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/cookys/autopilot/learnnpx skills add cookys/autopilot --skill learngit clone --depth 1 https://github.com/cookys/autopilotWhat 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 | $0.00139 | $0.01471 |
| Opus 5 | $0.00069 | $0.00736 |
| Sonnet 5 | $0.00028 | $0.00294 |
| Haiku 4.5 | $0.00014 | $0.00147 |
Grade B, and why
learn scanned grade B with 1 finding 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 2d 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.
Reads agent configuration directoriesmediumAgent snooping
.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.
grep -ri "<keyword>" .claude/knowledge/*.md How it starts
The opening of the file, as written. The whole thing — 187 lines — stays where its author put it; the contents beside it link to each section on GitHub.
learn
Record reusable knowledge so future sessions avoid the same mistakes.
When to Record
| Trigger | Category |
|---|---|
| Bash command failed on path/config, then fixed | env |
| Compile error took 2+ retries to fix | build |
| Searched 3+ times to find a file/class | env |
| API usage was wrong, then corrected | api |
| Architecture decision required iteration | arch |
Flow
-
Dedup check — search existing knowledge before writing:
grep -ri "<keyword>" .claude/knowledge/*.md- Already recorded and complete: skip
- Recorded but incomplete: update existing entry (Edit)
- Not found: add new entry
-
Read the target knowledge file (by category):
build-errors.md|debug-patterns.md|architecture.md|environment.md
-
Append entry using this template:
## [Title] **Date**: YYYY-MM-DD | **Context**: what you were doing **Problem**: what went wrong **Solution**: what fixed itAdd
**Failed attempts**:and**Related**:lines only when they add value. -
Update INDEX.md "recent learning" table
-
Rotate — keep recent list at 10 entries max:
# If your project has a rotate script: node .claude/scripts/learn-rotate.js # Otherwise: manually trim the oldest entries
Categories
| Category | File | Content |
|---|---|---|
build |
build-errors.md |
Compile/link/CMake errors |
debug |
debug-patterns.md |
Debugging techniques, crash patterns |
arch |
architecture.md |
Design decisions, pitfalls |
env |
environment.md |
Paths, Docker, config |
api |
(in relevant file) | API misuse patterns |
Invocation
/learn [category] [brief description]
Examples:
/learn build Missing dependency — install with apt/brew/pip
/learn env Script path wrong — use relative path from project root
Session Learning Summary (L-size)
At the end of L-size tasks, produce a structured summary before the dev-flow session-end phase:
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.
- 2d ago First seen · 187 lines · 139 tokens per session scan B 64e2b6226be2
learn is a skill published in the GitHub repository cookys/autopilot (11 stars, last pushed 2d ago), licensed MIT. It adds 139 tokens to every session and 1,471 once invoked, about $0.0007 per session on Opus 5. A static security scan graded it B with 1 finding (reads agent configuration directories). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
article-writing
Write articles, guides, blog posts, tutorials, newsletter issues, and other long-form content in a distinctive voice derived from supplied examples or brand guidance. Use when the user wants polished written content longer than a paragraph, especially when voice consistency, structure, and credibility matter.
a-evolve
Apply A-Evolve's agentic evolution methodology to improve AI agent performance across runs. Use when the user wants to diagnose agent failures, generate targeted skills from error patterns, evolve system prompts, or accumulate episodic knowledge. Works standalone or inside AutoResearchClaw pipelines. Triggers on…
hive.chart-creation-foundations
Required reading whenever any chart tool is available. Teaches the one-tool embedding contract (call chartrender → live chart appears in chat AND a downloadable PNG lands in the queen session dir), the ECharts (data viz) vs Mermaid (structural diagrams) decision, the BI/financial-grade aesthetic baseline (no…
deck-course-module
暖纸背景 + Playfair, 左侧学习目标常驻, 含 MCQ 自测页.
code-documenter
Use when adding docstrings, creating API documentation, or building documentation sites. Invoke for OpenAPI/Swagger specs, JSDoc, doc portals, tutorials, user guides.
creating-skills
Guide for creating Claude Code skills following Anthropic's official best practices. Use when user wants to create a new skill, build a skill, write SKILL.md, update an existing skill, or needs skill creation guidelines. Provides structure, frontmatter fields, naming conventions, and new features like dynamic context…