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 michaeljauk/brain-starter --skill ingest-articlegit clone --depth 1 https://github.com/michaeljauk/brain-starterWrote 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/michaeljauk/brain-starter/ingest-article)<a href="https://agentmods.dev/skills/michaeljauk/brain-starter/ingest-article"><img src="https://agentmods.dev/badge/skills/michaeljauk/brain-starter/ingest-article.svg" alt="Measured on agentmods" height="20"></a>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 | $0.00058 | $0.03058 |
| Opus 5 | $0.00029 | $0.01529 |
| Sonnet 5 | $0.00012 | $0.00612 |
| Haiku 4.5 | $0.00006 | $0.00306 |
Grade A, and why
ingest-article 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 6d 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 — 253 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Ingest Article
Takes a URL or raw text, extracts the key knowledge, and places it in the right location(s) in the brain vault.
Trigger phrases
- "ingest this: [URL]"
- "ingest article: [URL]"
- "/ingest-article [URL]"
- "add this to my brain: [URL or text]"
- "save this knowledge: [URL or text]"
Input
The user provides one of:
- A URL — extract content using Defuddle CLI
- Raw text — use directly (pasted article, email, notes)
Optional: the user may specify a target topic or project to file under.
Step-by-step workflow
1. Extract content
If URL:
defuddle parse <url> --md
Also grab metadata:
defuddle parse <url> -p title
defuddle parse <url> -p domain
defuddle parse <url> -p description
If raw text: Use the text as-is. Ask the user for a title/source if not obvious.
Paywall bail-out: If defuddle output is < 500 chars AND contains markers like subscribe, paywall, sign up to read, become a member, abort the auto-ingest. Tell the user the source is paywalled and ask them to paste the full text. Do NOT write a thin note from a paywalled snippet.
2. Analyze and classify
Read the extracted content and determine:
- Topic summary — What is this article about? (1-2 sentences)
- Key insights — The 3-8 most actionable or notable takeaways
- Actionable insights with application targets — For each key insight, identify the specific project/area where it could be applied. Format as
{insight} → {project or area} — {what to do}. This is mandatory output, not optional. If an insight has no application target across active projects (check memory for active projects list), label itgeneral referenceand explain why. - Relevance — Which existing projects, notes, or topics does this relate to?
- Placement decision — Where should this go?
3. Determine placement
Use this decision tree:
| Condition | Action |
|---|---|
Article directly relates to an active project (check projects/) |
Update the project note with a new section or append insights |
| Article is research for an in-progress deliverable | Create in projects/{project}/ |
| Otherwise (general knowledge, reference material) | Create a new note in research/ as a standalone knowledge note |
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.
- 6d ago First seen · 253 lines · 58 tokens per session scan A 4abc9f0fb6d4
ingest-article is a skill published in the GitHub repository michaeljauk/brain-starter (5 stars, last pushed 10d ago), licensed MIT. It adds 58 tokens to every session and 3,058 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 2026-08-31.
Other skills, from other repositories
log
Use this when a PersonalOS work session, chat outcome, personal reflection, or provided source should be persisted into the modular Daily context and any already-owned canonical files. Do NOT use for single-call processing, single-source knowledge ingestion, Gmail/WhatsApp propagation, or Lexware booking.
context-compression
A skill for condensing the history of meetings and projects into a short memory file. It records decisions, changes, outdated agreements, open questions, and key meetings.
parking
A workflow for saving the current state of a task before switching to another one. It records the stopping point, blockers, project plan changes, and information needed to resume later.
analyse-call
Use this when a local call transcript or meeting note should be analyzed into traceable PersonalOS context. Preserves the source, separates evidence from interpretation, updates only proven owner truth, routes confirmed commitments through task-manager, and never sends messages or triggers external actions without…
vault-onboarding-guide
An interactive guide for learning a file-based knowledge store with an agent. It teaches how to organize incoming material, projects, plans, tasks, logs, parked work, and resumed work.
new-dialog-handoff
A workflow for creating a new project in a knowledge vault, including its plan, tasks, context, activity log, and README. A knowledge vault is a structured collection of project notes and documents.