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/agigante80/actual-sync/claude-mdgit clone --depth 1 https://github.com/agigante80/Actual-syncWrote 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/agigante80/actual-sync/claude-md)<a href="https://agentmods.dev/instructions/agigante80/actual-sync/claude-md"><img src="https://agentmods.dev/badge/instructions/agigante80/actual-sync/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 5.1 | $0.07792 | $0.07792 |
| Opus 5 | $0.03896 | $0.03896 |
| Sonnet 5 | $0.01558 | $0.01558 |
| Haiku 4.5 | $0.00779 | $0.00779 |
Grade A, and why
Actual-sync 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 yesterday.
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 — 440 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.
Project Overview
Actual-sync is a self-hosted Node.js service that automates bank transaction synchronization for Actual Budget servers. It supports multiple budget instances, encrypted budgets, scheduling, multi-channel notifications, and a web dashboard with Prometheus metrics.
Commands
# Install git hooks (run once after cloning — also runs automatically via npm install)
git config core.hooksPath .githooks
# This installs a pre-push hook that runs npm test --coverage --ci before every push.
# Run all tests
npm test
# Run a single test file
npm test -- configLoader.test.js
# Run tests matching a name pattern
npm test -- --testNamePattern="should validate configuration"
# Watch mode for a specific file
npm run test:watch -- syncService.test.js
# Generate coverage report
npm run test:coverage
# Check for dead code (unused files/exports) with knip
npm run dead:check # blocking (exit 1 on findings); CI runs this in the lint job
npm run knip # report-only (always exit 0); for local diffing
# Report config that is written here but NOT YET IN EFFECT, because GitHub reads
# it only from the default branch (#204). Report-only, always exits 0.
# CI runs this in the lint job too (#211), so this is a convenience.
npm run drift:check
# Mutation testing — the verification bar here. Reintroduces each shipped
# defect one at a time and asserts the suite FAILS. Not in CI (it runs the
# whole suite once per mutation); run it before a release and after any
# change the catalog covers.
npm run test:mutation # all of them, full suite each
npm run test:mutation -- --fast # only each mutation's hinted test file
npm run test:mutation -- --ticket '#177' # one ticket's mutations
npm run test:mutation -- --list # what is covered, without running anything
npm run test:mutation -- --recover # restore a file after a hard kill
# Start the scheduled sync service
npm start
# Force immediate sync (all servers)
npm run sync
# Sync a specific server
npm run sync -- --server "ServerName"
# Validate config against schema
npm run validate-config
# List discovered bank accounts
npm run list-accounts
# View sync history
npm run history
# Regenerate docs/screenshots/* (Puppeteer, dev-only) and README metric badges
npm run screenshots
npm run badges:generate
# Bump version (updates VERSION + package.json + package-lock.json in sync;
# aborts if local version is behind the latest released tag). For a patch
# release you do not need this (the auto-release patch-bumps). Run it on
# `development` only to cut a MINOR or MAJOR release, which the auto-release
# then publishes as-is (see Git Workflow).
npm run version:bump -- minor # or: patch / major
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.
- yesterday First seen · 440 lines · 7,792 tokens per session scan A 13c365509236
Actual-sync CLAUDE.md is an instructions file published in the GitHub repository agigante80/Actual-sync (12 stars, last pushed 2d ago), licensed MIT. It adds 7,792 tokens to every session, about $0.0390 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 2026-09-04.
Other instructions, from other repositories
appwrite AGENTS.md
AGENTS.md instructions for appwrite/appwrite, covering appwrite, commands, stack, layout and libraries.
netdata AGENTS.md
AGENTS.md instructions for netdata/netdata, covering agents.md, goals, requirement language, working with the user and development principles.
SForum AGENTS.md
AGENTS.md instructions for zhuchunshu/SForum, covering agent guide, project intent, working principles, stack and directory map and commands.
selfhost-ai CLAUDE.md
Claude Code instructions for kossakovsky/selfhost-ai, covering claude.md, project overview, core architecture, key files and installation flow.
redd-archiver CLAUDE.md
Instructions for 19-84/redd-archiver, covering claude.md, project overview, deviations from global standards, build & run commands and docker development (primary method).
homelab-monitor CLAUDE.md
Claude Code instructions for SikamikanikoBG/homelab-monitor, covering claude.md and conventions.