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 skills add albeorla/personal-finance-agent --skill finance-skillgit clone --depth 1 https://github.com/albeorla/personal-finance-agentWrote 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/skills/albeorla/personal-finance-agent/finance-skill)<a href="https://agentmods.dev/skills/albeorla/personal-finance-agent/finance-skill"><img src="https://agentmods.dev/badge/skills/albeorla/personal-finance-agent/finance-skill/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/skills/albeorla/personal-finance-agent/finance-skill"><img src="https://agentmods.dev/badge/skills/albeorla/personal-finance-agent/finance-skill.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 | $0.00062 | $0.01226 |
| Opus 5.5 | $0.00025 | $0.00490 |
| Sonnet 5.5 | $0.00012 | $0.00245 |
| Haiku 4.5 | $0.00006 | $0.00123 |
Grade A, and why
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 2mo 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 — 93 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Finance Ritual
This skill drives the local finance MCP server (financial-agent). It owns the
source-of-truth reads, deterministic projections, provenance, and guarded
actions. Your job is to call the right tools in the right order and report what
they return — never to guess a number.
Hard rule
Every financial claim (a balance, an amount due, a date, a projection) MUST be backed by a finance MCP tool result in the same turn. If you do not have a tool result for it, say so and call the tool. Do not estimate, recall, or extrapolate dollar figures.
When the user corrects an account fact, re-read that account's live state with a
finance MCP tool (get_finance_status or get_daily_digest) in the same turn
before acting on the correction. Do not delete or reschedule a reminder, complete
a follow-up task, or write a memory from a claimed or inferred account fact you
have not re-read from a tool this turn. Never assume two accounts or two feeds
are the same one; confirm the specific account first.
Daily ritual (the common path)
- Collect inputs up front: ask for any portal screenshots or statement
exports NOW, not mid-flow. Apple Card especially: its feed is balance-only,
so its statement balance only enters the system when the user supplies it.
Checking CSV pastes are safe to import since 2026-09-04 (MCP 0.3.35): the
importer skips rows the SimpleFIN feed already has (reported as
feed_duplicate), and a feed row that lands after a paste absorbs the paste copy. Feed row always wins. If a double count ever shows up anyway, rundedupe_pasted_transactions(dry run first). - Refresh live data:
run_background_syncwithoptions={"sync": true}(pulls SimpleFIN, then scans/reconciles/detects drift and surfaces due items in one audited run). For a quick manual refresh usesync_simplefin(incremental=true). - Read the digest:
get_daily_digest(working cash, 7/14/30/60d projection, upcoming obligations, drift, matches to confirm, guardrail status). This is the morning summary. Lead your answer with itsstatus_colorand working cash. - Close out matches:
list_reconciliation_review_itemsshows matches awaiting confirmation. For each one the user confirms, callconfirm_reconciliation_match(instance_id). Useunconfirm_reconciliation_matchto reverse. Never confirm without the user. - Triage discovered charges:
list_charge_onboarding_queue/get_next_charge_onboarding_candidate; record a decision withrecord_charge_onboarding_decision; preview then apply withpreview_charge_onboarding_applyandapply_charge_onboarding_candidate.
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.
- 2mo ago Changed · +8 lines 79d8a067cb5b
- 2mo ago First seen · 85 lines · 62 tokens per session scan A fe0addaf5c95
finance is a skill published in the GitHub repository albeorla/personal-finance-agent (0 stars, last pushed 1mo ago), licensed MIT. It adds 62 tokens to every session and 1,226 once invoked, about $0.0002 per session on Opus 5.5. 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.
finance compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| financealbeorla/personal-finance-agent | Skill | 0 | 1mo ago | MIT | A | 62 | Claude Code, Codex |
| genpark-financealphaparkinc/openclaw-genpark-finance | Skill | 9 | 9d ago | MIT | A | 17 | Claude Code, Codex |
| Agentic Commerce Protocol (ACP)alphaparkinc/openclaw-agentic-commerce-protocol | Skill | 11 | 15d ago | none | A | 52 | Claude Code, Codex |
| zenbill-ai-skillalphaparkinc/genpark-hub | Skill | 9 | 15d ago | none | A | 98 | Claude Code, Codex |
| zenpoint-ai-skillalphaparkinc/genpark-hub | Skill | 9 | 15d ago | none | A | 82 | Claude Code, Codex |
| zenpower-ai-skillalphaparkinc/genpark-hub | Skill | 9 | 15d ago | none | A | 60 | Claude Code, Codex |
| zentax-ai-skillalphaparkinc/genpark-hub | Skill | 9 | 15d ago | none | A | 80 | Claude Code, Codex |