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 lyc403223157-source/knowledge-inbox --skill personal-knowledge-ingestiongit clone --depth 1 https://github.com/lyc403223157-source/knowledge-inboxWrote 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/lyc403223157-source/knowledge-inbox/personal-knowledge-ingestion)<a href="https://agentmods.dev/skills/lyc403223157-source/knowledge-inbox/personal-knowledge-ingestion"><img src="https://agentmods.dev/badge/skills/lyc403223157-source/knowledge-inbox/personal-knowledge-ingestion/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/lyc403223157-source/knowledge-inbox/personal-knowledge-ingestion"><img src="https://agentmods.dev/badge/skills/lyc403223157-source/knowledge-inbox/personal-knowledge-ingestion.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00086 | $0.00534 |
| Opus 5 | $0.00043 | $0.00267 |
| Sonnet 5 | $0.00017 | $0.00107 |
| Haiku 4.5 | $0.00009 | $0.00053 |
Grade A, and why
personal-knowledge-ingestion 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 9d 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 — 44 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Personal Knowledge Ingestion
Use the knowledge_ingest tool when the user explicitly asks to save, ingest,
archive, or add supplied content to their personal knowledge base.
Tool input
content: pass the exact URL, absolute local file path, or original text.title: optional user-provided title. Do not invent one unless it improves a text-only note.source_url: only use whencontentis a local file that came from a known web URL.timeout_seconds: normally omit; use up to 1800 for long media.
Behavior
- Call the tool once and wait for its result.
- Do not separately summarize the content; the ingestion pipeline performs AI understanding, classification, tags, linking, and Markdown formatting.
- On success, report the returned absolute
note_path. - On failure, report the exact actionable error and never claim the note was saved.
- For WeChat Channels links, the tool starts the local downloader, temporarily
enables the approved SunnyNet proxy, and uses one logged-in Channels page as
a local API client. It must not ask the user to open the supplied video URL.
Never call
scripts/ingest.pydirectly for these links. Ifknowledge_ingestreports that the client is disconnected, callknowledge_wechat_prepareimmediately and retryknowledge_ingestafter it returnsready. Do not investigate the downloader with terminal or browser tools, and do not invent alternative workflows. If preparation reports that the Hermes Python binary lacks Accessibility permission, return that exact binary path and the single required permission action. For any other preparation failure, ask the user once to close and reopen any Channels window; never ask them to open or play the supplied video. This bootstrap is needed only after WeChat or its renderer restarts. The tool always restores the system proxy to off and deletes the downloaded video only after the card and database write succeed. - Do not call this tool for read-only questions about existing notes.
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.
- 9d ago First seen · 44 lines · 86 tokens per session scan A 40aac223b63a
personal-knowledge-ingestion is a skill published in the GitHub repository lyc403223157-source/knowledge-inbox (7 stars, last pushed 4d ago), licensed Apache-2.0. It adds 86 tokens to every session and 534 once invoked, about $0.0004 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
linker
Discovers missing cross-domain connections between knowledge documents and creates/updates connection wiki articles.
personal-api
Turn an Obsidian vault into an AI-readable personal identity layer. Use when setting up ME.md and AGENT.md, scaffolding the full Knowledge Palace v2 structure, onboarding AI assistants, or maintaining the vault contract. Default setup creates the complete 30.knowledge system; --minimal creates only the lightweight…
wiki-save
A tool for saving useful parts of the current conversation as organised wiki pages. It classifies the material, adds page metadata and links, and updates the wiki’s indexes and activity records.
brain
Orient in the user's big-brain second brain and work brain-aware for the rest of the session. Use when the user types /brain, or asks "what am I working on", "what's on my plate", "catch me up", "what's overdue", or at the start of a session about ongoing work. Loads the vault overview, reports it in one screen, and…
capture
Quick-capture a thought, idea, link, or fact into the big-brain second brain's inbox. Use when the user types /capture , or says "note this down", "remember this in my brain", "add to my inbox", "capture this idea". Zero-friction: file it now, organize later.
obsidian-bases
Explain, draft, and validate Obsidian Bases .base files with filters, formulas, properties, summaries, and table, card, or list views. Use for Obsidian Bases, database-like vault views, dynamic tables, reading lists, task trackers, filters, formulas, summaries, and .base file edits.