Monarch Money

TypeScript library and CLI for Monarch Money budget management. Search transactions by date/merchant/amount, update categories, list accounts and budgets, manage authentication. Use when user asks about Monarch Money transactions, wants to categorize spending, needs to find specific transactions, or wants to automate budget tasks.

This package appears coherent for a Monarch Money CLI, but it requires highly sensitive credentials (password + full TOTP/MFA secret). Before installing: (1) verify the source/maintainer since the registry 'Source: unknown' provides no upstream homepage; (2) review the bundled code yourself (or inspect the CaptchaAvoidanceService/CaptchaHandler files) if you are concerned about automation that attempts to circumvent interactive protections; (3) prefer using a throwaway or limited account if you must supply credentials/MFA secret for automation; (4) note that the tool stores session data in ~/.mm/session.json and saves an email to ~/.mm/cli-config.json — check file permissions and delete sessions when no longer needed; (5) be careful running the bundled tests or the 'test' command with write-enabled flags (--allow-writes or --all), as E2E write tests will modify real account data. If you need higher assurance, ask the publisher for provenance (homepage/repo) or run the CLI in an isolated environment first.

Type: OpenClaw Skill Name: monarch-money Version: 1.0.1 The OpenClaw AgentSkills skill bundle for Monarch Money is a well-structured Node.js CLI and library designed for legitimate interaction with the Monarch Money API. It handles sensitive user credentials (email, password, MFA secret) as required for its stated purpose, storing session and cache data locally in encrypted files with appropriate permissions (`~/.mm/session.json`, `~/.mm/cache.json`). The use of `child_process.spawn` in `cli/commands/test.ts` is limited to running internal E2E tests and is explicitly guarded for write operations, indicating a developer tool rather than malicious intent. There is no evidence of data exfiltration to unauthorized endpoints, malicious execution, persistence mechanisms, or prompt injection attempts in `SKILL.md` or other documentation.