A local semantic search tool for Claude Code. It can index information and find relevant passages by meaning, not only by exact words.

Use it to ingest sources, search your knowledge base, save notes, explain results, and show where information came from.

It helps locate useful information in your indexed files or web sources without manually searching through them.

quarry-dev — Plugin for Claude Code by punt-labs/quarry

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.

Clone the repo

git clone --depth 1 https://github.com/punt-labs/quarry

Made for: Claude Code.

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/plugins/punt-labs/quarry/plugin/github.svg)](https://agentmods.dev/plugins/punt-labs/quarry/plugin)

Your own site

<a href="https://agentmods.dev/plugins/punt-labs/quarry/plugin"><img src="https://agentmods.dev/badge/plugins/punt-labs/quarry/plugin/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

Your own site · 80×15

<a href="https://agentmods.dev/plugins/punt-labs/quarry/plugin"><img src="https://agentmods.dev/badge/plugins/punt-labs/quarry/plugin.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session not measured What this adds to a session before it is invoked.

When invoked not measured The manifest loads nothing itself; its 2 skills, 16 commands, 1 agent, 5 hooks cost 715 tokens a session between them.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

Origin original No closer match found in the catalogue.

Security

Grade A, and why

quarry-dev 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 24d 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.

plugin/.claude-plugin/plugin.json · 19 lines

What it actually says

{
  "name": "quarry-dev",
  "description": "Local semantic search for Claude Code: /find, /ingest, /remember, /explain, /source, /quarry",
  "version": "3.4.0",
  "author": {
    "name": "Punt Labs",
    "email": "[email protected]"
  },
  "mcpServers": {
    "quarry": {
      "type": "stdio",
      "command": "quarry",
      "args": [
        "mcp"
      ]
    }
  }
}

Contents

What it installs

The manifest is a name and a version. 2 skills, 16 commands, 1 agent, 5 hooks travel with it, and installing the plugin installs all of them — 715 tokens a session between them. Each is measured on its own page, and each can be installed alone.

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.

24d ago Changed fe6f58253ac2
26d ago Changed 27349960422c
1mo ago Changed ca51b85be130
1mo ago First seen · 19 lines scan A a8c27443acd4

Subscribe to this mod's changes

quarry-dev is a plugin published in the GitHub repository punt-labs/quarry (6 stars, last pushed yesterday), licensed MIT. Its token cost is not measured: this kind of file is read by the harness, not the model. 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.

Memory and context beta claude-code-plugin mcp-server ocr vector-search

toonify-mcp

Local context compression for Claude Code workflows, including structured data and debug-heavy output.

PCIRCLE-AI/toonify-mcp · not measured

memem

Persistent, self-evolving memory for Claude Code. Local-first, no cloud, browsable Obsidian vault.

TT-Wang/memem · not measured

captain-memo

Cross-AI local memory layer for Claude Code, Codex, Gemini CLI, Antigravity, goose, Cursor, opencode, Kimi CLI and more: hybrid search, six summarizer providers, hosted or local embedder. Replaces claude-mem.

kalinbogatzevski/captain-memo · not measured

axme-code

(Alpha) Persistent memory, architectural decisions, and safety guardrails for Claude Code. Your agent starts every session with full project context — stack, decisions, patterns, safety rules, and a handoff from the previous session.

AxmeAI/axme-code · not measured

sapience

Human-like memory and a judgment ledger for AI — persistent semantic memory that compounds across sessions, plus calibration and bias maps for your own predictions. Requires uv (https://docs.astral.sh/uv/) and OPENAIAPIKEY + ANTHROPICAPIKEY in your environment.

allenc84/sapience · not measured

astral

Context-budget manager for Claude Code. Warns before auto-compact and long-context accuracy degradation, checkpoints finished work so you can shed it, gates large file reads to subagents, recalls context evicted by compaction, guards against unrelated context switches, and audits unused agents/skills.

sourikduttanyu/astral · not measured