Kiro Crew is a persistent development workspace where agents continue multi-step software work across sessions, schedules, and connected interfaces. Developers use it locally or remotely through a desktop app, web dashboard, CLI, Slack, or Discord, with unattended tasks and recurring jobs. The catalogue contains skills and instructions for working with this workspace.
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 kirodotdev/KiroCrew --skill mochi-remindgit clone --depth 1 https://github.com/kirodotdev/KiroCrewWrote 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/kirodotdev/kirocrew/mochi-remind)<a href="https://agentmods.dev/skills/kirodotdev/kirocrew/mochi-remind"><img src="https://agentmods.dev/badge/skills/kirodotdev/kirocrew/mochi-remind/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/kirodotdev/kirocrew/mochi-remind"><img src="https://agentmods.dev/badge/skills/kirodotdev/kirocrew/mochi-remind.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00020 | $0.01026 |
| Opus 5.5 | $0.00008 | $0.00410 |
| Sonnet 5.5 | $0.00004 | $0.00205 |
| Haiku 4.5 | $0.00002 | $0.00103 |
Grade A, and why
mochi-remind 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 15d 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 — 98 lines — stays where its author put it; the contents beside it link to each section on GitHub.
@mochi-remind — Handle Due Reminders
Handle reminders that have reached their trigger time.
Steps
1. Verify Meetings (if applicable)
For items with kind=meeting, only if the user has connected a calendar tool. Do not assume a
server or tool name — look at the tools you actually have and find one that lists events in a
time range.
- List events in a window around the meeting's
triggerAt(±2 hours) to find it. - Match by subject/title (fuzzy — the label may be abbreviated).
- Check the event status:
- Cancelled: Tell the user the meeting was cancelled. Mark the item
done. - Rescheduled (calendar start differs from the item's
notes.meetingStartby >1 min; if the item has nomeetingStart, treat it as on schedule): Tell the user the new time. Keep the user's lead time (meetingStartminustriggerAt) and callupdate_watchlistwithtriggerAt= new start minus that lead andnotes.meetingStart= new start. Do NOT mark done. - Still on schedule: Proceed to notify normally (step 2).
- Cancelled: Tell the user the meeting was cancelled. Mark the item
- If the lookup fails or returns no match, proceed with the reminder anyway — don't block notification on a calendar lookup failure.
Skip this step for kind=reminder items or when you have no calendar tool.
2. Notify the User
Before notifying, check activity log for duplicates:
Call read_mochi_file({ which: "activity" }) and scan the last 10 entries.
If you find a notification entry within the last 15 minutes that already communicated
the same reminder (same label/subject), skip the notification — it was already delivered
by a concurrent agent. Just mark the item done and finish. A "got moved to …" message
from a reschedule is NOT the reminder itself and does not count as a duplicate.
Right after 00:00 UTC the log rotates, so also check "activity-yesterday".
Use perform_pet_action({ action: "notify", pushToChat: true, source: "reminder", priority: "critical", summary: "<≤100 chars>" })
with natural language — summary is required (a notify without it is dropped), and
critical is what lets a due reminder through quiet mode and an in-flight chat turn.
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.
- 15d ago Changed · +5 lines f4cf5dff0804
- 1mo ago First seen · 93 lines · 20 tokens per session scan A 3490d88c8eea
mochi-remind is a skill published in the GitHub repository kirodotdev/KiroCrew (4,545 stars, last pushed today), licensed Apache-2.0. It adds 20 tokens to every session and 1,026 once invoked, about $0.0001 per session on Opus 5.5. 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 2026-08-30.
Other skills, from other repositories
pto-planning
Check an employee's PTO balance and policy, then plan or submit a time-off request.
bootstrap
Onboarding conversation to generate a user profile.
workflow-helper
Guidance for creating, managing and executing workflow automations that chain multiple tools and agents together. Use when the user asks about building, listing, running or composing workflows and automated task pipelines.
ecosystem-defrag
Inventory an existing Windows agent/developer-tool setup, identify concrete capability overlap, and plan or execute a reversible consolidation when the setup is fragmented.
cost-efficiency-analyzer
Analyzes cost structure, cost efficiency, and expense management from P&L data. Use when the user asks about costs, expenses, COGS, operating expenses, cost ratios, cost control, spending efficiency, margin compression from cost side, or wants to understand where money is going. Also use for "are we spending too…
trend-analysis
Analyze price and volume trends for one or more stocks to determine momentum direction and key technical levels.