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 akiotanaka847/qaio-desktop --skill prepare-my-investor-packgit clone --depth 1 https://github.com/akiotanaka847/qaio-desktopWrote 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/akiotanaka847/qaio-desktop/prepare-my-investor-pack)<a href="https://agentmods.dev/skills/akiotanaka847/qaio-desktop/prepare-my-investor-pack"><img src="https://agentmods.dev/badge/skills/akiotanaka847/qaio-desktop/prepare-my-investor-pack/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/akiotanaka847/qaio-desktop/prepare-my-investor-pack"><img src="https://agentmods.dev/badge/skills/akiotanaka847/qaio-desktop/prepare-my-investor-pack.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 | $0.00138 | $0.01989 |
| Opus 5 | $0.00069 | $0.00994 |
| Sonnet 5 | $0.00028 | $0.00398 |
| Haiku 4.5 | $0.00014 | $0.00199 |
Grade A, and why
prepare-my-investor-pack 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 — 92 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Prepare My Investor Pack
Board pack from your latest close. Exec summary up top — cash, burn, runway, monthly revenue / annual revenue, gross margin, headcount, top-3 variance drivers — then full statements, SaaS KPIs, cohort retention, and runway sensitivity below. Optional Google Docs mirror so your board can comment in place. Drafts only — I never send.
When to use
- "draft the board financials pack" / "prep investor update financials" / "build the Q{N} investor pack".
mode=saas-metrics- "refresh monthly revenue / annual revenue" / "what's our NRR this month" - skip full pack, write metrics-only file.- After
close-my-monthfinishes quarter-end month, or any time user wants fresh pack between closes.
Connections I need
I run external work through Composio. Before this skill runs I check that the categories below are linked. Missing → I name the category, ask you to connect it from the Integrations tab, stop.
- Google Docs (docs) — optional, lets me mirror the pack to a Google Doc your board can comment on. If not connected I keep it as a markdown file.
This skill assembles entirely from your existing closed months, runway reports, and revenue recognition schedules. No connection blocks the run.
Information I need
I read your bookkeeping context first. For every required field that's missing I ask ONE plain-language question (best modality: connected app > file drop > URL > paste) and wait.
- A finished close for the period — Required. Why: the pack copies P&L, balance sheet, and cash flow straight from the close. If missing I ask: "Have we closed the books for the latest month yet? If not, let's run the close first."
- A current burn and runway report — Required. Why: the pack includes cash, burn, and runway sensitivity from the runway report. If missing I ask: "Do you want me to refresh the runway report first? It only takes a minute."
- Your revenue model — Required. Why: SaaS pack includes monthly revenue / annual revenue / NRR / cohort retention; non-SaaS skips those sections. If missing I ask: "How does the business make money, recurring subscriptions, usage-based, services, or a mix?"
- The KPIs your investors care about — Optional. Why: lets me anchor the exec summary to numbers your board already tracks. If you don't have it I default to cash, burn, runway, monthly revenue / annual revenue, and gross margin.
- Contract data spanning at least 13 months — Optional. Why: needed for trailing-twelve-month NRR and cohort retention. If you don't have it I skip those sections and note that they'll show up once you have enough history.
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 · 92 lines · 138 tokens per session scan A 32bd83e55490
prepare-my-investor-pack is a skill published in the GitHub repository akiotanaka847/qaio-desktop (2 stars, last pushed 8d ago), licensed MIT. It adds 138 tokens to every session and 1,989 once invoked, about $0.0007 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 skills, from other repositories
reading-receipt
An image-reading workflow for extracting structured information from receipts, invoices, and hometown-tax donation certificates. It can first extract text from PDFs and otherwise read their images.
reading-deduction-cert
An image-reading workflow for extracting structured information from Japanese insurance and social-insurance deduction certificates. It can read image files and PDFs, including scanned PDFs.
jangbu-import
A data-import workflow for turning bank files, card records, spreadsheets, receipts, tax invoices, and statement PDFs into a standard set of 13 transaction fields. OCR, or optical character recognition, is used to read information from document images and PDFs.
reading-payment-statement
An image-reading workflow for extracting structured information from Japanese payment statements, which report payments such as fees, compensation, contracts, or prizes.
reading-invoice
A guide for reading invoice images or PDFs and returning structured details such as the supplier, date, and amount.
csv-importer
A tool for importing transaction CSV files—spreadsheet files separated by commas—from Japanese accounting software and classifying every imported row.