Ars Contexta is a Claude Code plugin that creates a personalized knowledge system from a conversation about how someone thinks and works, using connected Markdown files, note-processing skills, hooks, navigation maps, and templates. It is for people who want an owned, persistent second brain tailored to their domain. The catalogue entries are its generated skills, hooks, agent, and plugin workflow.
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 skills add agenticnotetaking/arscontexta --skill learngit clone --depth 1 https://github.com/agenticnotetaking/arscontextaWrote 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/agenticnotetaking/arscontexta/learn)<a href="https://agentmods.dev/skills/agenticnotetaking/arscontexta/learn"><img src="https://agentmods.dev/badge/skills/agenticnotetaking/arscontexta/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/skills/agenticnotetaking/arscontexta/learn"><img src="https://agentmods.dev/badge/skills/agenticnotetaking/arscontexta/learn.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00059 | $0.01942 |
| Opus 5.5 | $0.00024 | $0.00777 |
| Sonnet 5.5 | $0.00012 | $0.00388 |
| Haiku 4.5 | $0.00006 | $0.00194 |
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 1mo 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 — 254 lines — stays where its author put it; the contents beside it link to each section on GitHub.
EXECUTE NOW
Topic: $ARGUMENTS
Parse immediately:
- If topic provided: research that topic
- If topic empty: read
self/goals.mdfor highest-priority unexplored direction and propose it - If topic includes
--deep/--light/--moderate: force that depth, strip flag from topic - If no topic and no goals.md: ask "What would you like to research?"
Steps:
- Read config — tool preferences, depth, domain vocabulary
- Determine depth — from flags, config default, or fallback to moderate
- Research — tool cascade: primary → fallback → last resort
- File to inbox — with full provenance metadata
- Chain to processing — next step based on pipeline chaining mode
- Update goals.md — append new research directions discovered
START NOW. Reference below explains methodology.
Step 1: Read Configuration
ops/config.yaml — research tools, depth, pipeline chaining
ops/derivation-manifest.md — domain vocabulary (inbox folder, reduce skill name)
From config.yaml (defaults if missing):
research:
primary: exa-deep-research # exa-deep-research | exa-web-search | web-search
fallback: exa-web-search
last_resort: web-search
default_depth: moderate # light | moderate | deep
pipeline:
chaining: suggested # manual | suggested | automatic
From derivation-manifest.md (universal defaults if missing):
- Inbox folder:
inbox/(could bejournal/,encounters/, etc.) - Reduce skill name:
/reduce(could be/surface,/break-down, etc.) - Domain name and hub MOC name
Step 2: Determine Depth
Priority: explicit flag > config default > moderate
| Depth | Tool | Sources | Duration | Use When |
|---|---|---|---|---|
| light | WebSearch | 2-3 | ~5s | Checking a specific fact |
| moderate | mcp__exa__web_search_exa | 5-8 | ~10-30s | Exploring a subtopic |
| deep | mcp__exa__deep_researcher_start | Comprehensive | 15s-3min | Major research direction |
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.
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.
- 1mo ago First seen · 254 lines · 59 tokens per session scan A c0643ca90ba5
learn is a skill published in the GitHub repository agenticnotetaking/arscontexta (3,509 stars, last pushed 7mo ago), licensed MIT. It adds 59 tokens to every session and 1,942 once invoked, about $0.0002 per session on Opus 5.5. 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
improve
Critique an outside idea (a pasted tip, post, transcript or video summary) against what this system already has. Use when the founder pastes something and asks whether to adopt it, or says 'improve', 'should we do this', 'compare this to what we have'. Grounded by scripts/improveground.py in the lessons corpora and…
video-to-knowledge
Use by2kb to find videos for a learning topic, present numbered recommendations, and ingest the selected videos; also turn Bilibili/YouTube URLs or local media into transcripts, abstracts, and study notes.
default-video-digest
Turn a transcript into grounded, structured notes for deep study.
llm-wiki
Build and maintain an LLM-curated knowledge base from papers, articles, transcripts, notes and project findings. Ingest sources into linked Markdown, answer questions with citations, lint or upgrade a wiki, and preserve useful synthesis across sessions and agents. Also capture verified task experience, consolidate…
learn
Learn a source together with the user and record only what they understood as a new page in this Scraps wiki. Explains the source with a diagram anchored on the pages the wiki already has, checks comprehension with questions, then writes one page from the points that passed; when understanding is not reached, nothing…
gh-discussions
A guide for answering GitHub Discussions, a question-and-answer area separate from issue reports. In its Q&A categories, a maintainer can mark a reply as the accepted answer.