knowledge_search

A workspace search tool that finds information in your documents by meaning, not just exact words. It can also list available documents and return a whole document.

In plain words
What is it for?
Use it to answer questions about workspace documents, search for related text, browse the document collection, or read a selected document in full.
Why use it?
It helps you find relevant passages without knowing the exact wording or file where the information is stored.

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/binary16labs/prime-silo/knowledge_search
Any agent
npx skills add binary16labs/prime-silo --skill knowledge_search
Clone the repo
git clone --depth 1 https://github.com/binary16labs/prime-silo

Made for: Claude Code, Codex.

Per session 15 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 212 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 $0.00015 $0.00212
Opus 5 $0.00008 $0.00106
Sonnet 5 $0.00003 $0.00042
Haiku 4.5 $0.00002 $0.00021

Measured 2d ago against content hash 32622972deb9, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

knowledge_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 2d 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.

runtime/skills/knowledge_search/SKILL.md · 21 lines

What it actually says

Usage

Use this skill when you need to answer questions or find information within the user's workspace documents. It is backed by ChromaDB and local embeddings. You can search semantically, list all available documents, or retrieve an entire document's contents.

Tools

  • search_knowledge_workspace(query, workspace="default", top_k=20, active_nexus_id=None) - Perform semantic search and return relevant text chunks with relevance scores.
  • list_available_documents(workspace="default") - Returns a list of all documents currently ingested into the ChromaDB knowledge base.
  • read_full_document(document_name, workspace="default") - Retrieves the complete text of a specified document.

Examples

Action: search_knowledge_workspace Action Input: {"query": "governance policies for the Pypes engine"} Observation: Returns chunks of requirement.md discussing Pypes engine governance.

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. 2d ago First seen · 21 lines · 15 tokens per session scan A 32622972deb9

Subscribe to this mod's changes

knowledge_search is a skill published in the GitHub repository binary16labs/prime-silo (5 stars, last pushed 9d ago), licensed MIT. It adds 15 tokens to every session and 212 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 2026-08-31.