learn

A skill-discovery and installation guide that searches agentskill.sh, a directory of skills for AI agents. It also supports managing installed skills and rating them.

In plain words
What is it for?
Use it to search for skills, find an extension for a task, install or update skills, list installed skills, check available versions, and rate skills after using them.
Why use it?
It saves you from manually browsing a large skills catalogue and explains how to choose and install an extension. It also provides platform-specific instructions for confirming selections.

Skill for Claude CodeCodex

Part of the learn plugin — 2 skills shipped together

Install

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.

agentmods
npx agentmods add skills/agentskill-sh/ags/learn
Any agent
npx skills add agentskill-sh/ags --skill learn
Clone the repo
git clone --depth 1 https://github.com/agentskill-sh/ags

Made for: Claude Code, Codex.

Or install learn, the plugin that ships this one along with the rest of its 2 skills.

Per session 115 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 3,363 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00115 $0.03363
Opus 5 $0.00057 $0.01682
Sonnet 5 $0.00023 $0.00673
Haiku 4.5 $0.00012 $0.00336

Measured 3d ago against content hash e6b59a320ace, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

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.

skills/learn/SKILL.md · 349 lines

How it starts

The opening of the file, as written. The whole thing — 349 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Learn — Find & Install Agent Skills

Search 100,000+ skills from agentskill.sh. Delegates all operations to the ags CLI via npx @agentskill.sh/cli. The CLI is auto-downloaded by npx on first use.

All commands below use npx @agentskill.sh/cli with --json for structured output.


Platform Interaction

Different agent platforms have different tools for user interaction. Adapt your approach based on what's available.

If AskUserQuestion tool is available (Claude Code, Cursor, etc.):

  • Use AskUserQuestion for all user selections (creates interactive buttons)
  • Include header, question, and labeled options with descriptions
  • Max 4 options per question (tool limit)

If AskUserQuestion tool is NOT available (OpenHands, Codex, Aider, etc.):

  • Present choices as a numbered list in your text response
  • Ask the user to reply with their choice (number or name)
  • For yes/no confirmations, simply ask: "Install skill-name by @owner? (yes/no)"

Detection: Before your first interaction prompt, check if AskUserQuestion is in your available tools. Cache this detection for the session.


Commands

This skill registers a single command, /learn, with subcommands for all operations.

/learn <query> — Search for Skills

When the user runs /learn followed by a search query, search for matching skills.

Steps:

  1. Run via Bash: npx @agentskill.sh/cli search "<query>" --json --limit 5
  2. Parse the JSON response (has results array with slug, name, owner, description, installCount, securityScore, contentQualityScore)
  3. Display results using a clean markdown table format:
    ## Skills matching "<query>"
    
    | # | Skill | Author | Installs | Security |
    |---|-------|--------|----------|----------|
    | 1 | **<name>** | @<owner> | <installCount> | <securityScore>/100 |
    ...
    
    **Descriptions:**
    1. **<name>**: <description (first 80 chars)>
    ...
    
  4. Present interactive selection (see Platform Interaction section):
    • If AskUserQuestion is available: create options from search results (max 4), label = skill name, description = "@, installs, Security: /100", header = "Install", question = "Which skill would you like to install?"
    • If not available: present a numbered list and ask the user to reply with their choice
  5. If user selects a skill, proceed to the Install Flow below
  6. If user selects "Other" or asks to do something else, accommodate

Read the full file on GitHub · 349 lines

Files

What ships with it

1 file 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.

Changes

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.

  1. 3d ago First seen · 349 lines · 115 tokens per session scan A e6b59a320ace

Subscribe to this mod's changes

learn is a skill published in the GitHub repository agentskill-sh/ags (35 stars, last pushed 3mo ago), licensed MIT. It adds 115 tokens to every session and 3,363 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 2026-08-30.

Related

Other skills, from other repositories

copilotkit-upgrade

Use when migrating a CopilotKit v1 application to v2 -- updating package imports, replacing deprecated hooks and components, switching from GraphQL runtime to AG-UI protocol runtime, and resolving breaking API changes.

CopilotKit/CopilotKit · 48 tokens

babysit

Same-session monitoring loop for PRs, CI runs, tickets, and deployments using the monitorstart / monitorupdate / autonudgestop MCP tools. The loop re-injects your check instructions into THIS session on an idle interval — same context, same tools — and works from dashboard chat, Slack threads, and Discord DMs. Use…

kirodotdev/KiroCrew · 137 tokens

mochi-plan

INTERNAL pet queue — generates the pet's 30-minute behavior schedule (moves, moods, notifications). NOT for user task or calendar planning.

kirodotdev/KiroCrew · 33 tokens

explain-for

Explain a topic, a piece of code, an error, or a design decision calibrated to one named audience — a 5-year-old, a 5th grader, a manager, a designer, a graduate student, a parent. Resolves who the explanation is for (from the request, or from what memory already records about that person), establishes the ground…

kirodotdev/KiroCrew · 102 tokens

goal-loop

Bootstrap a goal-driven self-improving AutoNudge loop. Give it a goal + anchor directory; it generates LOOP.md + GOAL.md + kanban board, then you write the Definition of Done and arm the loop. The running agent manages the board autonomously: finds issues, adds cards, resolves them, handoffs to Review, repeats until…

kirodotdev/KiroCrew · 144 tokens

spec-workflow

Drive the Kiro CLI v3 spec workflow (Requirements → Design → Tasks → Execution) for the Spec Builder app. Load when authoring a spec inside a spec-builder worker slot, or when the seed prompt references a spec directory and a spec type.

kirodotdev/KiroCrew · 55 tokens