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 track-my-promisesgit 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/track-my-promises)<a href="https://agentmods.dev/skills/akiotanaka847/qaio-desktop/track-my-promises"><img src="https://agentmods.dev/badge/skills/akiotanaka847/qaio-desktop/track-my-promises/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/track-my-promises"><img src="https://agentmods.dev/badge/skills/akiotanaka847/qaio-desktop/track-my-promises.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 | $0.00068 | $0.00776 |
| Opus 5 | $0.00034 | $0.00388 |
| Sonnet 5 | $0.00014 | $0.00155 |
| Haiku 4.5 | $0.00007 | $0.00078 |
Grade A, and why
track-my-promises 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 — 54 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Track My Promises
When to use
- Say "send it" / "approved" on
draft.mdwith time-bound language. - Write own reply in chat with date, day, or timeframe.
- Review existing thread, mention "oh right, I told them I'd…".
Any phrase like: "I'll X by Y", "next week", "tomorrow", "by Friday", "end of day", "within the hour" triggers this.
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.
- Inbox (Gmail / Outlook) - optional, only used to pull the source thread when the promise lives in an email I haven't ingested yet.
This skill mostly works against your local conversation index, so no connection is strictly required.
Information I need
I read your support 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 promise text - Required. Why I need it: I track what was actually said, not what I thought I heard. If missing I ask: "What did you commit to, and to which customer or thread?"
- The due date or timeframe - Required. Why I need it: vague deadlines slip silently. If missing I ask: "When did you tell them you'd get back - a specific day, end of week, or did you leave it open?"
- Conversation or customer link - Optional. Why I need it: lets me file the followup against the right thread. If you don't have it I keep going with TBD and ask you to point me at the thread later.
Steps
- Extract promise text verbatim from message or draft (keep original phrasing - may want see what they said).
- Parse due date.
- Explicit date ("Friday", "March 3") → next occurrence in local timezone → ISO-8601 UTC.
- Relative ("tomorrow", "next week") → apply relative to now.
- Vague ("soon", "asap", no date) → default
now + 48h, note ambiguity in promise text.
- Link to conversation. Pull
conversationIdandcustomerSlugfrom thread. - Append atomically to
followups.json:{ "id": "<uuid>", "conversationId": "...", "customerSlug": "...", "promise": "...", "dueAt": "...", "status": "open", "createdAt": "...", "updatedAt": "..." } - Mirror promise as dated line in
conversations/{id}/notes.md. - If existing open followup on same conversation contradicted by new promise (e.g. date pushed), mark old one
status: "cancelled", reference new id.
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 · 54 lines · 68 tokens per session scan A 9e386b50fbbb
track-my-promises is a skill published in the GitHub repository akiotanaka847/qaio-desktop (2 stars, last pushed 8d ago), licensed MIT. It adds 68 tokens to every session and 776 once invoked, about $0.0003 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
customer-support-expert
Build comprehensive customer support systems including ticketing, knowledge management, SLA tracking, and customer satisfaction analytics. Use when the user mentions helpdesk or service desk, ticketing, SLA targets, knowledge bases, escalation workflows, CSAT/NPS, or customer success operations.
Zendesk Automation
Automate customer support workflows with Zendesk ticket management, routing, and analytics.
auto-tag
Automatically analyze and tag untagged Gorgias tickets based on content.
bug-report
Extract a structured bug report from a support ticket and create a Linear issue.
escalate
Escalate a support ticket to a Linear issue and notify the team on Slack.
merge-tickets
Find and flag duplicate or related Gorgias tickets that should be merged.