reindex

reindex is a command for coding agents from proticom/gnosys. It costs 0 tokens per session (354 once invoked), scanned A, original, MIT.

A command that rebuilds semantic search indexes for every memory in configured stores. Semantic search finds memories by meaning, while embeddings are numerical representations used to compare that meaning.

In plain words
What is it for?
Use `gnosys reindex` to clear and rebuild the local index, create embeddings for all memories, and restore hybrid and semantic search.
Why use it?
It fixes or refreshes search when memories were imported in bulk, the storage schema changed, or meaning-based results are poor.

Command

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/proticom/gnosys/reindex
Clone the repo
git clone --depth 1 https://github.com/proticom/gnosys

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 reindex

README.md
[![agentmods](https://agentmods.dev/badge/commands/proticom/gnosys/reindex.svg)](https://agentmods.dev/commands/proticom/gnosys/reindex)
Your own site
<a href="https://agentmods.dev/commands/proticom/gnosys/reindex"><img src="https://agentmods.dev/badge/commands/proticom/gnosys/reindex.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 354 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 $0.00354
Opus 5 $0.00000 $0.00177
Sonnet 5 $0.00000 $0.00071
Haiku 4.5 $0.00000 $0.00035

Measured 4d ago against content hash 715764b54051, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

reindex 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 4d 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.

docs/commands/reindex.md · 66 lines

What it actually says

gnosys reindex

Rebuild semantic embeddings for every memory in configured stores.

Usage

gnosys reindex

Run after bulk imports, schema changes, or when hybrid/semantic search returns poor matches.

Behavior

  1. Resolves configured stores via the project resolver.
  2. Clears the local search index for the primary store path.
  3. Re-adds memories from all configured stores to the search index.
  4. Loads GnosysEmbeddings and GnosysHybridSearch.
  5. Builds semantic embeddings for all indexed memories.

On first run, downloads the all-MiniLM-L6-v2 embedding model (~80 MB).

Progress output

While indexing:

Building semantic embeddings (downloading model on first run)...
  Indexing: 12/240 — memories/architecture/decisions.md

Completion output

Reindex complete: 240 memories embedded.
Hybrid and semantic search are now available.

Errors

No stores configured:

No stores found. Run gnosys init first.

Exits with code 1.

Resource cleanup

Always closes the search index and embedding resources in a finally block, including when indexing fails.

Validation

cd gnosys-public
npm run cli -- reindex --help
npx vitest run src/test/reindex-command-handler.test.ts
  • gnosys hybrid-search — hybrid keyword + semantic search (requires embeddings).
  • gnosys semantic-search — semantic-only search (requires embeddings).
  • gnosys import — bulk import memories before reindexing.
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. 4d ago First seen · 66 lines · 0 tokens per session scan A 715764b54051

Subscribe to this mod's changes

reindex is a command published in the GitHub repository proticom/gnosys (4 stars, last pushed today), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 354 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 2026-08-31.