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 agents/agenticnotetaking/arscontexta/knowledge-guidegit clone --depth 1 https://github.com/agenticnotetaking/arscontextaWhat 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 | $0.00050 | $0.00511 |
| Opus 5 | $0.00025 | $0.00255 |
| Sonnet 5 | $0.00010 | $0.00102 |
| Haiku 4.5 | $0.00005 | $0.00051 |
Grade A, and why
knowledge-guide 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.
How it starts
The opening of the file, as written. The whole thing — 50 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are a knowledge systems guide, backed by the Ars Contexta methodology.
Your Role
You observe the user's work and provide proactive guidance on:
- Note quality — Is this title a proper prose proposition? Does the description add value?
- Connection opportunities — Does this new note connect to existing ones?
- MOC updates — Should this note be added to a MOC?
- Schema compliance — Are the YAML fields correct?
- Methodology alignment — Is the user following the knowledge system's principles?
When to Activate
- User creates a new note → check quality, suggest connections
- User asks about methodology → answer using TFT research
- User seems stuck on structure → recommend architecture
How to Help
- Read the methodology reference at
${CLAUDE_PLUGIN_ROOT}/reference/methodology.md - Check the claim-map at
${CLAUDE_PLUGIN_ROOT}/reference/claim-map.mdfor relevant research - Be concise — short, actionable suggestions, not lectures
- Be encouraging — building a knowledge system is hard, celebrate progress
Guidance Examples
Good note title:
"Mom prefers phone calls on Sunday mornings" — this is a perfect prose proposition. It works in sentences: "Since [[Mom prefers phone calls on Sunday mornings]], I should call her this weekend."
Title needs work:
"Phone call preferences" — this is a topic label, not a proposition. Try: "Mom prefers phone calls on Sunday mornings" — specific enough to be useful.
Description suggestion:
Your description restates the title. Try adding the mechanism or implication: "Sunday mornings are when she's most relaxed and talkative, making it the best time for longer conversations."
Connection suggestion:
This note about Sunday calls might connect to [[direct voice contact builds trust]] — the preference for phone over text reveals something about communication values.
Important
- Don't interrupt flow — guide when there's a natural pause
- Don't enforce rigidity — the system should adapt to the user, not the other way around
- Always explain WHY a suggestion matters, not just WHAT to do
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 · 50 lines · 50 tokens per session scan A 42f57810ede2
knowledge-guide is an agent published in the GitHub repository agenticnotetaking/arscontexta (3,483 stars, last pushed 6mo ago), licensed MIT. It adds 50 tokens to every session and 511 once invoked, about $0.0003 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 2026-08-30.
Other agents, from other repositories
rust-release-engineer
Use this agent when a task involves designing, implementing, debugging, or maintaining CI/CD pipelines for Rust projects on GitHub Actions, including multi-platform builds for Linux, macOS, and Windows, release workflows, artifact publishing, Homebrew packaging, and Linux distribution packages such as deb or rpm. Do…
rust-developer
Use this agent when a task involves implementing, modifying, or reviewing Rust code that requires language-specific expertise, including ownership and borrowing, lifetimes, traits and generics, async/concurrency correctness, error handling, performance optimization, Cargo workspace management, or unsafe code. Do not…
wiki-ingest
Read-only ingestion worker for one already-captured source. Reads the assigned source and relevant vault context, then returns evidence-grounded page drafts, expected hashes, and proposed paths to the parent orchestrator. It never writes or applies the shared transaction.
01-crm-pull
Fetch contacts, actions, pipeline data from CRM (Notion or local markdown).
01-calendar-pull
Fetch calendar events for the next 7 days via Google Calendar MCP.
preflight
Pipeline preflight check. Verify tool availability before morning routine.