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 web-previewgit 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/web-preview)<a href="https://agentmods.dev/skills/kirodotdev/kirocrew/web-preview"><img src="https://agentmods.dev/badge/skills/kirodotdev/kirocrew/web-preview/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/web-preview"><img src="https://agentmods.dev/badge/skills/kirodotdev/kirocrew/web-preview.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to high
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- high Prompt Injection · line 19 Hidden instructions were detected in comments or invisible text. These could contain malicious directives. Manual review is recommended.Fix: Audit all comments and invisible characters. Remove any instructions that direct the agent to perform unauthorized actions. Use plain, reviewable content.
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 | $0.00058 | $0.00951 |
| Opus 5.5 | $0.00023 | $0.00380 |
| Sonnet 5.5 | $0.00012 | $0.00190 |
| Haiku 4.5 | $0.00006 | $0.00095 |
Grade A, and why
web-preview 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 12d 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 — 78 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Web Preview marker
KiroCrew's chat right-side panel has a Browser tab (+ menu → Browser) that embeds a URL in a live iframe. When you start a local web server so the user can preview a site/app, tell the dashboard which URL to load by emitting a single hidden marker in your reply.
The marker
Emit exactly this, on its own line, once the server is confirmed listening:
<!-- kirocrew:preview url="http://127.0.0.1:PORT" -->
- It's an HTML comment, so the user never sees it in the dashboard chat. Only the dashboard has a Browser panel: in a Slack, Discord or other channel conversation the marker is not stripped and reaches the user as literal text, so do not emit it there — give the URL in prose instead. The dashboard opens the Browser tab and shows a Load preview card for that URL, contextual to the current session. Nothing is fetched until the user clicks Load, so tell them to click it rather than saying the preview is already showing.
- Use the actual URL the server binds to, including the real port
(
http://localhost:5173,http://127.0.0.1:8080, …). Only loopback is usable: a non-loopback marker is dropped silently — you get no error, the panel just stays empty — so emit only127.0.0.1,localhostor[::1]. A URL on the dashboard's own loopback port is refused too (it would frame the dashboard), so serve previews on a different port. - The panel may rewrite the host it loads:
[::1]becomes127.0.0.1, andlocalhostand127.0.0.1are swapped against each other for cookie isolation. Same server, different spelling — do not read the difference as a failure. - Emit it after you've confirmed the server is up (e.g. it returned HTTP 200), not before.
- If you restart on a different port, emit a new marker with the new URL — the panel re-points to the newest one. Re-emitting the same URL does nothing (it is applied once per session), so if the user closed the tab, point them back to it instead of re-emitting.
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.
- 12d ago Changed · +3 lines f91a3dae4597
- 1mo ago Changed · -24 tokens per session bf2bf86fcdcc
- 1mo ago Changed · +13 lines · +3 tokens per session 0e47e3c83b5a
- 1mo ago First seen · 62 lines · 79 tokens per session scan A c159d3a622cd
web-preview is a skill published in the GitHub repository kirodotdev/KiroCrew (4,496 stars, last pushed today), licensed Apache-2.0. It adds 58 tokens to every session and 951 once invoked, about $0.0002 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
browser-testing-with-screenshots
Use when testing web applications with visual verification - automates Chrome browser interactions, element selection, and screenshot capture for confirming UI functionality.
creating-actions
This skill should be used when the user asks to "create an action", "save this flow as an action", "make this replayable", "record a reusable action", "author a Maestro flow as an action", "add a login/setup action", or when a verified UI walk should be persisted under .rn-agent/actions/ so future sessions can replay…
node-inspect-debugger
Debug Node.js via --inspect + Chrome DevTools Protocol.
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.