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/paulieb89/property-shared/claude-mdgit clone --depth 1 https://github.com/paulieb89/property-sharedWrote 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/paulieb89/property-shared/claude-md)<a href="https://agentmods.dev/instructions/paulieb89/property-shared/claude-md"><img src="https://agentmods.dev/badge/instructions/paulieb89/property-shared/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 | $0.03258 | $0.03258 |
| Opus 5 | $0.01629 | $0.01629 |
| Sonnet 5 | $0.00652 | $0.00652 |
| Haiku 4.5 | $0.00326 | $0.00326 |
Grade A, and why
property-shared 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 — 218 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md
@GUIDELINES.md
This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository.
Project Overview
Property Shared is a FastAPI service + pure-Python core library for UK property data. It integrates:
- PPD (Price Paid Data) - Land Registry transactions via SPARQL/Linked Data API
- EPC - Energy Performance Certificates (requires API credentials)
- Rightmove - Property listings via scraping with built-in politeness
- Planning - UK council planning applications via vision-guided browser automation (99 verified councils)
- Stamp Duty - SDLT calculator with April 2025 bands, additional property/FTB/non-resident surcharges
- Block Analyzer - Groups PPD transactions by building to find bulk-buy opportunities
- Companies House - Company search and lookup via free API (requires API key)
Commands
# Install dependencies (dev tooling installs by default via [dependency-groups])
uv sync
# Run API server
uv run --extra api --env-file .env property-api # production mode
uv run --extra api --env-file .env uvicorn app.main:app --reload # dev mode with reload
# Run CLI (core mode - no server needed)
uv run --extra cli property-cli meta
uv run --extra cli property-cli ppd comps "SW1A 1AA" --months 24
uv run --extra cli property-cli rightmove search-url "SW1A 1AA"
uv run --extra cli property-cli calc stamp-duty 300000
uv run --extra cli property-cli ppd blocks "B1 1AA"
uv run --extra cli property-cli companies search "Tesco"
uv run --extra cli property-cli analysis yield "NG1 1AA"
uv run --extra cli property-cli analysis rental "NG1 1AA"
# CLI targeting running API (add --api-url)
uv run --extra cli property-cli ppd comps "SW1A 1AA" --api-url http://localhost:8000
# Full validation (lockfile check, pre-commit, all extras, full suite) —
# run this, don't hand-assemble the extras yourself; it's the same
# entrypoint CI and the release gate use.
./scripts/validate.sh # unit tests (mocked)
RUN_LIVE_TESTS=1 ./scripts/validate.sh # + live network tests
# Single test
uv run --extra api --extra apps --extra cli pytest tests/test_ppd_service_live.py -v
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 · +6 lines · +82 tokens per session edfa6ca74dc7
- yesterday Changed · +9 lines · +82 tokens per session 3427c6e8d402
- 6d ago First seen · 203 lines · 3,094 tokens per session scan A ec4a20979a6e
property-shared CLAUDE.md is an instructions file published in the GitHub repository paulieb89/property-shared (16 stars, last pushed yesterday), licensed MIT. It adds 3,258 tokens to every session, about $0.0163 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.
Other instructions, from other repositories
python-sdk AGENTS.md
AGENTS.md instructions for modelcontextprotocol/python-sdk, covering development guidelines, note for ai agents, branching model, package management and code quality.
Embody AGENTS.md
AGENTS.md instructions for dylanroscover/Embody, covering embody + envoy - ai instructions, critical rules, td python rules, network layout rules and mcp server safety rules.
Cortex CLAUDE.md
Claude Code instructions for cdeust/Cortex, covering cortex — persistent memory mcp server, problem statement, build & test, releasing and architecture.
ros2_mcp AGENTS.md
AGENTS.md instructions for wise-vision/ros2_mcp, covering agent instructions, project layout, dev setup (preferred), running locally and tests.
NetLicensing-MCP AGENTS.md
AGENTS.md instructions for Labs64/NetLicensing-MCP, covering agents.md, development commands, install dev environment (editable + dev extras), run the server locally and lint / format / type-check (these are the exact ci checks).
naja-scope CLAUDE.md
Claude Code instructions for najaeda/naja-scope: When writing code that talks to najaeda — inside src/najascope/ or in throwaway exploration scripts — always go through from najaeda import naja (the raw naja.so binding: NLUniverse, NLDB, SNL objects) and never through najaeda.netlist (the high-level…