRayder42/jarvis-os (5 stars, last pushed 4d ago), licensed MIT. It adds 121 tokens to every session and 924 once invoked, about $0.0006 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
analyze
Reads input artifact(s) — codebase, planning session, refactor plan, or generic doc — and writes a tour-spec.json describing sections, embedded sources, cross-refs, quizzes, and external link maps. Use when the user wants a fresh learning guide built from source material; auto-hands-off to learning-guide:render.…
confidence-gate
When you're about to claim success ("fixed", "done", "works", "passing tests") at the end of a turn, verify the claim is backed by actual evidence in this session. presence's Stop hook will flag a success claim that has no recent test/build pass behind it. Be aware of this gate and either run the verification, or…
ccc-research
In addition to web search, research can use connected channels as surfaces.
developer-growth-analysis
Analyzes your recent Claude Code chat history to identify coding patterns, development gaps, and areas for improvement, curates relevant learning resources from HackerNews, and automatically sends a personalized growth report to your Slack DMs.
create-slidev-presentation
Build or edit Slidev (sli.dev) presentations for tech talks, workshops, conference sessions, and live-coding demos. Use when the user asks to create slides, a deck, a presentation, a workshop deck, a conference talk, or edit an existing slides.md.
explain
On-demand deep teaching — explains how Compass works, or walks you (or a stakeholder) through a specific build, at whatever depth you want. The "help me understand this" surface. Invoked when the user asks to understand Compass or a build; not a user menu entry (user-invocable:false).