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 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/knowledge-ingestion)<a href="https://agentmods.dev/skills/lyc403223157-source/knowledge-inbox/knowledge-ingestion"><img src="https://agentmods.dev/badge/skills/lyc403223157-source/knowledge-inbox/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/knowledge-ingestion"><img src="https://agentmods.dev/badge/skills/lyc403223157-source/knowledge-inbox/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 | $0.00112 | $0.00507 |
| Opus 5.5 | $0.00045 | $0.00203 |
| Sonnet 5.5 | $0.00022 | $0.00101 |
| Haiku 4.5 | $0.00011 | $0.00051 |
Grade A, and why
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 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.
What it actually says
Knowledge Ingestion
Call knowledge_ingest with the exact URL, absolute local path, or original text.
-
Treat a standalone forwarded link, file, or content message with no accompanying question as an ingestion request; do not ask for a separate “save this” command.
-
If forwarded text contains exactly one supported URL plus share text, pass the URL as
contentso the service fetches the source instead of archiving only the wrapper text. -
When content is supplied as context for a question or another task, answer that task without silently ingesting it unless the user also asks to save it.
-
Pass a user title only when supplied or useful for a text-only note.
-
Pass
source_urlonly for a local file that came from a known URL. -
Use up to 1800 seconds for long audio or video.
-
On success, report the returned
note_path. -
On failure, report the exact actionable error. Never claim a note was saved.
-
If storage is not configured, direct the user once to
http://127.0.0.1:8787/to choose an Obsidian Vault or Markdown folder, then retry the original content. -
Do not summarize separately; the service handles AI analysis, tags, links, and Markdown.
-
Use
knowledge_list_capabilitiesonly when source support is uncertain. -
Use
knowledge_get_jobto inspect a known asynchronous job.
For WeChat Channels, call knowledge_ingest first. If it reports a disconnected client,
call knowledge_wechat_prepare and retry once. Never ask the user to open or play the
supplied video URL. Only when preparation fails may you ask the user once to close and
reopen any Channels window. The service restores the system proxy and deletes the source
video only after both Obsidian and SQLite writes succeed.
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 · 33 lines · 112 tokens per session scan A 3406d84c65af
knowledge-ingestion is a skill published in the GitHub repository lyc403223157-source/knowledge-inbox (6 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 112 tokens to every session and 507 once invoked, about $0.0004 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 2026-08-31.
Other skills, from other repositories
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.
molio-kb
Query the user's local Molio knowledge base — browse files, full-text search, read documents, and run AI Q&A grounded in the user's own notes (read-only).
enzyme
Use Enzyme in an already activated Obsidian, Markdown, or Hermes workspace for working-memory retrieval, source-grounded exploration, semantic search by concept rather than keyword, runtime note-writing, and refresh. If the workspace is not initialized, follow the first-time setup section before normal retrieval.
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…
linker
Discovers missing cross-domain connections between knowledge documents and creates/updates connection wiki articles.
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…