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 simota/agent-skills --skill vectorgit clone --depth 1 https://github.com/simota/agent-skillsWrote 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/simota/agent-skills/vector)<a href="https://agentmods.dev/skills/simota/agent-skills/vector"><img src="https://agentmods.dev/badge/skills/simota/agent-skills/vector/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/simota/agent-skills/vector"><img src="https://agentmods.dev/badge/skills/simota/agent-skills/vector.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 2 findings, 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 7 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.
- medium Excessive Agency · line 139 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 | $0.00038 | $0.05169 |
| Opus 5.5 | $0.00015 | $0.02068 |
| Sonnet 5.5 | $0.00008 | $0.01034 |
| Haiku 4.5 | $0.00004 | $0.00517 |
Grade A, and why
vector scanned grade A with 1 finding 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
- `stealth`: Read `reference/stealth-mode.md` first. Apply human-like behavior (mouse movement curves, dwell time variance, scroll inertia), TLS fingerprint matching (curl-impersonate / playwright-stealth-equivalent), re How it starts
The opening of the file, as written. The whole thing — 302 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Vector
"The browser is a stage. Every click is a scene."
Browser automation specialist who completes tasks through precise web interactions. Navigate web apps, collect data, fill forms, capture evidence to accomplish ONE specific task completely. Operates on Playwright MCP accessibility snapshots (structured data, not pixel-based vision) by default, with vision mode fallback for shadow DOM and canvas elements. Enables deterministic, observable, and self-healing browser workflows.
Principles: Task completion is paramount · Observe and report accurately · Safe navigation always · Evidence backs findings · Human proxy automation · Accessibility-first selectors over brittle CSS chains
What ships with it
12 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.
- _common 10 B
- reference/_common 13 B
- reference/autorun-schema.md 719 B
- reference/computer-use-optimization.md 7.0 KB
- reference/crawl/compliance-architecture.md 11 KB
- reference/data-extraction.md 10 KB
- reference/execution-templates.md 6.1 KB
- reference/mobile-emulation.md 11 KB
- reference/parallel-sessions.md 11 KB
- reference/playwright-cdp.md 7.3 KB
- reference/stealth-mode.md 11 KB
- reference/video-recording.md 3.6 KB
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 3e4efd580855
- 14d ago Changed f0c6b5dab9d6
- 17d ago Changed 3110f9dc0182
- 1mo ago Changed 5ac2748574c0
- 1mo ago Changed · -1 lines 40faebfce224
- 1mo ago First seen · 303 lines · 38 tokens per session scan A 96ed7cfec008
vector is a skill published in the GitHub repository simota/agent-skills (95 stars, last pushed yesterday), licensed MIT. It adds 38 tokens to every session and 5,169 once invoked, about $0.0002 per session on Opus 5.5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-03.
Other skills, from other repositories
browser-doctor
Read-only health check on browser-control setup. Verifies browser binary, Playwright MCP Bridge extension presence, token file mode/contents, AIWG MCP registration, provider config injection, and optional workspace allow-list. Outputs pass/fail per check with remediation commands.
browser-automation-expert
Expert guide for autonomous web agents (Browser-Use, Stagehand v0.4+), hardcore anti-bot evasion (Playwright Stealth, WebGL masking), and Vision LLM visual QA / Panduan ahli agen web otonom, penghindaran deteksi bot, dan QA visual berbasis Vision LLM.
computer-use-os-agent-expert
Computer-using agents (CUA), desktop GUI automation, and VM sandbox / Agen CUA pengguna komputer, otomasi GUI desktop, dan sandbox VM.
web-scraper
Smart agentic web data extraction with multi-strategy scraping (Crawl4AI v4, Firecrawl), LLM extraction loops, anti-bot bypass, and structured export / Ekstraksi data web cerdas dan agentic dengan scraping multi-strategi (Crawl4AI v4, Firecrawl), ekstraksi LLM, bypass anti-bot, dan ekspor terstruktur.
local-slm-edge-ai-expert
Expert guide for Local Small Language Models (SLMs) and Edge AI execution — WebLLM, Transformers.js v3, ONNX Runtime Web, WebGPU, and zero-latency local embeddings / Panduan ahli SLM lokal dan AI edge di browser.
shogun-screenshot
A screenshot tool for getting images from a computer or web page and then cropping, resizing, or masking sensitive information. Playwright is a browser-automation tool used here to capture web pages.