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.
git clone --depth 1 https://github.com/huuanh20/awesome-ai-agent-skillsWrote 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/huuanh20/awesome-ai-agent-skills/learn)<a href="https://agentmods.dev/commands/huuanh20/awesome-ai-agent-skills/learn"><img src="https://agentmods.dev/badge/commands/huuanh20/awesome-ai-agent-skills/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/commands/huuanh20/awesome-ai-agent-skills/learn"><img src="https://agentmods.dev/badge/commands/huuanh20/awesome-ai-agent-skills/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 | $0.00023 | $0.00414 |
| Opus 5 | $0.00012 | $0.00207 |
| Sonnet 5 | $0.00005 | $0.00083 |
| Haiku 4.5 | $0.00002 | $0.00041 |
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 8d 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
/ck:learn — Extract Reusable Patterns
Analyze the current session and save any patterns worth reusing as skill files.
What qualifies
Extract only if the pattern is:
- Non-obvious — not just fixing a typo or standard syntax
- Reusable — applicable beyond this specific session
- Generalizable — worth activating in a future session
Good candidates:
- Error resolution patterns (root cause + fix + when it recurs)
- Non-obvious debugging techniques or tool combinations
- Library/API quirks or version-specific workarounds
- Project-specific conventions discovered during investigation
Do not extract:
- One-time issues (API outages, transient failures)
- Trivial fixes (missing semicolons, import order)
- Patterns already covered by existing skills
Process
- Review the session for extractable patterns
- Pick the single most valuable insight (one skill per run)
- Draft the skill file using the format below
- Show the draft and ask for confirmation before saving
- Save to
.claude/skills/learned/{pattern-name}.md
Skill file format
Use SKILL.md format so the skill is discoverable by the skills system:
---
name: {pattern-name}
description: >
{One-line trigger description — when should this activate?
Be specific enough that Claude will recognize the situation.}
type: learned
extracted: {YYYY-MM-DD}
---
## Problem
{What goes wrong — be specific about symptoms}
## Root Cause
{Why it happens}
## Solution
{The fix or technique}
## Example
{Code or command example if applicable}
## When to apply
{Trigger conditions — what situation activates this pattern}
Save to .claude/skills/learned/{pattern-name}/SKILL.md so the skills index picks it up.
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.
- 8d ago First seen · 66 lines · 23 tokens per session scan A ab44083aa898
learn is a command published in the GitHub repository huuanh20/awesome-ai-agent-skills (1 stars, last pushed 1mo ago), licensed MIT. It adds 23 tokens to every session and 414 once invoked, about $0.0001 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 2026-09-03.
Other commands, from other repositories
awesome-chatgpt
Search awesome-ChatGPT-repositories for open-source GitHub repositories related to ChatGPT and LLMs.
prompts
Search and discover AI prompts from prompts.chat.
diagrams
Analyze the provided code, architecture, or concept and generate a clear, well-structured Mermaid diagram that visualizes the relationships, flow, or structure.
code-review
Perform a thorough code review that verifies functionality, maintainability, and security before approving a change. Focus on architecture, readability, performance implications, and provide actionable suggestions for improvement.
git-commit
Create a git commit for the current changes using Conventional Commits-style format.
security-audit
Command "security-audit" from adriannoes/awesome-agentic-ai, covering security audit, steps and security checklist.