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/teejayen/arc/knowledge-extractionnpx skills add teejayen/arc --skill knowledge-extractiongit clone --depth 1 https://github.com/teejayen/arcWhat 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 | $0.00036 | $0.00484 |
| Opus 5 | $0.00018 | $0.00242 |
| Sonnet 5 | $0.00007 | $0.00097 |
| Haiku 4.5 | $0.00004 | $0.00048 |
Grade A, and why
knowledge-extraction 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 yesterday.
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
Knowledge Extraction
Capture learnings, patterns, and reusable knowledge from conversations.
When to Use
- A useful pattern or approach emerged
- Something was learned that's worth remembering
- A solution was found that might apply elsewhere
- User explicitly wants to save knowledge
Execution Steps
Step 1: Identify the knowledge
Types of extractable knowledge:
- How-to: Process or technique
- Pattern: Recurring approach or structure
- Insight: Understanding about how something works
- Reference: Facts or information worth keeping
- Lesson: Learning from experience (including failures)
Step 2: Determine destination
| Knowledge Type | Destination |
|---|---|
| Technical how-to | areas/learning/[topic].md |
| Life pattern | areas/[relevant-area]/patterns.md or standalone |
| Project insight | areas/[project]/learnings.md |
| General reference | resources/[topic]/ |
| Tool/product knowledge | resources/tools/[tool].md |
Step 3: Create knowledge file
---
title: "[Clear descriptive title]"
created: YYYY-MM-DD
tags: [knowledge, topic, source-area]
type: [how-to|pattern|insight|reference|lesson]
---
# [Title]
## Summary
[One paragraph - what this knowledge is and why it matters]
## The Knowledge
### Context
[When/where this applies]
### Detail
[The actual knowledge - steps, pattern description, insight explanation]
### Examples
[If applicable - concrete examples of application]
## Caveats
[If applicable - when this doesn't apply, edge cases]
## Source
[Where this came from - session reference, experience, external source]
## Related
- [[related-notes]]
Step 4: Link appropriately
- Add reference in relevant area/project files
- Update any index files if they exist
- Note in session file that knowledge was extracted
Step 5: Confirm
- Show file location
- Summarise what was captured
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.
- yesterday First seen · 84 lines · 36 tokens per session scan A 8f51a5d0aaff
knowledge-extraction is a skill published in the GitHub repository teejayen/arc (5 stars, last pushed 7mo ago), licensed MIT. It adds 36 tokens to every session and 484 once invoked, about $0.0002 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
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…
📝 任务完成后归档
重要提醒: 每次完成复杂调试或开发任务后，主动执行此流程！ 将学到的经验归档为 skill，供以后参考。不要等用户提醒。.
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.