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 audit-my-saas-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/audit-my-saas-spend)<a href="https://agentmods.dev/skills/akiotanaka847/qaio-desktop/audit-my-saas-spend"><img src="https://agentmods.dev/badge/skills/akiotanaka847/qaio-desktop/audit-my-saas-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/audit-my-saas-spend"><img src="https://agentmods.dev/badge/skills/akiotanaka847/qaio-desktop/audit-my-saas-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 | $0.00071 | $0.01362 |
| Opus 5 | $0.00036 | $0.00681 |
| Sonnet 5 | $0.00014 | $0.00272 |
| Haiku 4.5 | $0.00007 | $0.00136 |
Grade A, and why
audit-my-saas-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 — 91 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Audit My SaaS Spend
Surprise-reveal skill. Most solo founders not know annualized SaaS spend. Surface in one file.
When to use
- "audit my SaaS spend".
- "what am I paying for".
- "find the subscriptions I forgot about".
- "how much are we spending on tools".
Connections I need
I run external work through Composio. Before this skill runs I check the categories below are linked. Missing → I name the category, ask you to connect it from the Integrations tab, stop.
- Billing (Stripe) - Required. Pulls recurring charges so I can see the real subscription list, not just what you remember.
- Inbox (Gmail, Outlook) - Required. Catches receipts and renewal emails for tools that aren't on your card.
- Files (Google Drive) - Optional. Helps me find executed contracts so I can match them to charges.
If neither billing nor inbox is connected I stop and ask you to connect your billing first.
Information I need
I read your operations 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.
- Vendor posture - Required. Why I need it: tells me how aggressive to be flagging duplicates and cancel candidates. If missing I ask: "How do you usually think about vendors - keep things lean and cancel fast, or stay with what works?"
- Known vendor list - Optional. Why I need it: anything I find outside this list is a forgotten subscription. If you don't have it I keep going with TBD and treat everything I find as new.
- Prior audit - Optional. Why I need it: lets me flag price drift since last time. If you don't have it I skip the price-drift section.
Steps
-
Read
context/operations-context.md- stage + vendor posture anchor severity thresholds. If missing: stop, ask forset-up-my-ops-info. -
Read
config/procurement.json-knownVendors= known list; anything NOT on list found during audit = potential forgotten-subscription.
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 · 91 lines · 71 tokens per session scan A 7f6682a7c1a1
audit-my-saas-spend is a skill published in the GitHub repository akiotanaka847/qaio-desktop (2 stars, last pushed 8d ago), licensed MIT. It adds 71 tokens to every session and 1,362 once invoked, about $0.0004 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
splits
Use Splits with Bankr for onchain treasury operations: secure assets, process revenue, manage operating subaccounts, pay expenses, govern contracts, and maintain clean accounting books.
cross-cutting-finance-position-read
Report the recorded money position.
pipa-budget-review
Use only when pipa-budget-review is explicitly invoked or pipa-get-paid delegates to it. Do not trigger from generic language.
pipa-budget-setup
Use only when pipa-budget-setup is explicitly invoked or pipa-get-paid delegates to it. Do not trigger from generic language.
pipa-get-paid
Use when the user wants Pipa to help a service business get paid: invoices, payments, billable time, budgets, margin, change-control money impact, and payment follow-through.
quote-builder
Build a line-item client quote with payment terms and a revision policy, run an internal margin check, and warn when gross margin drops below 40 percent before you send it.