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-recordinggit 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-recording)<a href="https://agentmods.dev/skills/kirodotdev/kirocrew/browser-recording"><img src="https://agentmods.dev/badge/skills/kirodotdev/kirocrew/browser-recording/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-recording"><img src="https://agentmods.dev/badge/skills/kirodotdev/kirocrew/browser-recording.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 MCP Rug Pull · line 169 npx commands without a version suffix (e.g. @1.0.0) create a rug-pull risk if the upstream server is compromised and publishes a malicious update.Fix: Pin the version: npx @scope/[email protected]
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 | $0.02202 |
| Opus 5.5 | $0.00026 | $0.00881 |
| Sonnet 5.5 | $0.00013 | $0.00440 |
| Haiku 4.5 | $0.00006 | $0.00220 |
Grade A, and why
browser-recording 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 26d 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 — 183 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Browser Recording — video/GIF evidence for UI flows
A still frame cannot prove motion or sequence correctness. When a UI change
involves animation, transitions, or a multi-step flow (wizard steps, a
modal opening, drag interactions), record it. This skill is the how for the
evidence rule in the frontend-design-workflow skill's Phase 3.
Recording evidence for GUI PRs (provenance)
frontend-design-workflow Phase 3 owns which evidence a GUI change needs: a
still screenshot for a static layout or styling change, a recording for
motion, a transition, or a multi-step flow a still frame cannot prove. This
section does not widen that rule — do not record a change a screenshot already
covers — it adds the one thing Phase 3 leaves open: how to make a recording
reproducible and honest about how it was produced.
When a change does need a recording, it must come from the real server and model flow: the actual dev/preview server running the branch, driven through a real interaction, never a fixture, a mock, or a hand-faked event stream. A recording of a stubbed surface proves nothing about the code under review.
Embed the recording with a provenance line beside it disclosing how it was produced:
recorded from <full-SHA> · <tree/origin> · mode: <flags> · real server + model, no fixtures
State the commit SHA, the tree or origin it came from, any mode flags that change behaviour, and an explicit real-vs-fixture disclosure. The line is written by the same agent that made the recording, so it discloses provenance rather than proving it — the real check is the SHA-pinned embed a reviewer can open and a re-record from that SHA. A recording with no provenance line leaves how it was produced unstated.
What it does
scripts/record_browser.py drives a headless Chromium through the target
project's own Playwright install, records the session as webm, and — when
ffmpeg is available — converts it to mp4 and a palette-optimized GIF.
python3 <skill-dir>/scripts/record_browser.py \
--url http://127.0.0.1:5173/settings \
--scenario $KIROCREW_SCRATCH/demo-scenario.mjs \
--project /path/to/frontend \
--size 1280x800 --name settings-flow --out $KIROCREW_SCRATCH/rec
What ships with it
2 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 26d ago Changed · -21 tokens per session ad475e788af3
- 1mo ago Changed · -6 lines 46a747968d4f
- 1mo ago Changed · +7 lines 5d835ed33867
- 1mo ago First seen · 182 lines · 85 tokens per session scan A 1fe4c270b2f3
browser-recording 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 2,202 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 2026-08-30.
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.