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.
git clone --depth 1 https://github.com/datacore-one/datacoreWrote 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/commands/datacore-one/datacore/ingest)<a href="https://agentmods.dev/commands/datacore-one/datacore/ingest"><img src="https://agentmods.dev/badge/commands/datacore-one/datacore/ingest/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/commands/datacore-one/datacore/ingest"><img src="https://agentmods.dev/badge/commands/datacore-one/datacore/ingest.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 | $0.00019 | $0.03918 |
| Opus 5.5 | $0.00008 | $0.01567 |
| Sonnet 5.5 | $0.00004 | $0.00784 |
| Haiku 4.5 | $0.00002 | $0.00392 |
Grade A, and why
ingest 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 — 516 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/ingest Command
Command Context
When to Reference DIP-0015
Always reference when:
- Determining file destinations
- Creating companion files
- Routing to semantic folders
- Extracting knowledge (zettels, insights)
Key decisions this DIP informs:
- Semantic routing (active/knowledge/archive)
- Companion file format
- Tag application (DIP-0014)
- YAML frontmatter requirements
Quick Reference
| Question | Answer |
|---|---|
| Default inbox? | 0-inbox/ in each space |
| Active work? | 1-tracks/ or 1-active/ |
| Reference? | 3-knowledge/ |
| Archive? | 4-archive/ |
| What DIPs govern this? | DIP-0015 (Semantic Org), DIP-0014 (Tags) |
Agents This Command Invokes
| Agent | Purpose |
|---|---|
ingest-orchestrator |
Orchestration, planning (replaces ingest-coordinator, DIP-0021) |
knowledge-extractor |
Per-file knowledge extraction (replaces ingest-processor, DIP-0021) |
docx-reader |
DOCX conversion |
Integration Points
- DIP-0021 - Search & Research Architecture
- DIP-0015 - Semantic organization
- DIP-0014 - Tag taxonomy
- Git LFS - Large file handling
Process files from inbox folders or external sources into Datacore with deep knowledge extraction - not just file sorting, but reading, analyzing, extracting insights, and discovering actionable items.
Usage
/ingest [optional: folder path]
- Default: Processes
0-inbox/folders across all spaces - With path: Processes specified folder (e.g.,
~/Documents/Migration/)
The source is cleared last — only once everything from it is saved
This rule overrides every step below, including "bulk archive the remaining files".
- A source file may be cleared (moved, archived or deleted) only after every note AND every task extracted from it has been written and you have read it back on disk. Clearing is the very last step of the run, after all saves.
- If any save for a source fails (a write error, a read-only or missing folder, a refused command), that source file stays where it is, unchanged: do not move it, archive it, rename it, edit it or delete it. Other sources whose saves all succeeded may still be cleared.
- Report the failure plainly: which source, what could not be saved, and why, and say that the source was left in place so a re-run can finish it. Handing the unsaved task back in chat ("add this by hand") is not a save and does not allow clearing the source.
- Never force a save by changing permissions (chmod/chown/chflags/sudo) or by writing somewhere the plan did not name.
- Nothing is half-cleared: a source is either fully saved and then cleared, or left exactly as it was.
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 Changed 7b4cc378d77f
- 19d ago Changed · +11 lines b2ab24996fb2
- 1mo ago First seen · 505 lines · 19 tokens per session scan A 04878823fb46
ingest is a command published in the GitHub repository datacore-one/datacore (4 stars, last pushed yesterday), licensed MIT. It adds 19 tokens to every session and 3,918 once invoked, about $0.0001 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 2026-09-03.
Other commands, from other repositories
voice-refresh
Refresh the founder-voice DNA from new Granola meetings (interactive, MCP-backed). Pulls meetings since the last refresh, harvests Assaf-only speech, runs the Stage 2-3 orchestrator, and presents a founder-gated delta. Never auto-writes voice-dna.md.
okf
A command that exports a private knowledge wiki into an OKF-compatible bundle. OKF is a format for packaging knowledge, with a separate guarded mode for preparing material to share externally.
wikimate-lint
A read-only health check for an Obsidian vault, a folder of linked Markdown notes. It scans for duplicate notes, broken links, orphaned notes, frontmatter problems, and incomplete indexes.
pdf-to-wiki
A workflow for sending a large PDF from Google Drive to NotebookLM, Google's document-analysis tool, and saving the resulting notes as Obsidian markdown files. It passes the file link rather than reading the PDF directly.
capture-tabs
Capture a Chrome research tab group or AI-chat research session into LLM Wiki Inbox markdown, then optionally route it through /inbox or /ingest.
pdf-to-markdown-docling
Convert a local PDF to markdown via Docling's standard pipeline (layout + table-structure recognition — higher fidelity than MarkItDown on complex tables/layouts, 10x slower). Requires the opt-in Docling install.