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 browser-authgit 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/browser-auth)<a href="https://agentmods.dev/skills/kirodotdev/kirocrew/browser-auth"><img src="https://agentmods.dev/badge/skills/kirodotdev/kirocrew/browser-auth/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/browser-auth"><img src="https://agentmods.dev/badge/skills/kirodotdev/kirocrew/browser-auth.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to medium
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 →
- medium Excessive Agency · line 118 Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
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 | $0.00047 | $0.03199 |
| Opus 5.5 | $0.00019 | $0.01280 |
| Sonnet 5.5 | $0.00009 | $0.00640 |
| Haiku 4.5 | $0.00005 | $0.00320 |
Grade A, and why
browser-auth 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 4d 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 — 268 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Browser Auth: browsing what needs a login
For public pages, use the browser MCP tool in the dashboard's Browser panel.
This skill handles login walls through playwright-cli: attach and saved state
have no native-tool equivalent. Loopback, private and link-local targets also
need the CLI's approval path. A policy denial has no fallback.
There is no bundled SSO. Use the user's existing browser context or saved state; never navigate a borrowed tab away from the user's work.
Pick a path
| Path | When | Setup cost |
|---|---|---|
Attach (attach --extension) |
The user is at their machine with the site already logged in, in a Chromium-family browser | None. Their live sessions are the session |
Saved state (state-save / state-load) |
You will come back to this site across sessions or restarts, or the host has no interactive browser to attach | One human login, once |
Individual cookies (cookie-*) |
You hold a specific cookie value, or you are repairing one entry rather than a whole context | Per-cookie |
Attach is the strongest of the three, and worth naming as such: it drives the
user's own running browser with every session they are logged into, not a scoped
copy. When the user has Chrome on this machine, attach is the default: asking for
"my Chrome", or for a site they are signed in to (their mail, their files), means
attach. Saved state fits a site you return to often. Fall back to the headless
playwright-cli open only when no Chrome is installed, the user asks for
headless, or the gateway runs on another machine. The browser tool's fallback
text tells you which of these this host is.
Attach
Attach mode has one prerequisite the install flow cannot satisfy: the Playwright extension must be installed in the browser being attached to. A browser extension is granted inside the browser by the person using it, so nobody but the user can add it:
https://chromewebstore.google.com/detail/playwright-extension/mmlmfjhmonkocbjadbfplnigmagldckm
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.
- 4d ago Changed · +20 lines 904b2f6e82cf
- 9d ago Changed · +4 lines 796467ed4c62
- 15d ago Changed · +6 lines 6bc0c898ae5f
- 23d ago Changed · +76 lines 957fbab0245e
- 1mo ago Changed · -11 lines bbc09eb7d65f
- 1mo ago Changed · +1 lines 4d1b93749ee1
- 1mo ago Changed · +22 lines c31313bd4b99
- 1mo ago First seen · 150 lines · 47 tokens per session scan A b3c30025d064
browser-auth is a skill published in the GitHub repository kirodotdev/KiroCrew (4,464 stars, last pushed today), licensed Apache-2.0. It adds 47 tokens to every session and 3,199 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.