What is archive-search?

A command for finding documents in archived storage by the meaning of a search query, rather than only matching exact words.

Use it to search all archives or one workspace, fetch full documents, and rebuild the archive search index.

It helps recover historical files without knowing their exact names or wording.

archive-search — Command for coding agents by datacore-one: A command for finding documents in archived storage by…

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 commands/datacore-one/datacore/archive-search

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.

README.md

[![agentmods](https://agentmods.dev/badge/commands/datacore-one/datacore/archive-search.svg)](https://agentmods.dev/commands/datacore-one/datacore/archive-search)

Your own site

<a href="https://agentmods.dev/commands/datacore-one/datacore/archive-search"><img src="https://agentmods.dev/badge/commands/datacore-one/datacore/archive-search.svg" alt="Measured on agentmods" height="20"></a>

Per session 11 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.

When invoked 1,420 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.

Model	Per session	Once invoked
Fable 5	$0.00011	$0.01420
Opus 5	$0.00005	$0.00710
Sonnet 5	$0.00002	$0.00284
Haiku 4.5	$0.00001	$0.00142

Measured yesterday against content hash c136fe211aee, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

archive-search 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/commands/archive-search.md · 216 lines

How it starts

The opening of the file, as written. The whole thing — 216 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Command: /archive-search

Search archived content using semantic similarity via datacortex embeddings.

Command Context

When to Reference DIP-0017

Always reference when:

Searching historical content
Finding archived documents
Retrieving content from server archives

Key decisions this DIP informs:

Archive snapshots use datacortex embeddings
Snapshots sync from server to local for search
Full content fetched on-demand via SSH

Quick Reference

Question	Answer
What gets searched?	Datacortex embedding snapshots
Where are snapshots?	`[space]/.archive-snapshot/` (synced from server)
What's the embedding model?	sentence-transformers/all-mpnet-base-v2
Can I get full content?	Yes, via `--fetch` option

Integration Points

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

Usage

/archive-search <query>                    # Search all archives
/archive-search --space <name> <query>     # Search specific space
/archive-search --reindex                  # Rebuild index (runs archive-indexer)

Examples

/archive-search "investor agreement terms"
/archive-search --space 1-teamspace "2019 financial statements"
/archive-search --fetch "1-tracks/legal/contracts/acme-2018.pdf"
/archive-search --sync                     # Sync snapshots from server first

Workflow

Phase 1: Snapshot Check

Check local snapshots in [space]/.archive-snapshot/

If missing or stale, offer to sync from server:

Archive snapshots not found locally.
Sync from server? [Y/n]

Phase 2: Semantic Search

Embed query using datacortex model
Search each space's snapshot:
- Load embeddings from archive.db
- Compute cosine similarity
- Rank by score
Return top results with excerpts

Phase 3: Content Retrieval (Optional)

If --fetch specified:

SSH to server
Cat file content
Return to user

Read the full file on GitHub · 216 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.

yesterday First seen · 216 lines · 11 tokens per session scan A c136fe211aee

Subscribe to this mod's changes

archive-search is a command published in the GitHub repository datacore-one/datacore (4 stars, last pushed today), licensed MIT. It adds 11 tokens to every session and 1,420 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 2026-09-03.

Research ai-assistant ai-memory claude-code gtd knowledge-management mcp

archive-search