A semantic search and storage workflow using ChromaDB, a vector database that finds content by meaning rather than exact words. It searches collections of descriptions, notes, memories, posts, and related material.

Use it to search for similar model descriptions or content, find items related to an existing record, manage vector collections, or store searchable notes and memories.

It helps find related content when the same idea is expressed with different words. It also stores searchable items so they can be added, updated, compared, or removed.

chromadb — Skill for Claude Code and Codex by ssube: A semantic search and storage workflow using ChromaDB, a…

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/ssube/conclave/chromadb

Any agent

npx skills add ssube/conclave --skill chromadb

Clone the repo

git clone --depth 1 https://github.com/ssube/conclave

Made for: Claude Code, Codex.

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/skills/ssube/conclave/chromadb.svg)](https://agentmods.dev/skills/ssube/conclave/chromadb)

Your own site

<a href="https://agentmods.dev/skills/ssube/conclave/chromadb"><img src="https://agentmods.dev/badge/skills/ssube/conclave/chromadb.svg" alt="Measured on agentmods" height="20"></a>

Per session 42 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 972 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	$0.00042	$0.00972
Opus 5	$0.00021	$0.00486
Sonnet 5	$0.00008	$0.00194
Haiku 4.5	$0.00004	$0.00097

Measured 4d ago against content hash 82322778f578, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

chromadb 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.

The scan reads SKILL.md. This mod also ships 1 executable file (query.py), 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.

pi/skills/chromadb/SKILL.md · 140 lines

How it starts

The opening of the file, as written. The whole thing — 140 lines — stays where its author put it; the contents beside it link to each section on GitHub.

ChromaDB Skill

Semantic search and vector storage using ChromaDB for finding similar content across collections.

Requirements

pip install chromadb

Usage

Query for similar items

python3 {baseDir}/query.py query "gothic fantasy creature" --collection models [--limit 5]

Find similar to existing item

python3 {baseDir}/query.py similar <id> --collection models [--limit 5]

Add or update content (upsert)

python3 {baseDir}/query.py add --collection models --id <id> --text "..." [--metadata '{"key": "value"}']

This command performs an upsert: if the ID already exists, it updates the content; otherwise, it creates a new entry.

List collections

python3 {baseDir}/query.py collections

Create a new collection

python3 {baseDir}/query.py create-collection <name>

Delete an item

python3 {baseDir}/query.py delete <id> --collection models

Collections

Pre-defined collections for different use cases:

Collection	Purpose
`models`	LoRA model descriptions (name, category, style notes)
`memories`	Bot memories and learned context
`notes`	User notes and reference material
`posts`	Posted content for semantic similarity checking

Environment Variables

All variables are optional with sensible defaults:

CHROMADB_HOST: ChromaDB server hostname (default: localhost)
CHROMADB_PORT: ChromaDB server port (default: 8000)
CHROMADB_PATH: Path for persistent storage (optional, uses server if not set)

Default Mode: The skill connects to the ChromaDB server at localhost:8000 by default. To use persistent local storage instead, set CHROMADB_PATH=/path/to/storage.

Metadata

Each item can have metadata for filtering:

python3 {baseDir}/query.py add \
    --collection models \
    --id creature_v2 \
    --text "A LoRA for generating fantasy creatures with detailed scales and claws" \
    --metadata '{"category": "creatures", "base_model": "flux", "quality": 5}'

Read the full file on GitHub · 140 lines

Files

What ships with it

1 file 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.

query.py 10 KB runs code

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.

4d ago First seen · 140 lines · 42 tokens per session scan A 82322778f578

Subscribe to this mod's changes

chromadb is a skill published in the GitHub repository ssube/conclave (2 stars, last pushed 6mo ago), licensed MIT. It adds 42 tokens to every session and 972 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 2026-08-31.

Data and AI Databases RAG and vectors ai-agents chromadb claude claude-code codex coding-assistant

vector-backend-operations

Select and connect the right vector-store backend for the vector-mcp MCP server — chromadb, postgres/pgvector, qdrant, couchbase, or mongodb — and supply the correct dbtype/connection parameters that every collection and search call needs. Use when the agent must decide which engine to target, wire up…

Knuckles-Team/vector-mcp · 113 tokens

vector-collection-management

Create, populate, list, and delete vector-store collections through the vector-mcp MCP server's vectorcollectionmanagement tool. Use when the agent must stand up a new RAG collection, ingest documents (from a directory, file paths/URLs, or raw text) into an existing collection, enumerate collections, or drop one …

Knuckles-Team/vector-mcp · 123 tokens

vector-mcp-operations

Operate vector-mcp through its governed MCP and GraphOS capabilities. Use for collection lifecycle, root-confined document ingestion, semantic or lexical retrieval, hybrid search, backend readiness, troubleshooting, and sanitized verification evidence.

Knuckles-Team/vector-mcp · 48 tokens

chromadb