sg-connectors: Instructions file for Claude Code

CLAUDE.md

sg-connectors CLAUDE.md is an instructions file for Claude Code from Lobang-Scout/sg-connectors. It costs 495 tokens per session, scanned A, original, MIT.

Project instructions for sg-connectors, a set of free MCP connectors for Singapore small-business data. They describe rules for company lookups and address or postal-code searches, including the limits of the source data.

In plain words
What is it for?
Guiding development of Singapore company and address connectors, including Python packaging, offline tests, and honest handling of monthly snapshot data.
Why use it?
They help contributors follow the project’s layout, packaging, testing, and data-accuracy rules without implying that unavailable fields exist.

Instructions file for Claude Code

Written for Claude Code: the file is CLAUDE.md.

This is Lobang-Scout/sg-connectors's own configuration. It tells Claude Code how to work on sg-connectors itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything sg-connectors configures →

Reuse

Borrowing it

Nothing to install: this file belongs to Lobang-Scout/sg-connectors. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/Lobang-Scout/sg-connectors/main/CLAUDE.md
Clone the repo
git clone --depth 1 https://github.com/Lobang-Scout/sg-connectors

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.

agentmods badge for sg-connectors CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/lobang-scout/sg-connectors/claude-md/github.svg)](https://agentmods.dev/instructions/lobang-scout/sg-connectors/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/lobang-scout/sg-connectors/claude-md"><img src="https://agentmods.dev/badge/instructions/lobang-scout/sg-connectors/claude-md/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.

agentmods 80×15 button for sg-connectors CLAUDE.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/lobang-scout/sg-connectors/claude-md"><img src="https://agentmods.dev/badge/instructions/lobang-scout/sg-connectors/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 495 This file is loaded in full into every session.
When invoked 495 The same file — it is already loaded in full.
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.
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 5.1 $0.00495 $0.00495
Opus 5 $0.00247 $0.00247
Sonnet 5 $0.00099 $0.00099
Haiku 4.5 $0.00049 $0.00049

Measured 10d ago against content hash 9ebeecfd4703, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

sg-connectors 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 10d 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.

CLAUDE.md · 35 lines

What it actually says

sg-connectors — project rules

Free, no-auth MCP connectors for Singapore SME data surfaces, by Lobang Scout. Connectors: sg-company-lookup (ACRA company/UEN over data.gov.sg) and sg-onemap (address/postal over OneMap). Packaged so each ships as a uvx-installable server.

Conventions

  • Python: use python3.12 explicitly. Servers are stdio MCP via FastMCP (mcp SDK).
  • Packaging: src/ layout, one console entry point per connector in pyproject.toml. Installable from git via uvx --from git+...<repo> <entry> — no PyPI publish needed.
  • Honest scope is a hard rule. Never return or imply fields the free dataset doesn't carry (officers, financials, full address, real-time status). Tests in tests/test_acra.py guard against inventing paywalled fields — keep them.
  • Snapshot honesty: every data response includes a note that the source is a monthly snapshot, not real-time. Don't strip it.
  • No live network in tests. Mock httpx. Live smoke tests are manual only.
  • Branching: task branch, no commits to main directly. Don't auto-commit.
  • No emojis. Keep docs tight.

Layout

  • src/sg_connectors/uen.py — UEN format validation (offline, no network).
  • src/sg_connectors/acra.py — data.gov.sg CKAN client + Entity shape.
  • src/sg_connectors/company_server.py — FastMCP sg-company-lookup server.
  • src/sg_connectors/onemap.py — OneMap Search client + Address shape.
  • src/sg_connectors/onemap_server.py — FastMCP sg-onemap server.
  • tests/ — pytest (asyncio_mode = auto, pythonpath = src); network mocked.

Adding a connector

Each new SG surface (e.g. postal/address, GST registration check) gets its own client module + tools, with the same honest-scope discipline: document exactly what the free source returns and what it can't, and add a test that guards the boundary.

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. 10d ago First seen · 35 lines · 495 tokens per session scan A 9ebeecfd4703

Subscribe to this mod's changes

sg-connectors CLAUDE.md is an instructions file published in the GitHub repository Lobang-Scout/sg-connectors (0 stars, last pushed 1mo ago), licensed MIT. It adds 495 tokens to every session, about $0.0025 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.

Related

Other instructions, from other repositories

vibe-coding-prompt-template backend.instructions.md

Instructions for KhazP/vibe-coding-prompt-template: Read AGENTS.md, agentdocs/techstack.md, and agentdocs/codepatterns.md.

KhazP/vibe-coding-prompt-template · 139 tokens

next.js AGENTS.md

AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.

vercel/next.js · 7,296 tokens

codex AGENTS.md

AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.

openai/codex · 5,153 tokens

vscode buildNext.instructions.md

Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).

microsoft/vscode · 6,785 tokens

spec-kit AGENTS.md

AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.

github/spec-kit · 7,104 tokens

langchain AGENTS.md

AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.

langchain-ai/langchain · 4,469 tokens