digester

digester is an agent for Claude Code from ohdearquant/khive. It costs 45 tokens per session (1,591 once invoked), scanned A, original, Apache-2.0.

A specialist agent that turns source material such as papers, architecture decisions, design documents, or code into typed entities, links, and notes in a knowledge graph.

In plain words
What is it for?
Use it for batch processing documents or code regions, extracting concepts, linking them to existing graph items, and checking that the imported material is represented.
Why use it?
It makes large collections of source material searchable and connected without asking an open-ended research agent to perform structured ingestion.

Agent for Claude Code

Written for Claude Code: shipped in a Claude Code plugin.

Part of the khive plugin — 11 skills, 6 agents shipped together

Good fit Use it for batch processing documents or code regions, extracting concepts, linking them to existing graph items, and checking that the imported material is represented.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/ohdearquant/khive/digester
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.

Clone the repo
git clone --depth 1 https://github.com/ohdearquant/khive

Made for: Claude Code.

Or install khive, the plugin that ships this one along with the rest of its 11 skills, 6 agents.

Wrote 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.

agentmods badge for digester

README.md
[![agentmods](https://agentmods.dev/badge/agents/ohdearquant/khive/digester/github.svg)](https://agentmods.dev/agents/ohdearquant/khive/digester)
Your own site
<a href="https://agentmods.dev/agents/ohdearquant/khive/digester"><img src="https://agentmods.dev/badge/agents/ohdearquant/khive/digester/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.

agentmods 80×15 button for digester

Your own site · 80×15
<a href="https://agentmods.dev/agents/ohdearquant/khive/digester"><img src="https://agentmods.dev/badge/agents/ohdearquant/khive/digester.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 45 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,591 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 5.1 $0.00045 $0.01591
Opus 5.5 $0.00018 $0.00636
Sonnet 5.5 $0.00009 $0.00318
Haiku 4.5 $0.00005 $0.00159

Measured 3d ago against content hash fe5e3bf0bc75, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

digester 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 3d 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.

marketplace/khive/agents/digester.md · 173 lines

How it starts

The opening of the file, as written. The whole thing — 173 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Digester Agent

You are a digester. You take material — papers, ADRs, design docs, codebase regions — and turn it into queryable graph structure. You do not do open-ended research; you do ingestion. The source is given; your job is to extract entities, link them correctly, and verify density.

Core mandate: every piece of source material leaves the graph with at least one new entity OR a new edge wired to an existing entity.


Skill

Follow marketplace/khive/skills/digest/SKILL.md. It is the workflow contract. This file adds digester-specific operating rules.

When to call this agent

  • A new paper / ADR / design doc needs to land in the graph
  • A batch of N source files needs to be processed in parallel (one digester per slice)
  • A codebase region needs concept extraction (e.g., a new crate's modules)

Do not use the digester for: open-ended topic exploration (explorer), graph cleanup (polisher), or strategic gap analysis (gap-analyst).


Pre-flight (mandatory)

Before processing any source:

  1. List your slice. Know exactly which files you own.
  2. For each file, search the graph for the obvious entity names FIRST. Most ADRs and papers will reference existing concepts — link to them, do not duplicate.
  3. Skim the source's references / citations section. Pre-emptively search for cited entities so you can wire introduced_by edges correctly.

Operating rules

  1. One source file → one digestion pass. Don't read all files into context, then batch-create. The cross-file context bloats and you'll start hallucinating edges. Process one file fully, then move to the next.

  2. UUID-keyed link calls. Pull id/full_id from create and search responses, reuse them. Passing entity names as strings to link(source_id=…) is the single most common ingestion error.

  3. No colons in FTS5 search queries. search(query="arxiv:2106") fails parse. Use the title or author instead.

  4. Properties capture facts, edges capture relationships. Year, version, author list, benchmark numbers → properties. "Introduced by", "competes with", "depends on" → link. Do not encode relationships as property strings.

Read the full file on GitHub · 173 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. 3d ago First seen · 173 lines · 45 tokens per session scan A fe5e3bf0bc75

Subscribe to this mod's changes

digester is an agent published in the GitHub repository ohdearquant/khive (34 stars, last pushed today), licensed Apache-2.0. It adds 45 tokens to every session and 1,591 once invoked, about $0.0002 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 2026-11-03.

Related

digester compared with agents from other repositories

digester next to 6 agents from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
digesterohdearquant/khiveAgent34todayApache-2.0A45Claude Code
context-builderjulymetodiev/post-cortexAgent2017d agoMITA45Claude Code
memory-curatorjulymetodiev/post-cortexAgent2017d agoMITA41Claude Code
Doc WriterFu-Jie/openwebui-extensionsAgent33327d agoMITA29Claude Code
Plugin ImplementerFu-Jie/openwebui-extensionsAgent33327d agoMITA29Claude Code
context-researchermajor7apps/pensyveAgent99yesterdaynoneA47Claude Code
architecture-reviewercogniplex/codememAgent183mo agoApache-2.0A51Claude Code