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.
npx agentmods add commands/proticom/gnosys/reindexgit clone --depth 1 https://github.com/proticom/gnosysWrote 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.
[](https://agentmods.dev/commands/proticom/gnosys/reindex)<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>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 | $0.00000 | $0.00354 |
| Opus 5 | $0.00000 | $0.00177 |
| Sonnet 5 | $0.00000 | $0.00071 |
| Haiku 4.5 | $0.00000 | $0.00035 |
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.
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
- Resolves configured stores via the project resolver.
- Clears the local search index for the primary store path.
- Re-adds memories from all configured stores to the search index.
- Loads
GnosysEmbeddingsandGnosysHybridSearch. - 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
Related commands
gnosys hybrid-search— hybrid keyword + semantic search (requires embeddings).gnosys semantic-search— semantic-only search (requires embeddings).gnosys import— bulk import memories before reindexing.
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.
- 4d ago First seen · 66 lines · 0 tokens per session scan A 715764b54051
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.
Other commands, from other repositories
wrap
Close the session cleanly. Update entity state. Capture decisions. Detect momentum shifts.
promote
Move .memory/ artifacts to permanent knowledge locations.
checkpoint
Create or update .memory/ with current conversation state.
cleanup
Delete promoted content from the .memory/ directory.
perf-investigate
Drive an iOS performance or memory-leak investigation on using Memory Graph + Time Profiler. Enforce data-before-architecture and stacked PRs.
gains
Show what Kage saved you — tokens, cost, stale memories blocked, stale knowledge caught.