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 tag-my-rd-spendgit 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/tag-my-rd-spend)<a href="https://agentmods.dev/skills/akiotanaka847/qaio-desktop/tag-my-rd-spend"><img src="https://agentmods.dev/badge/skills/akiotanaka847/qaio-desktop/tag-my-rd-spend/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/tag-my-rd-spend"><img src="https://agentmods.dev/badge/skills/akiotanaka847/qaio-desktop/tag-my-rd-spend.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 | $0.00111 | $0.02021 |
| Opus 5 | $0.00056 | $0.01010 |
| Sonnet 5 | $0.00022 | $0.00404 |
| Haiku 4.5 | $0.00011 | $0.00202 |
Grade A, and why
tag-my-rd-spend 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.
Tag My R&D Spend
Section 174 and R&D-credit support for the tax year. I bucket qualified spend into the four IRS categories — wages, supplies, cloud / computer leasing, contract research at 65% — and allocate by project where you have one. Exclusions (routine analytics, post-release work, funded research, General & Admin of R&D) are listed with citations so your tax preparer can audit each call. Support only — I never file Form 6765.
When to use
- "tag R&D spend for the credit" / "Section 174 breakout" / "classify R&D expenses for {year}".
- Called by
hand-off-to-my-tax-preparerwhendomains.tax.rdCreditEligible == "yes". - Before year-end handoff, surface missing project tags or uncertain R&D-vs-General & Admin calls.
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.
- Payroll provider (Gusto, Rippling, Justworks, Deel, ADP) — preferred source for wages by employee and role, which drives the qualified-wages bucket. Required if you have employees.
- QuickBooks Online or Xero (accounting) — optional supplement for vendor payments and contractor spend if I can't see them in run history.
If no payroll connection exists and you do have employees I stop and ask you to connect your payroll tool, or drop a payroll summary CSV.
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.
- The tax year you're claiming — Required. Why: defines the date range I aggregate spend across. If missing I ask: "Which tax year are we classifying R&D for?"
- R&D-credit eligibility — Required. Why: confirms whether to run a federal-credit-style breakout or just a Section 174 amortization view. If missing I ask: "Is the company planning to claim the federal R&D credit this year, or is this just for Section 174 amortization?"
- Each employee's role and the share of their time spent on qualified R&D — Required. Why: drives the qualified-wages bucket; engineers default to 100%, product / design less. If missing I ask: "What does each person on the team do, and roughly what share of their time is hands-on engineering or research? If you'd rather, I'll start with defaults (engineering 100%, product 50%, design 25%, others 0%) and you correct anything off."
- Your project list — Optional. Why: lets me allocate qualified spend by project, which the credit form wants. If you don't have it I roll everything into one "Unallocated R&D" bucket.
- Your cloud-hosting R&D share — Optional. Why: pre-revenue companies usually treat 100% of cloud as R&D; revenue companies split production vs. R&D. If missing I ask: "How much of your AWS / GCP / Vercel spend is for development and research vs. running the live product? If you don't have it I default to 100% R&D pre-revenue."
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 · 111 tokens per session scan A d448df28c722
tag-my-rd-spend is a skill published in the GitHub repository akiotanaka847/qaio-desktop (2 stars, last pushed 8d ago), licensed MIT. It adds 111 tokens to every session and 2,021 once invoked, about $0.0006 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
assess
A Japanese tax-filing assessment guide that asks about your income, family, and business situation to identify which tax returns you may need.
setup
A setup wizard for shinkoku, a Japanese tax-filing tool. It creates or updates the configuration file and initializes the tool’s database.
furusato
A Japanese hometown-tax donation manager for furusato nozei, a system where donations to municipalities can qualify for an income-tax or local-tax deduction. It reads donation receipts, stores donation records, and calculates deduction limits.
tax-advisor
A Japanese tax-advice skill based on 2025 tax rules. It answers tax-filing and tax-saving questions using documents in a reference folder rather than general guesses.
e-bookkeeping-compliance
A compliance checker for Japan's rules on keeping high-quality electronic accounting books. It checks whether accounting records and related documentation meet specified requirements for electronic storage.
incorporation
A guide for moving from working as an individual business owner to operating through a company in Japan. It covers company types, setup steps, officer pay, taxes, and social insurance.