archive-indexer

archive-indexer is an agent for coding agents from datacore-one/datacore. It costs 0 tokens per session (2,149 once invoked), scanned A, original, MIT.

An agent that builds and maintains a searchable index for archived documents using text embeddings, which represent document meaning numerically for similarity searches.

In plain words
What is it for?
Use it to index new or changed archive content, skip unsupported binary files, and rebuild the archive index when needed.
Why use it?
It makes archived text easier to find by meaning and avoids reprocessing files that do not need indexing.

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/archive-indexer
Clone the repo
git clone --depth 1 https://github.com/datacore-one/datacore

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 archive-indexer

README.md
[![agentmods](https://agentmods.dev/badge/agents/datacore-one/datacore/archive-indexer.svg)](https://agentmods.dev/agents/datacore-one/datacore/archive-indexer)
Your own site
<a href="https://agentmods.dev/agents/datacore-one/datacore/archive-indexer"><img src="https://agentmods.dev/badge/agents/datacore-one/datacore/archive-indexer.svg" alt="Measured on agentmods" height="20"></a>
Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 2,149 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 $0.00000 $0.02149
Opus 5 $0.00000 $0.01074
Sonnet 5 $0.00000 $0.00430
Haiku 4.5 $0.00000 $0.00215

Measured yesterday against content hash 8369aa97ac7f, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

archive-indexer 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/modules/outbox/agents/archive-indexer.md · 318 lines

How it starts

The opening of the file, as written. The whole thing — 318 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Agent: archive-indexer

Maintains searchable index in archive repos using datacortex embeddings.

Metadata

Field Value
ID archive-indexer
Module outbox
Version 1.0.0
Type indexing
Model sonnet
DIP DIP-0017

Engram Injection

Before starting work, load relevant learned patterns:

  1. Preferred: Call plur_admin MCP tool with action = "plur_inject_hybrid", prompt = your task description, scope = agent:archive-indexer
  2. Fallback: If MCP is unavailable, read .datacore/state/agent-engrams/archive-indexer.md for compiled engrams

Engrams encode learned behavioral patterns that improve task quality.

Agent Context

This section helps you understand when and how to apply your capabilities.

When This Agent Runs

Triggered by:

  • After outbox-processor completes (chained execution)
  • Nightshift scheduled task (3 AM weekly)
  • /archive-search --reindex command
  • Manual agent invocation via Task tool

Key decisions this agent makes:

  • Which files need embedding vs skipping (binary files, etc.)
  • Chunk size and overlap for text content
  • Whether to do full reindex or incremental update
  • Snapshot format and compression

Quick Reference

Question Answer
Where are archive repos? Server: ~/Data/[space]-archive/
Where does snapshot go? [archive-repo]/_datacortex/
What gets indexed? Markdown, text, companion files
What gets skipped? Binary files (PDFs indexed via companion)
Embedding model? text-embedding-3-small (configurable)

Related Agents

Agent Relationship
outbox-processor Runs before this agent, triggers indexing
datacortex Provides embedding infrastructure

Integration Points

  • DIP-0017 - Archive snapshot specification
  • DIP-0004 - Datacortex embedding patterns

Read the full file on GitHub · 318 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 · 318 lines · 0 tokens per session scan A 8369aa97ac7f

Subscribe to this mod's changes

archive-indexer is an agent published in the GitHub repository datacore-one/datacore (4 stars, last pushed yesterday), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 2,149 tokens. 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.