counterpoise-ledger: Instructions file for Claude Code

CLAUDE.md

counterpoise-ledger CLAUDE.md is an instructions file for Claude Code from jeffjjohnston/counterpoise-ledger. It costs 4,156 tokens per session, scanned A, original, MIT.

Repository instructions for Counterpoise, a Next.js personal-finance app that uses double-entry accounting, investment tracking, PostgreSQL, login accounts, and Moneydance imports.

In plain words
What is it for?
Use them when developing Counterpoise, starting its database and development server, checking types and lint, or running unit and browser tests.
Why use it?
They give a coding agent the project context and the exact commands needed to run, check, build, and test the app.

Instructions file for Claude Code

Written for Claude Code: the file is CLAUDE.md. Also seen: reads .claude/ paths; mentions CLAUDE.md; mentions Claude Code.

This is jeffjjohnston/counterpoise-ledger's own configuration. It tells Claude Code how to work on counterpoise-ledger 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 counterpoise-ledger configures →

Reuse

Borrowing it

Nothing to install: this file belongs to jeffjjohnston/counterpoise-ledger. 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/jeffjjohnston/counterpoise-ledger/main/CLAUDE.md
Clone the repo
git clone --depth 1 https://github.com/jeffjjohnston/counterpoise-ledger

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 counterpoise-ledger CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/jeffjjohnston/counterpoise-ledger/claude-md/github.svg)](https://agentmods.dev/instructions/jeffjjohnston/counterpoise-ledger/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/jeffjjohnston/counterpoise-ledger/claude-md"><img src="https://agentmods.dev/badge/instructions/jeffjjohnston/counterpoise-ledger/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 counterpoise-ledger CLAUDE.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/jeffjjohnston/counterpoise-ledger/claude-md"><img src="https://agentmods.dev/badge/instructions/jeffjjohnston/counterpoise-ledger/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 4,156 This file is loaded in full into every session.
When invoked 4,156 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 $0.04156 $0.04156
Opus 5.5 $0.01662 $0.01662
Sonnet 5.5 $0.00831 $0.00831
Haiku 4.5 $0.00416 $0.00416

Measured 7d ago against content hash 4da91898953e, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

counterpoise-ledger 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 7d 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 · 236 lines

How it starts

The opening of the file, as written. The whole thing — 236 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CLAUDE.md

This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository.

This file is the index. It holds the commands, the rules that apply everywhere, and the warnings you must read before you act. Everything else is in guides/, one file per subject. Read the guide for the subject you are about to touch. The guides carry the reasons, and a rule without its reason is the rule that gets undone.

This checkout is for development only. Development needs no Docker and no Cloudflare account: the Rust server keeps its SQLite file in data/.

Production has two targets. COUNTERPOISE_DEPLOY_TARGET selects the target that a release deploys to. Set it in the environment or in the gitignored .env.deploy.local. See guides/architecture.md.

  • worker: the Cloudflare Worker in rust-api/worker/. One Durable Object holds the database. The owner's production runs on this target. When a release PR merges into main, GitHub Actions publishes the tag and deploys it. No local checkout or container takes part.
  • docker (the default): one image, one container and one process, from docker-compose.yml in a separate checkout on main. The default path is ~/counterpoise-production. COUNTERPOISE_BUILD_DIR (in the environment or in .env.deploy.local) can name another directory. That checkout has its own .env.production.local and backups/. An install on its own machine uses this target. docker-compose.yml is for this target only.

Project Overview

Counterpoise is a multi-book personal finance accounting application with true double-entry bookkeeping and investment tracking. The UI is a React and React Router client that Vite builds into static files (client/, pages in app/). A Rust server (axum and rusqlite, in rust-api/) serves every /api route, the MCP server and, on the Docker target, the client build; the browser runs its shared domain code as WASM. One SQLite database holds all data: a file (DATABASE_PATH) on the Docker target, the Durable Object's own storage on the Worker. The server applies the numbered SQL migrations in rust-api/db/migrations/ at startup, and runs the scheduled jobs and the backups itself. The Docker target is one image, one container and one process. The Worker runs the same router inside its Durable Object, and the object's alarm runs the jobs. The app supports user authentication, shared books, and a Moneydance import tool (ledger-cli import-moneydance).

Read the full file on GitHub · 236 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.

  1. 7d ago Changed · +24 lines · +531 tokens per session 4da91898953e
  2. 28d ago Changed · -1 lines · -31 tokens per session b7a0096ab6cd
  3. 1mo ago Changed · +11 lines · +314 tokens per session 12dd1fe4485c
  4. 1mo ago Changed · +12 lines · +602 tokens per session 486ad47cf31a
  5. 1mo ago Changed · -1,116 lines · -19,435 tokens per session 6097fd55f6a2
  6. 2mo ago First seen · 1,306 lines · 22,175 tokens per session scan A 5f364a82a7d5

Subscribe to this mod's changes

counterpoise-ledger CLAUDE.md is an instructions file published in the GitHub repository jeffjjohnston/counterpoise-ledger (9 stars, last pushed 8d ago), licensed MIT. It adds 4,156 tokens to every session, about $0.0166 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.

Related

counterpoise-ledger CLAUDE.md compared with instructions from other repositories

counterpoise-ledger CLAUDE.md next to 6 instructions from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
counterpoise-ledger CLAUDE.mdjeffjjohnston/counterpoise-ledgerInstructions file98d agoMITA4,156Claude Code
vscode buildNext.instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA9,719GitHub Copilot
next.js AGENTS.mdvercel/next.jsInstructions file143kyesterdayMITA7,461Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA5,516GitHub Copilot
langchain AGENTS.mdlangchain-ai/langchainInstructions file149kyesterdayMITA4,680Codex, OpenCode
vscode copilot-instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA3,093GitHub Copilot
vscode ai-customization.instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA1,907GitHub Copilot