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 agentmods add skills/kirodotdev/kirocrew/mochi-tipsnpx skills add kirodotdev/KiroCrew --skill mochi-tipsgit 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-tips)<a href="https://agentmods.dev/skills/kirodotdev/kirocrew/mochi-tips"><img src="https://agentmods.dev/badge/skills/kirodotdev/kirocrew/mochi-tips.svg" alt="Measured on agentmods" 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 | $0.00025 | $0.00998 |
| Opus 5 | $0.00013 | $0.00499 |
| Sonnet 5 | $0.00005 | $0.00200 |
| Haiku 4.5 | $0.00003 | $0.00100 |
Grade A, and why
mochi-tips 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 5d 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 — 50 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Mochi Feature Tips
These tips are shown to new users during the first week of companionship. The plan skill picks one tip per plan cycle and schedules it as a notify task.
Check planner_notes.skipped_tips for tips already shown — pick one that hasn't been used yet. After scheduling a tip, add its id to skipped_tips so it won't repeat.
New to Mochi — advertise the shortcuts first. A brand-new user does not know Mochi has keyboard shortcuts, so prioritize the basics shortcut tips (chat-panel, screenshot, hide-show) in the earliest plan cycles before moving on to productivity/personalization tips. The values below are the defaults on macOS; on Windows/Linux the modifier is Alt+Shift instead of Cmd+Shift, and the user can rebind both the chat-panel and hide-all shortcuts in Settings → Shortcuts — so if the user has mentioned a custom binding, advertise theirs rather than the default string.
Tips
basics
- drag-me: "Try dragging me to a different spot! I'll walk from wherever you put me next time. 🐾"
- chat-panel: "Press Cmd+Shift+M to toggle the chat panel — or just click me!"
- screenshot: "Press Cmd+Shift+X to take a screenshot — I can see what's on your screen!"
- hide-show: "Press Cmd+Shift+H to hide or show me and all my windows."
productivity
- watch-url: "I can keep an eye on any page for you — just say 'watch ' and I'll tell you when it changes! 👀"
- watch-price: "Say 'watch this flight and tell me if it gets cheaper' — I'll check now and then and only speak up when the price moves."
- watch-restock: "Sold out? Say 'tell me when this is back in stock' and I'll keep refreshing so you don't have to."
- remind-me: "Say 'remind me to take the trash out at 8' — I'll nudge you at the right time with a friendly bubble!"
- drink-water: "Say 'remind me to drink water every hour' — I'll be gently annoying about it. 💧"
- stretch-break: "Been sitting a while? Say 'get me up every 45 minutes' and I'll make you stand and stretch."
- watch-cancel: "Changed your mind? Just say 'stop watching that' and I'll drop it. You can always ask again later."
- watch-status: "Ask 'what are you watching?' and I'll give you a quick summary of everything I'm keeping an eye on."
- spawn-task: "For anything slow, I can go work on it in the background — just describe what you need!"
- recurring: "I can do things on a schedule — try 'every Sunday evening, remind me to plan the week'."
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.
- 5d ago First seen · 50 lines · 25 tokens per session scan A 08278d49dd10
mochi-tips is a skill published in the GitHub repository kirodotdev/KiroCrew (3,532 stars, last pushed 3d ago), licensed Apache-2.0. It adds 25 tokens to every session and 998 once invoked, about $0.0001 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 2026-08-30.
Other skills, from other repositories
kodama-verification
Define measurable success criteria and collect targeted test, build, lint, type-check, or smoke-test evidence before claiming work is complete.
kodama-behavior
Classify requests, assess unfamiliar codebases, delegate work safely, and recover from failed attempts. Use for multi-step, ambiguous, or parallelizable work.
kodama-constraints
Enforce non-negotiable safety, scope, security, and quality constraints for implementation and review work.
project-release-check
Validate this example project's release readiness. Use before publishing a release candidate.
aatmf-t10-confidentiality-breach
AATMF T10 — Integrity & Confidentiality Breach. System prompt extraction, training-data extraction, model-weight leakage, private-key recovery.
sidewinder-rattlesnake
Adversary-emulation profile for SideWinder (G0121 / Rattlesnake / T-APT-04 / Razor Tiger), India's suspected state-sponsored cyber-espionage actor.