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 remote-crew-microvmgit 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/remote-crew-microvm)<a href="https://agentmods.dev/skills/kirodotdev/kirocrew/remote-crew-microvm"><img src="https://agentmods.dev/badge/skills/kirodotdev/kirocrew/remote-crew-microvm/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/remote-crew-microvm"><img src="https://agentmods.dev/badge/skills/kirodotdev/kirocrew/remote-crew-microvm.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 | $0.00064 | $0.02955 |
| Opus 5.5 | $0.00026 | $0.01182 |
| Sonnet 5.5 | $0.00013 | $0.00591 |
| Haiku 4.5 | $0.00006 | $0.00296 |
Grade A, and why
remote-crew-microvm 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 yesterday.
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 — 244 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Running a remote crew on an AWS Lambda MicroVM
A crew on this lane runs inside a MicroVM that the platform terminates at a maximum lifetime it will not extend. That clock is the whole shape of the lane, and almost every surprise on it comes from the one fact below.
The crew's home lives on the VM's disk and goes away with the VM. Nothing on this lane copies it anywhere: no suspend, no archive, no reopen. When the VM goes, the conversations go. Say that plainly to anyone who asks what a crew here keeps, and say it BEFORE they put work into one.
Before anything else: the lane is offered only when its block is complete.
An incomplete microvm block publishes no provisioner row at all, which is the
deliberate choice: a row whose every launch is refused is worse than no row. So
the first thing to do is READ the provisioner list, not assume. If the microvm
row is absent, the block is incomplete and the missing field is the thing to find
-- most often activation_role_arn, which the AWS call that enrols the crew
refuses to run without, or bundle_dir, which a block that will build an image
also requires.
Completeness is judged on every request, so a correct edit shows up immediately with no restart.
Two numbers that decide everything.
| 1 hour | the lifetime a launch asks for when the operator sets none. Raisable through wall_seconds; it is this short because the home is not kept past it |
| 28,800 seconds | the platform's own maximum, and the ceiling on wall_seconds. Not adjustable and nothing extends it |
First: is the lane even configured?
Do this before anything else, and do not infer it from the presence of an AWS profile. The lane is offered only when its configuration is complete; an incomplete block leaves it unregistered rather than registered and refusing.
GET /api/cloud/provisioners
Look for a row with "id": "microvm". Three outcomes, and they mean different
things:
- the row is there — the lane is offered and configured. Note its
confirm_before_launchstring exactly as written; you need it verbatim to launch. - no
microvmrow, butaws_ec2is there — this is the expected answer today. The lane is withheld until its guest half lands, and it is also what an incomplete block looks like. Do not try to tell the two apart by guessing: report that the lane is not available yet, and only walk through the configuration below if the operator asks for it knowing it will not launch. - the request fails — this is not a lane problem. Report it as it is.
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.
- yesterday First seen · 244 lines · 64 tokens per session scan A 9ab54d88b768
remote-crew-microvm is a skill published in the GitHub repository kirodotdev/KiroCrew (4,449 stars, last pushed today), licensed Apache-2.0. It adds 64 tokens to every session and 2,955 once invoked, about $0.0003 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 2026-10-15.
Other skills, from other repositories
vigilante-issue-implementation-on-terraform
Implement a GitHub issue end-to-end when Vigilante dispatches work for a Terraform repository with fmt, validate, and secret-safe infrastructure guidance.
tcapi
A helper for managing Tencent Cloud resources through Tencent Cloud's command-line API tool. Tencent Cloud is a cloud-services provider offering products such as virtual servers, storage, networks, and containers.
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…
sector-rotation
Identify which market sectors to overweight or underweight based on current macro conditions and sector performance data.
trend-analysis
Analyze price and volume trends for one or more stocks to determine momentum direction and key technical levels.
deploying-to-staging-environment
Use when deploying changes to staging across relay, relay-dashboard, and relay-cloud repos - coordinates multi-repo branch syncing using git worktrees, automatically triggers staging deployments via GitHub Actions.