Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/snyk/saw-mcpnpx agentmods add skills/snyk/saw-mcp/saw-web-target-configurationWrote 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/snyk/saw-mcp/saw-web-target-configuration)<a href="https://agentmods.dev/skills/snyk/saw-mcp/saw-web-target-configuration"><img src="https://agentmods.dev/badge/skills/snyk/saw-mcp/saw-web-target-configuration/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/snyk/saw-mcp/saw-web-target-configuration"><img src="https://agentmods.dev/badge/skills/snyk/saw-mcp/saw-web-target-configuration.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 2 findings, 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 18 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]
- medium MCP Rug Pull · line 34 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 | $0.00077 | $0.03704 |
| Opus 5 | $0.00039 | $0.01852 |
| Sonnet 5 | $0.00015 | $0.00741 |
| Haiku 4.5 | $0.00008 | $0.00370 |
Grade A, and why
saw-web-target-configuration 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 11d 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 — 261 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Web Target Configuration Skill (Snyk API & Web)
Configure web application targets for Snyk API & Web security scanning with authentication support. For API targets, use the saw-api-target-configuration skill instead.
Browser Automation — Detect Before Recording
Login sequences require a real browser. Detect availability in this order:
1. playwright-cli (preferred for coding agents with Shell access)
playwright-cli --version
# or: npx @playwright/cli --version
If missing, install (no repo clone required):
npm install -g @playwright/cli@latest
playwright-cli install-browser chromium
Or, when a clone of this repo is available:
./scripts/setup-playwright.sh
Use npx @playwright/cli instead of playwright-cli when the global binary is not on PATH.
2. Playwright MCP (fallback for MCP-only clients)
Check whether Playwright MCP tools are available (e.g. browser_navigate, browser_snapshot, browser_evaluate, browser_network_requests).
If missing, tell the user to install Playwright MCP:
{
"mcpServers": {
"playwright": {
"command": "npx",
"args": ["-y", "@playwright/mcp@latest"]
}
}
}
Or install Playwright from the Cursor Marketplace.
3. Neither available
If neither path works and the user cannot install one:
- Tell the user that login sequences (multi-step login, 2FA) require browser automation.
- Offer to install
playwright-cli(preferred) or Playwright MCP. - Only if the user declines or installation fails, fall back to form login (Step 4) for simple single-page login forms.
Never guess CSS/XPath selectors without browser inspection.
Target Type Check — Do This First
Before proceeding, determine whether this is an API target or a web target:
- If the user has provided an OpenAPI/Swagger schema (URL or file), a Postman collection, or explicitly said "API target" — stop and use the
saw-api-target-configurationskill instead. - Otherwise, treat it as a web target by default. If the user just says "add a target", "create a target", or provides a URL without further qualification, proceed here.
What ships with it
5 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.
- 11d ago First seen · 261 lines · 77 tokens per session scan A 5067fb50e695
saw-web-target-configuration is a skill published in the GitHub repository snyk/saw-mcp (8 stars, last pushed yesterday), licensed Apache-2.0. It adds 77 tokens to every session and 3,704 once invoked, about $0.0004 per session on Opus 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 2026-08-31.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…
next-partial-prefetching-adoption
Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…