moss-search

A local search tool for finding documents by meaning as well as exact words. It uses named indexes, which are prepared collections of searchable text.

In plain words
What is it for?
Loading an index, searching support or code documentation, and creating an index from supplied text.
Why use it?
It helps find relevant passages when a search does not use the same wording as the stored document.

Skill for Claude CodeCodex

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 skills/usemoss/moss/zo-skill
Any agent
npx skills add usemoss/moss --skill zo-skill
Clone the repo
git clone --depth 1 https://github.com/usemoss/moss

Made for: Claude Code, Codex.

Per session 48 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,230 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 $0.00048 $0.01230
Opus 5 $0.00024 $0.00615
Sonnet 5 $0.00010 $0.00246
Haiku 4.5 $0.00005 $0.00123

Measured 3d ago against content hash 896e66e76579, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

moss-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 3d ago.

The scan reads SKILL.md. This mod also ships 2 executable files (install.sh, scripts/moss.sh), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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.

packages/zo-computer/zo-skill/SKILL.md · 157 lines

How it starts

The opening of the file, as written. The whole thing — 157 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Sub-10ms semantic search. Run from anywhere:

bash /home/workspace/Skills/moss-search/scripts/moss.sh load-index support-docs
bash /home/workspace/Skills/moss-search/scripts/moss.sh search support-docs "how long do refunds take?"
bash /home/workspace/Skills/moss-search/scripts/moss.sh create-index my-docs '[{"id":"1","text":"Refunds take 3-5 days."}]'

Commands

load-index

Download an index into memory for sub-10ms local queries. Always call this before searching an index for the first time.

bash /home/workspace/Skills/moss-search/scripts/moss.sh load-index <index-name>

Examples:

bash /home/workspace/Skills/moss-search/scripts/moss.sh load-index support-docs
bash /home/workspace/Skills/moss-search/scripts/moss.sh load-index code-docs

search

Search a loaded index. Sub-10ms after load-index.

bash /home/workspace/Skills/moss-search/scripts/moss.sh search <index-name> "<query>" [top_k]

Examples:

bash /home/workspace/Skills/moss-search/scripts/moss.sh search support-docs "how do I get a refund"
bash /home/workspace/Skills/moss-search/scripts/moss.sh search code-docs "authentication middleware" 10

create-index

Create a new index with initial documents.

bash /home/workspace/Skills/moss-search/scripts/moss.sh create-index <index-name> '<json-docs-array>'

Example:

bash /home/workspace/Skills/moss-search/scripts/moss.sh create-index faq '[{"id":"1","text":"Refunds take 3-5 business days."},{"id":"2","text":"Contact [email protected] for help."}]'

list-indexes

List all available indexes.

bash /home/workspace/Skills/moss-search/scripts/moss.sh list-indexes

add-docs

Add documents to an existing index.

bash /home/workspace/Skills/moss-search/scripts/moss.sh add-docs <index-name> '<json-docs-array>'

Example:

bash /home/workspace/Skills/moss-search/scripts/moss.sh add-docs faq '[{"id":"3","text":"Free shipping on orders over $50."}]'

Read the full file on GitHub · 157 lines

Files

What ships with it

3 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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 · 157 lines · 48 tokens per session scan A 896e66e76579

Subscribe to this mod's changes

moss-search is a skill published in the GitHub repository usemoss/moss (669 stars, last pushed 10d ago), licensed BSD-2-Clause. It adds 48 tokens to every session and 1,230 once invoked, about $0.0002 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 2026-08-30.

Related

Other skills, from other repositories

Hybrid Search Architect

Designs a hybrid retrieval pipeline combining dense vector search and BM25 sparse search with reciprocal rank fusion, and explains when to use each configuration.

Notysoty/openagentskills · 32 tokens

nemotron-retrieval-recipes

Use when planning, debugging, tuning, evaluating, exporting, or deploying public Nemotron embed/rerank retrieval recipes.

NVIDIA-NeMo/Nemotron · 36 tokens

mcp-local-rag

Searches, saves, and maintains a local document index through a local RAG MCP server. Use when user says "search my docs", "save this page", "read around that chunk", "sync my index", or invokes npx mcp-local-rag.

shinpr/mcp-local-rag · 61 tokens

tao-finetune-cosmos-embed

Cosmos-Embed1 video-text embedding for text-to-video retrieval, video-to-video search, semantic deduplication, and fine-tuning. Use when the user asks to "fine-tune Cosmos-Embed1", "run cosmos-embed inference", "export Cosmos-Embed1", "embed videos", or "search videos with text".

NVIDIA-TAO/tao-skill-bank · 79 tokens

pinecone:n8n

Build n8n workflows using the Pinecone Assistant node or Pinecone Vector Store node. Use when building RAG pipelines, chat-with-docs workflows, configuring Pinecone nodes in n8n, troubleshooting Pinecone n8n nodes, or asking about best practices for Pinecone in n8n.

pinecone-io/pinecone-claude-code-plugin · 67 tokens

pinecone:quickstart

Interactive Pinecone quickstart for new developers. Choose between two paths - Database (create an integrated index, upsert data, and query using Pinecone MCP + Python) or Assistant (create a Pinecone Assistant for document Q&A). Use when a user wants to get started with Pinecone for the first time or wants a guided…

pinecone-io/pinecone-claude-code-plugin · 79 tokens