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 instructions/punt-labs/quarry/claude-mdgit clone --depth 1 https://github.com/punt-labs/quarryWrote 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/instructions/punt-labs/quarry/claude-md)<a href="https://agentmods.dev/instructions/punt-labs/quarry/claude-md"><img src="https://agentmods.dev/badge/instructions/punt-labs/quarry/claude-md.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 5.1 | $0.08428 | $0.08428 |
| Opus 5 | $0.04214 | $0.04214 |
| Sonnet 5 | $0.01686 | $0.01686 |
| Haiku 4.5 | $0.00843 | $0.00843 |
Grade A, and why
quarry CLAUDE.md 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 today.
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.
How it starts
The opening of the file, as written. The whole thing — 290 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Quarry
Part of Punt Labs. This repo must be checked out inside the punt-labs/ workspace meta-repo so that org-wide configuration loads via Claude Code's ancestor directory walk:
punt-labs/CLAUDE.md— org workflow, delegation model, beads issue tracking, tool configurationpunt-labs/.claude/rules/python-*.md— 19 Python OO coding rules, scoped viapaths:frontmatter (load on-demand when.pyfiles are touched)punt-labs/.envrc— git identity, beads DB connection, API keys from platform keychainpunt-kit/standards/— canonical reference docs
If cloned outside the workspace, these rules and configuration will not be present.
OO Python standards adopted 2026-05-13. The codebase does not yet fully comply. Every commit must improve OO scores (make check-oo), never regress. Do not match existing code patterns that violate the rules — write new code to the standard and improve touched files incrementally.
Local semantic search for AI agents and humans. Indexes 20+ document formats, embeds with a local ONNX model (snowflake-arctic-embed-m-v1.5, 768-dim), stores vectors in LanceDB, serves via MCP (stdio or WebSocket daemon on port 8420).
- Package:
punt-quarry - CLI:
quarry - MCP server:
quarry mcp(stdio) ormcp-proxy→ daemon (/mcpWebSocket); there is noquarry-serverentry point - Python: 3.13+, managed with
uv
Mandatory Reading
Source-of-truth documents, @-imported so they stay in context. Read them
before writing code.
docs/WORKFLOW.mdis the authoritative development process: three nested loops (backlog → PR → mission), each with pseudocode for its control flow and a Z schema for its entry/exit doorway conditions. The Development Loop section below is a pointer to it, not a second copy.DESIGN.mdis the ADR log (DES-001+); on any conflict about settled architecture, it wins. Read it before proposing 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.
- today Changed · +1 lines · +312 tokens per session 977a2bc7241c
- 6d ago First seen · 289 lines · 8,116 tokens per session scan A b21277cbab9b
quarry CLAUDE.md is an instructions file published in the GitHub repository punt-labs/quarry (3 stars, last pushed yesterday), licensed MIT. It adds 8,428 tokens to every session, about $0.0421 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.
Other instructions, from other repositories
mcp-documentation-server copilot-instructions.md
Instructions for andrea9293/mcp-documentation-server, covering mcp documentation server - ai coding agent instructions, architecture overview, core components, server entry point (src/server.ts) and embedding providers (src/embedding-provider.ts).
notebooklm-skill copilot-instructions.md
Instructions for claude-world/notebooklm-skill: This Python project provides a JSON-first CLI, five async pipelines, and 13 MCP tools for NotebookLM. Keep all notebooklm-py API adaptation in scripts/common.py so the three public surfaces stay consistent. Follow the Ruff and mypy configuration, use typed async code…
rag-rat AGENTS.md
Instructions for cq27-dev/rag-rat, covering agents.md, prefer the rag-rat mcp for code browsing, record durable learnings as rag-rat memories, repo orientation and worktree correctness.
obsidian-rag CLAUDE.md
Instructions for thoreinstein/obsidian-rag, covering obsidian-rag, architecture, build, key constraints and data paths.
local_faiss_mcp CLAUDE.md
Instructions for nonatofabio/local_faiss_mcp, covering claude.md, project overview, architecture, key design principles and development commands.
personal-notes-assistant CLAUDE.md
Instructions for coeusyk/personal-notes-assistant, covering personal-notes-assistant, architecture, adding a tool, milvus notes (non-obvious, bit people twice already) and running / testing locally.