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 score-an-inboundgit 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/score-an-inbound)<a href="https://agentmods.dev/skills/akiotanaka847/qaio-desktop/score-an-inbound"><img src="https://agentmods.dev/badge/skills/akiotanaka847/qaio-desktop/score-an-inbound/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/score-an-inbound"><img src="https://agentmods.dev/badge/skills/akiotanaka847/qaio-desktop/score-an-inbound.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 | $0.00076 | $0.01286 |
| Opus 5 | $0.00038 | $0.00643 |
| Sonnet 5 | $0.00015 | $0.00257 |
| Haiku 4.5 | $0.00008 | $0.00129 |
Grade A, and why
score-an-inbound 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 7d 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.
Score An Inbound
Generic approval-rubric runner for any inbound needing founder decision. Vendor-specific supplier triage → vet-a-vendor skill (procurement criteria, different folder).
When to use
- "review this vendor application against our criteria" (supplier-specific →
vet-a-vendor). - "score these advisor candidates".
- "is this partnership a fit".
- "should I accept this press request".
- "run the approval flow on this".
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.
- Web research (Exa, Perplexity, Firecrawl) - Required. Pulls public signals on the submitter to verify claims and surface red flags.
- Inbox (Gmail, Outlook) - Optional. Lets me check prior correspondence with the submitter so the recommendation reflects history.
If no web research provider is connected I stop and ask you to connect a research provider 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.
- The submission itself - Required. Why I need it: I score what's in front of me. If missing I ask: "Drop the submission - pitch, application, request - or paste the email thread."
- Approval rubric - Required. Why I need it: ad-hoc scoring isn't reproducible. If missing I ask: "What criteria should I use? Paste them, or say 'default' and I'll save a starter rubric for this kind of inbound that you can edit later."
- Active priorities - Required. Why I need it: the fit-to-priorities score keys off these. If missing I ask: "What are the 2 to 3 things the company is pushing on this quarter?"
- Hard nos - Optional. Why I need it: lets me decline anything that violates them on sight. If you don't have it I keep going with TBD using workspace defaults.
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.
- 7d ago First seen · 92 lines · 76 tokens per session scan A 085ea43dd380
score-an-inbound is a skill published in the GitHub repository akiotanaka847/qaio-desktop (2 stars, last pushed 8d ago), licensed MIT. It adds 76 tokens to every session and 1,286 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 2026-09-05.
Other skills, from other repositories
after-action-report
Run a structured after-action review (postmortem, retrospective) on a launch, incident, or completed project to capture timeline, root cause analysis, contributing factors, and actionable lessons. Use this skill whenever the user wants to run a postmortem, retrospective, AAR, or after-action review on any past event.…
env-setup-assistant
Expert guide for setting up development environments including IDE configuration, tooling, dependencies, and developer onboarding. Use when bootstrapping new projects or standardizing team environments.
meeting-processor
Process meeting transcripts and Notion meeting notes into structured organizational records, action items, and memory updates.
mailroom-acknowledgement-sweep
Route unrouted mail and chase what nobody acknowledged.
asset-inventory-reconciliation
Reconcile recorded against observed assets.
committed-schedule-coordination
Keep committed schedule and reality in step.