What is spendglass CLAUDE.md?

Repository instructions for working on Spendglass, including its contribution process and rules for handling bank-transaction data.

Use them when changing Spendglass, debugging with synthetic data, restarting its supervised service, or preparing and merging a pull request.

They prevent personal financial information from entering code, tests, documentation, commits, or chat, while defining safe development and merge practices.

How shawn-durrani/spendglass configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to shawn-durrani/spendglass. 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/shawn-durrani/spendglass/main/CLAUDE.md

Clone the repo

git clone --depth 1 https://github.com/shawn-durrani/spendglass

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/instructions/shawn-durrani/spendglass/claude-md/github.svg)](https://agentmods.dev/instructions/shawn-durrani/spendglass/claude-md)

Your own site

<a href="https://agentmods.dev/instructions/shawn-durrani/spendglass/claude-md"><img src="https://agentmods.dev/badge/instructions/shawn-durrani/spendglass/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.

Your own site · 80×15

<a href="https://agentmods.dev/instructions/shawn-durrani/spendglass/claude-md"><img src="https://agentmods.dev/badge/instructions/shawn-durrani/spendglass/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 590 This file is loaded in full into every session.

When invoked 590 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.

Model	Per session	Once invoked
Fable 5.1	$0.00590	$0.00590
Opus 5.5	$0.00236	$0.00236
Sonnet 5.5	$0.00118	$0.00118
Haiku 4.5	$0.00059	$0.00059

Measured 1mo ago against content hash ed459de7103b, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

spendglass 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 1mo 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 · 52 lines

How it starts

The opening of the file, as written. The whole thing — 52 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CLAUDE.md

Instructions for AI sessions working in this repository.

Process

The pipeline is written down once, in CONTRIBUTING.md. These rules are for a session with write access, working for the maintainer:

Merge your own pull requests once CI is green, without waiting for a human to approve them. The maintainer comments when they can. An external contributor's pull request is merged by the maintainer.
Never commit straight to main, and never branch off another open pull request.
Restart the supervised service only with launchctl kickstart -k gui/$(id -u)/dev.spendglass.server, and ask /api/busy first, as docs/OPERATIONS.md describes.

Rules that come before convenience

data/ holds real bank transactions. Never read, copy or quote what's in it into code, tests, docs, commits or chat. Debug with a disposable SPENDGLASS_DB in a folder of its own. Real merchant names and amounts are personal data, and so are account nicknames.
No real personal data goes in any diff. Use the fleet's synthetic roster. The people are Alex, Sam, Dave and Mateo, the place is Fairhaven, and the companies are AcmeCo, Initech and Globex. tests/conftest.py shows the house style for banks and accounts, such as Example Bank and acc-1.
Nothing may add a way to write to the bank or through the agent tools. The Redbark client only makes GET requests, and a test pins the exact list of read-only MCP tools. Widening either one is a decision for review, and a refactor never does it.
The suite stays green without keys. Every deterministic feature runs with no model configured, and CI runs without credentials to keep it that way.
Nothing is worked out from holdings or trades. The API can serve them and the store syncs them, but a recommendation about a portfolio is regulated financial advice. ARCHITECTURE.md has the decision.
Sum money in SQL over integer cents, and never let a language model work out an amount. Some trend and subscription maths runs in Python through floating point today, so don't copy it into new code.

Read the full file on GitHub · 52 lines

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.

1mo ago Changed · +6 lines · +98 tokens per session ed459de7103b
2mo ago First seen · 46 lines · 492 tokens per session scan A f59d1b5f580b

Subscribe to this mod's changes

spendglass CLAUDE.md is an instructions file published in the GitHub repository shawn-durrani/spendglass (2 stars, last pushed 1mo ago), licensed MIT. It adds 590 tokens to every session, about $0.0024 per session on Opus 5.5. 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.

Finance and fintech ai-agents local-first mcp mcp-server open-banking personal-finance

spendglass CLAUDE.md next to 6 instructions from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
spendglass CLAUDE.mdshawn-durrani/spendglass	Instructions file	2	1mo ago	MIT	A	590	Claude Code
vscode buildNext.instructions.mdmicrosoft/vscode	Instructions file	195k	today	MIT	A	9,719	GitHub Copilot
next.js AGENTS.mdvercel/next.js	Instructions file	144k	today	MIT	A	7,461	Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscode	Instructions file	195k	today	MIT	A	5,685	GitHub Copilot
langchain AGENTS.mdlangchain-ai/langchain	Instructions file	149k	today	MIT	A	4,680	Codex, OpenCode
deepseek-harness AGENTS.mddeepseek-ai/deepseek-harness	Instructions file	281k	yesterday	MIT	A	4,335	Codex, OpenCode
vscode copilot-instructions.mdmicrosoft/vscode	Instructions file	195k	today	MIT	A	3,086	GitHub Copilot

spendglass: Instructions file for Claude Code