ingest-processor

A deprecated agent for processing incoming files and deciding where they belong in a structured knowledge system. It has been replaced by the knowledge-extractor agent.

In plain words
What is it for?
Historical reference for file routing, creating companion files, and extracting notes or insights.
Why use it?
It was intended to remove guesswork from sorting active work, reference material, and archives. It should not be chosen for new work because it is deprecated.

Agent

Install

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.

agentmods
npx agentmods add agents/datacore-one/datacore/ingest-processor
Clone the repo
git clone --depth 1 https://github.com/datacore-one/datacore
Per session 23 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 3,534 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00023 $0.03534
Opus 5 $0.00012 $0.01767
Sonnet 5 $0.00005 $0.00707
Haiku 4.5 $0.00002 $0.00353

Measured yesterday against content hash e421fb0b8187, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

ingest-processor 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.

.datacore/4-archive/agents/ingest-processor.md · 529 lines

How it starts

The opening of the file, as written. The whole thing — 529 lines — stays where its author put it; the contents beside it link to each section on GitHub.

DEPRECATED per DIP-0021: Replaced by knowledge-extractor. Registry entry has superseded_by: knowledge-extractor. File kept for reference.

Ingest Processor

Agent Context

When to Reference DIP-0015

Always reference when:

  • Determining file destination
  • Creating companions for non-readable files
  • Routing to tracks vs knowledge vs archive
  • Extracting zettels and insights

Key decisions this DIP informs:

  • Semantic routing by purpose, not format
  • Space routing (personal vs org)
  • Companion file format
  • Knowledge extraction patterns

Quick Reference

Question Answer
Active work? 1-tracks/[track]/
Reference value? 3-knowledge/
Historical only? 4-archive/
Who spawns me? ingest-coordinator

Related DIPs

Related Agents

Agent Relationship
ingest-coordinator Spawns me for each item
structural-integrity Audits my work

Integration Points

  • DIP-0015 - Follows semantic structure
  • Git LFS - Handles large file tracking
  • Knowledge extraction - Creates zettels/insights

You are an ingest processor subagent for Datacore. You handle the processing of individual files or folders during import/ingestion workflows.

Your Role

You are a processor, invoked by the ingest-coordinator. For each file/folder you:

  1. READ - Analyze content (if AI-readable)
  2. ASSESS - Determine: active, knowledge, or archive?
  3. EXTRACT - Pull out zettels, insights, tasks
  4. CAPTURE - Log discovered tasks to inbox
  5. FILE - Move to semantic destination
  6. LINK - Connect to related content

6-Phase Processing Methodology

Phase 1: READ

AI-Readable Formats:

  • PDF, TXT, MD, RTF - Read full content directly
  • DOCX - Extract via XML parsing (see below)
  • XLSX, CSV - Read data, extract key metrics
  • Images (PNG, JPG) - Analyze visually
  • EML - Parse headers for From, To, CC, X-headers
  • XML - Schema-aware entity extraction

Read the full file on GitHub · 529 lines

Changes

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.

  1. yesterday First seen · 529 lines · 23 tokens per session scan A e421fb0b8187

Subscribe to this mod's changes

ingest-processor is an agent published in the GitHub repository datacore-one/datacore (4 stars, last pushed 2d ago), licensed MIT. It adds 23 tokens to every session and 3,534 once invoked, about $0.0001 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.

Related

Other agents, from other repositories

01-crm-pull

Fetch contacts, actions, pipeline data from CRM (Notion or local markdown).

assafkip/kipi-system · 22 tokens

01-calendar-pull

Fetch calendar events for the next 7 days via Google Calendar MCP.

assafkip/kipi-system · 18 tokens

verification-gate

Evidence-before-claims gate. Use before declaring work complete, fixed, or passing — before committing or creating PRs. Requires running verification commands, driving the affected flow end-to-end to observe real behaviour, and confirming output before any success claims. Adapted from Superpowers'…

sliamh11/Deus · 111 tokens

keystone

Structured end-to-end trace to find the FIRST broken link in a specific claim's dependency chain. Single-claim depth probe — NOT a breadth reviewer. Use when a consequential claim ("X is enforced", "Y has a fallback", "Z reaches the main agent") needs primary-evidence verification across its full chain. Advisory…

sliamh11/Deus · 87 tokens

brainstormer

Creative research and solution design agent. Takes a problem statement, surveys prior art (vault memory, web, papers), generates 3-5 ranked solution ideas with effort/impact/risk estimates, and identifies non-obvious connections. Use when stuck on a challenge, exploring design alternatives, or wanting creative input…

sliamh11/Deus · 210 tokens

code-reviewer

Post-implementation, pre-commit review of actual code changes against Deus-specific rules stored in a versioned rules file. Runs on the working-tree + staged diff like a PR reviewer tuned to this repo's standards (CI gates, cross-platform, token efficiency, security basics, cleanup, type safety, comment discipline…

sliamh11/Deus · 222 tokens