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 tutorialgit 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/tutorial)<a href="https://agentmods.dev/skills/agenticnotetaking/arscontexta/tutorial"><img src="https://agentmods.dev/badge/skills/agenticnotetaking/arscontexta/tutorial/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/tutorial"><img src="https://agentmods.dev/badge/skills/agenticnotetaking/arscontexta/tutorial.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium Excessive Agency · line 7 Skill selects an external model or provider that may use a different account or billing plan than the operator expects. Undisclosed model switches can cause unexpected cost or quota consumption.Fix: Remove the model/provider override or disclose it prominently and require explicit operator approval before invoking an external coding CLI or billed model.
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 | $0.00055 | $0.04358 |
| Opus 5.5 | $0.00022 | $0.01743 |
| Sonnet 5.5 | $0.00011 | $0.00872 |
| Haiku 4.5 | $0.00006 | $0.00436 |
Grade A, and why
tutorial 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 — 497 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Runtime Configuration (Step 0 — before any processing)
Read these files to configure domain-specific behavior:
-
ops/derivation-manifest.md— vocabulary mapping, platform hints- Use
vocabulary.notesfor the notes folder name - Use
vocabulary.note/vocabulary.note_pluralfor note type references - Use
vocabulary.reducefor the extraction verb - Use
vocabulary.reflectfor the connection-finding verb - Use
vocabulary.topic_mapfor MOC references - Use
vocabulary.inboxfor the inbox folder name
- Use
-
ops/config.yaml— processing depth, domain context
If these files don't exist, use universal defaults.
EXECUTE NOW
Target: $ARGUMENTS
- If
ops/tutorial-state.yamlexists andcurrent_step<= 5: resume from saved step - If target is "reset": delete
ops/tutorial-state.yamland start fresh - If no state file exists: begin new tutorial with track selection
START NOW. Reference below defines the flow.
Resume Detection
Read ops/tutorial-state.yaml. If it exists and tutorial is incomplete, display:
--=={ ars contexta : tutorial }==--
Welcome back.
Track: [track] [step-progress] Step [N] of 5
Resuming where you left off...
Skip to the saved current_step. Do NOT re-ask for track. If current_step > 5, tutorial is complete — offer to reset.
Progress indicator format:
- Step 1 of 5:
[=> ] - Step 2 of 5:
[==> ] - Step 3 of 5:
[===> ] - Step 4 of 5:
[====> ] - Step 5 of 5:
[=====>]
Track Selection (new tutorial only)
Display header, then use AskUserQuestion:
--=={ ars contexta : tutorial }==--
Which track fits your work best?
(a) Researcher -- academic papers, domain
research, literature processing
(b) Manager -- meeting notes, strategy docs,
decision tracking
(c) Personal -- daily observations, goal
setting, reflective journaling
Wait for response. Map a/b/c to researcher/manager/personal.
Write initial state to ops/tutorial-state.yaml:
track: [researcher|manager|personal]
current_step: 1
completed_steps: []
started: [ISO 8601 UTC]
last_activity: [ISO 8601 UTC]
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 · 497 lines · 55 tokens per session scan A c52a82af362a
tutorial is a skill published in the GitHub repository agenticnotetaking/arscontexta (3,509 stars, last pushed 7mo ago), licensed MIT. It adds 55 tokens to every session and 4,358 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.