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/peterjthomson/ledger/claude-mdgit clone --depth 1 https://github.com/peterjthomson/ledgerWrote 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/peterjthomson/ledger/claude-md)<a href="https://agentmods.dev/instructions/peterjthomson/ledger/claude-md"><img src="https://agentmods.dev/badge/instructions/peterjthomson/ledger/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 | $0.04324 | $0.04324 |
| Opus 5 | $0.02162 | $0.02162 |
| Sonnet 5 | $0.00865 | $0.00865 |
| Haiku 4.5 | $0.00432 | $0.00432 |
Grade A, and why
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 4d 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 — 474 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md - Ledger Project Reference
Project Overview
Ledger is a macOS Electron desktop application for managing Git repositories with first-class support for AI agent worktrees, Pull Requests, and Branches. It provides real-time visibility into multiple parallel coding agents (Cursor, Claude, Conductor, Gemini, Junie) working in Git worktrees.
Core Value Proposition: Traditional Git interfaces don't surface multi-worktree activity from AI agents. Ledger solves this by detecting agent workspaces, showing live diff stats, and providing unified branch/PR/worktree management.
Tech Stack: Electron 37 + React 19 + TypeScript 5 + Vite + simple-git
Architecture
┌─────────────────────────────────────────────────────────────┐
│ Main Process (Node.js) │
│ lib/main/main.ts - IPC handler registration │
│ lib/main/git-service.ts - All Git operations (3030 LOC) │
│ lib/main/settings-service.ts - JSON persistence │
│ lib/main/app.ts - Window creation │
└──────────────────────────┬──────────────────────────────────┘
│ ipcMain.handle() / ipcRenderer.invoke()
┌──────────────────────────┴──────────────────────────────────┐
│ Preload Script (Bridge) │
│ lib/preload/preload.ts - contextBridge.exposeInMainWorld │
└──────────────────────────┬──────────────────────────────────┘
│ window.electronAPI
┌──────────────────────────┴──────────────────────────────────┐
│ Renderer Process (React) │
│ app/app.tsx - Main component (~4000 LOC) │
│ app/renderer.tsx - React mount point │
│ app/components/ - UI components │
│ app/styles/app.css - Styling with CSS variables │
└─────────────────────────────────────────────────────────────┘
IPC Pattern: All async via ipcMain.handle() ↔ ipcRenderer.invoke(). Kebab-case channels. Standard response: { success: boolean, message: string }.
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.
- 4d ago First seen · 474 lines · 4,324 tokens per session scan A 1dba5fe4b9db
ledger CLAUDE.md is an instructions file published in the GitHub repository peterjthomson/ledger (326 stars, last pushed 1mo ago), licensed MIT. It adds 4,324 tokens to every session, about $0.0216 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
Grace AGENTS.md
AGENTS.md instructions for ScottArbeit/Grace, covering agent instructions, agent quickstart (local), issue tracking, development process and markdown guidelines.
ESAA-Core AGENTS.md
Instructions for elzobrito/ESAA-Core, covering agents.md — contrato operacional codex/esaa, 1. autoridade e termos, 2. cli e runner, ou configure o runner uma vez por sessão and 3. concorrência.
Kanvas AGENTS.md
Instructions for XMihura/Kanvas, covering canvas workflow — agent instructions, critical rule, session protocol, 1. start of session — read the board and 2. pick a task.
delivery-loop CLAUDE.md
Instructions for blakemartz/delivery-loop, covering claude.md, what this is, the cardinal rule: everything must stay repo-agnostic, layout and config: the one seam.
taskcenter AGENTS.md
AGENTS.md instructions for xiaogezi/taskcenter, covering taskcenter agent rules, safety boundaries, required workflow and verification.
idd-skill idd-resume.instructions.md
Instructions for kurone-kito/idd-skill, covering idd — resume phase, required inputs, step 0 — route classifier, operator-present release and step 1 — identify claim state.