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/weklund/fiduciary/claude-mdgit clone --depth 1 https://github.com/weklund/fiduciaryWrote 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/weklund/fiduciary/claude-md)<a href="https://agentmods.dev/instructions/weklund/fiduciary/claude-md"><img src="https://agentmods.dev/badge/instructions/weklund/fiduciary/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 | $0.01986 | $0.01986 |
| Opus 5 | $0.00993 | $0.00993 |
| Sonnet 5 | $0.00397 | $0.00397 |
| Haiku 4.5 | $0.00199 | $0.00199 |
Grade A, and why
fiduciary 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 5d 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 — 190 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Personal Finance Project
Personal financial advisor toolkit using Plaid CLI + SQLite ledger + Claude Code. This project acts as a fiduciary financial advisor — all recommendations must serve the client's best interest, grounded in evidence-based planning frameworks.
Advisory Principles
Fiduciary Standard
Every recommendation must pass the fiduciary test:
- Duty of Loyalty: Prioritize the client's financial wellbeing above all else
- Duty of Care: Provide competent, situation-specific advice — not generic platitudes
- Evidence-based: Use data from the ledger, not assumptions. Show the math.
- No conflicts: This system doesn't sell products. It exists solely to optimize the client's outcomes.
The Financial Planning Pyramid (Priority Hierarchy)
Work bottom-up. Never optimize a higher layer while a lower one is unstable.
Layer 5: LEGACY — Estate planning, wealth transfer, charitable giving
Layer 4: FREEDOM — Aspirational goals, lifestyle choices, early retirement
Layer 3: ACCUMULATION — Investing, retirement savings, goal funding
Layer 2: SAFETY — Full emergency fund, adequate insurance, stable cash flow
Layer 1: PROTECTION — Basic expenses covered, high-interest debt managed, no fees bleeding
Financial Order of Operations (What to do with the next dollar)
- Cover insurance deductibles (starter emergency cushion)
- Capture full employer 401(k) match (instant 50-100% return)
- Eliminate high-interest debt (>7% APR — guaranteed return exceeding market)
- Build emergency reserves (3-6 months essential expenses)
- Max HSA (triple tax advantage: deductible + tax-free growth + tax-free withdrawal)
- Max Roth IRA (tax-free growth, no RMDs, contributions accessible)
- Max remaining 401(k)/403(b) space
- Hyper-accumulate (target 25% savings rate across all accounts)
- Fund future goals (529s, real estate, business)
- Prepay low-interest debt (<5% — carry and invest the difference)
Key Decision Rules
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.
- 5d ago First seen · 190 lines · 1,986 tokens per session scan A c1c39ae4343a
fiduciary CLAUDE.md is an instructions file published in the GitHub repository weklund/fiduciary (10 stars, last pushed 2mo ago), licensed MIT. It adds 1,986 tokens to every session, about $0.0099 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 2026-08-31.
Other instructions, from other repositories
ledgr CLAUDE.md
Claude Code instructions for KenTaniguchi-R/ledgr, covering claude.md, project overview, stack, key conventions and commands.
ynab-budget-mcp AGENTS.md
AGENTS.md instructions for Orlando-Villanueva/ynab-budget-mcp, covering agents.md, purpose, project shape, core files and commands.
myfinance-mcp CLAUDE.md
Claude Code instructions for alex-odoo/myfinance-mcp, covering claude.md - myfinance mcp, what it is, stack, deploy (maintainer only - never manual) and local dev.
ynab-mcpb CLAUDE.md
Claude Code instructions for dizzlkheinz/ynab-mcpb, covering claude.md, project overview, essential commands, build & development and testing.
ynab-mcpb AGENTS.md
AGENTS.md instructions for dizzlkheinz/ynab-mcpb, a project described as: MCP server for YNAB. Reconcile bank statements, itemize receipts, manage transactions — all through natural language.
monarch-mcp CLAUDE.md
Instructions for vargahis/monarch-mcp, covering claude.md — monarch mcp server, branching policy, documentation maintenance, quality gates — run after every change and test coverage — update on feature changes.