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 skills/smk-labs/claude-plugins/learnnpx skills add smk-labs/claude-plugins --skill learngit clone --depth 1 https://github.com/smk-labs/claude-pluginsWrote 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/smk-labs/claude-plugins/learn)<a href="https://agentmods.dev/skills/smk-labs/claude-plugins/learn"><img src="https://agentmods.dev/badge/skills/smk-labs/claude-plugins/learn.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 | $0.00136 | $0.01264 |
| Opus 5 | $0.00068 | $0.00632 |
| Sonnet 5 | $0.00027 | $0.00253 |
| Haiku 4.5 | $0.00014 | $0.00126 |
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 4d 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 — 79 lines — stays where its author put it; the contents beside it link to each section on GitHub.
learn: continue, or decide how to start
One job: get the learner to the next useful thing in as few words as possible. Never re-plan, never restart, never interview them about something a file already answers.
First, look
Check the current directory and the obvious candidates for an existing course. A course is a folder containing STATE.md and TOC.md.
STATE.mdexists here or in a folder the learner names. Go to Continue.- Nothing exists. Go to Start.
- Several courses exist in subfolders. Show them in a card with where each one stopped, and let the learner pick.
Continue
Read STATE.md, then the chapter file it names. Read PROFILE.md once. Read the course's CLAUDE.md and follow it exactly: it is the teaching protocol for this specific course and it outranks your habits.
Give a three-line status: where we are, what is done, what is next. Then start the next lesson immediately. Do not ask permission.
Two cases worth handling cleanly:
- The chapter file does not exist yet. The book has run out. Say so in one line and offer
/learnable:new-bookto write the next one. STATE.mdsays a chapter is half finished. Resume at the named lesson, not at the start of the chapter. Do not re-teach lessons already marked done, and do not summarize them either unless asked. Learners resent being walked back through material they finished.
Start
Nothing exists yet. Ask exactly one thing: what do they want to learn. Then offer the two ways in, in a card, with a picker after it.
- Measure my level first.
/learnable:self-assessruns a placement quiz, then the course gets built around the gaps it finds. Costs about half an hour and makes everything after it sharper. - Just build the course.
/learnable:new-coursegoes straight to work, asks a couple of questions about their level, and assumes a standard ladder.
Recommend the first when they are experienced in the field and their gaps are probably not where they think, and the second when they are a genuine beginner in the subject, where a quiz would only confirm that they know nothing yet.
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.
- 4d ago First seen · 79 lines · 136 tokens per session scan A ad85acea00cf
learn is a skill published in the GitHub repository smk-labs/claude-plugins (11 stars, last pushed 2d ago), licensed MIT. It adds 136 tokens to every session and 1,264 once invoked, about $0.0007 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 skills, from other repositories
memory
Use this skill when the user asks to "update my PM Copilot memory", "save this to my profile", "remember that", "update my context", "update my product context", "save this decision", "add this to my memory", "track this risk", "mark this risk as resolved", "add a lesson learned", "save these stakeholder notes", or…
ab-test-analysis
Analyze A/B test results with statistical significance, sample size validation, confidence intervals, and ship/extend/stop recommendations. Use when evaluating experiment results, checking if a test reached significance, interpreting split test data, or deciding whether to ship a variant.
brainstorm-okrs
Brainstorm team-level OKRs aligned with company objectives — qualitative objectives with measurable key results. Use when setting quarterly OKRs, aligning team goals with company strategy, drafting objectives, or learning how to write effective OKRs.
pre-mortem
Run a pre-mortem risk analysis on a PRD or launch plan. Categorizes risks as Tigers (real problems), Paper Tigers (overblown concerns), and Elephants (unspoken worries), then classifies as launch-blocking, fast-follow, or track. Use when preparing for launch, stress-testing a product plan, or identifying what could go…
shipping-artifacts
The durable documentation set that makes an AI-built (vibe-coded) app reviewable before shipping. A small core every app needs — architecture, user/permission flows, permissions, variables/secrets, and a test-coverage map — plus conditional docs added only when they apply: emails, scheduled work, SEO, and embedded…
growth-loops
Identify growth loops (flywheels) for sustainable traction. Evaluates 5 loop types: Viral, Usage, Collaboration, User-Generated, and Referral. Use when designing growth mechanisms, building product-led traction, or understanding how growth loops work.