Borrowing it
Nothing to install: this file belongs to super-turbo-engineer/goblin-mny. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/super-turbo-engineer/goblin-mny/main/CLAUDE.mdgit clone --depth 1 https://github.com/super-turbo-engineer/goblin-mnyWrote 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/super-turbo-engineer/goblin-mny/claude-md)<a href="https://agentmods.dev/instructions/super-turbo-engineer/goblin-mny/claude-md"><img src="https://agentmods.dev/badge/instructions/super-turbo-engineer/goblin-mny/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.
<a href="https://agentmods.dev/instructions/super-turbo-engineer/goblin-mny/claude-md"><img src="https://agentmods.dev/badge/instructions/super-turbo-engineer/goblin-mny/claude-md.svg" alt="Reviewed on agentmods" width="80" 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 | $0.03074 | $0.03074 |
| Opus 5 | $0.01537 | $0.01537 |
| Sonnet 5 | $0.00615 | $0.00615 |
| Haiku 4.5 | $0.00307 | $0.00307 |
Grade A, and why
goblin-mny 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 8d 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.
How it starts
The opening of the file, as written. The whole thing — 251 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md
Guidance for Claude Code when working in this repository.
Setup instructions for a new machine live in SETUP.md. This file is for working on the code.
What this is
A local-first MCP server that caches a user's New Zealand bank data from Akahu into SQLite and exposes it to a model as analysis tools. Single-user, runs on the user's own machine, no hosted component.
Akahu API ──sync.ts──▶ SQLite (+FTS5) ──queries.ts──▶ tools.ts ──stdio──▶ Claude
Runtime
Bun, not Node. The project ships as a single self-contained executable via
bun build --compile, which is only possible because bun:sqlite is built into
the runtime. Do not reintroduce better-sqlite3 or any other native N-API
module — it cannot be embedded in the compiled binary and would break
distribution, which is the whole point of the Bun move.
Commands
bun install
bun test # adapter + environment assumptions
bun run typecheck # tsc --noEmit
bun run dev -- <cmd> # CLI from source, e.g. bun run dev -- doctor
bun run serve # MCP server from source
bun run build # single executable -> dist/goblin-mny
bun run build:all # cross-compile all platforms -> dist/
bun run dev -- diagnose # propose per-user classification rules
bun run dev -- seed-demo # synthetic data — use this for all testing
bun run dev -- doctor # verify config + live Akahu credentials
Never test against real financial data. Use seed-demo (see Testing).
Layout
| File | Responsibility |
|---|---|
src/sqlite.ts |
Adapter over bun:sqlite. Named-param safety. Read this before touching SQL. |
src/internal.ts |
What counts as spending. Bank-agnostic detectors + the predicate every aggregate uses. |
src/rules.ts |
Per-user ~/.goblin-mny/rules.json. Where institution-specific patterns live. |
src/diagnose.ts |
Proposes rules from a user's own data. Never applies them. |
src/akahu.ts |
HTTP client. Endpoints, auth headers, cursor pagination, error messages. |
src/config.ts |
Loads/validates ~/.goblin-mny/config.json. Owns file permissions. |
src/db.ts |
Schema (one big SQL string), upserts. The only file that writes SQL DDL. |
src/sync.ts |
Orchestrates Akahu → DB. Sync modes, run history, status. |
src/queries.ts |
All read/analysis logic. Pure functions of (db, opts). No MCP awareness. |
src/tools.ts |
MCP tool definitions — schemas, descriptions, and thin calls into queries.ts. |
src/index.ts |
startServer() — the MCP stdio server. |
src/cli.ts |
Human-facing CLI, and the compiled binary's entry point. serve starts the MCP server. |
src/demo.ts |
Synthetic Akahu-shaped fixtures. |
skills/goblin-mny/SKILL.md |
Agent-facing judgment: multi-tool recipes, data pitfalls, tone. Embedded into the binary at build time and installed by goblin-mny install-skill, so it can never drift from the tools it describes. |
scripts/build-all.ts |
Cross-platform release builds. |
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.
- 8d ago First seen · 251 lines · 3,074 tokens per session scan A 788191b7bd88
goblin-mny CLAUDE.md is an instructions file published in the GitHub repository super-turbo-engineer/goblin-mny (0 stars, last pushed 1mo ago), licensed MIT. It adds 3,074 tokens to every session, about $0.0154 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
plan-forge caching.instructions.md
Caching patterns for .NET — IDistributedCache, Redis, in-memory, cache-aside, TTL strategies.
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.
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.
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).
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).
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.