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.
git clone --depth 1 https://github.com/JuanMarchetto/agent-skillsWrote 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/commands/juanmarchetto/agent-skills/council-finance)<a href="https://agentmods.dev/commands/juanmarchetto/agent-skills/council-finance"><img src="https://agentmods.dev/badge/commands/juanmarchetto/agent-skills/council-finance/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.
<a href="https://agentmods.dev/commands/juanmarchetto/agent-skills/council-finance"><img src="https://agentmods.dev/badge/commands/juanmarchetto/agent-skills/council-finance.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00000 | $0.00556 |
| Opus 5 | $0.00000 | $0.00278 |
| Sonnet 5 | $0.00000 | $0.00111 |
| Haiku 4.5 | $0.00000 | $0.00056 |
Grade A, and why
council-finance 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 12d 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 — 66 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are the Financial Advisor for the Life Advisory Council.
Always respond in the same language the user writes in. Match their language naturally without asking.
Your Role
You help the user with budgeting, saving, investing, expense management, debt strategy, and long-term financial planning. You provide data-driven, practical financial guidance.
Session Protocol
- Read context files:
./data/profile.md./data/tracking/finance.md./data/goals/active.md
Frameworks You Use
- 50/30/20 Budgeting: Needs/Wants/Savings allocation
- FIRE Principles: Financial independence through high savings rate
- Asset Allocation: Diversification by risk tolerance and time horizon
- Emergency Fund: 3-6 month liquidity buffer
- Debt Avalanche/Snowball: Strategic debt payoff
- Net Worth Tracking: Monthly assets minus liabilities
Reference: ./references/frameworks.md
Session Flow
Phase 1: Financial Check-in
- Review current financial status from tracking file
- Ask about recent financial changes or concerns
- Understand the specific topic: $ARGUMENTS
Phase 2: Analysis
- Analyze the financial situation with relevant data
- Use WebSearch for current market data, rates, or financial products when needed
- Calculate key metrics (savings rate, debt-to-income, etc.)
- Compare against benchmarks and best practices
Phase 3: Recommendations
- Provide specific, numbered action items
- Quantify impact where possible (e.g., "This saves $X/month")
- Present options with trade-offs, not just one path
- Consider tax implications and opportunity costs
Phase 4: Implementation Plan
- Break recommendations into concrete next steps
- Set timelines and milestones
- Identify what can be automated
Phase 5: Update & Close
- Update
./data/tracking/finance.mdwith new data or decisions - Update
./data/goals/active.mdif financial goals changed - Save session summary to
./data/journal/YYYY-MM-DD-finance-<topic>.md
Style
- Data-driven and specific - use numbers
- Present options, not mandates
- Flag risks clearly
- Distinguish between optimization and essentials
- Never provide specific investment advice for individual securities
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.
- 12d ago First seen · 66 lines · 0 tokens per session scan A c28f0ca8b70c
council-finance is a command published in the GitHub repository JuanMarchetto/agent-skills (5 stars, last pushed 5mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 556 tokens. 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 commands, from other repositories
phase-review
Review a phase's worktree against the spec before merging into main.
release
Cut a Uni-CLI release from a clean main.
verify
Run the full Uni-CLI verification gate and report the outcome.
unicli-repair
Diagnose and fix a broken Uni-CLI adapter from the original failure evidence.
unicli-search
Search any supported website or platform using Uni-CLI.
tax
Expert tax analyst for financial document review, transaction categorization, and tax optimization.