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 MapleCity1314/vite-browser --skill vite-browser-network-regressiongit clone --depth 1 https://github.com/MapleCity1314/vite-browserWrote 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/maplecity1314/vite-browser/vite-browser-network-regression)<a href="https://agentmods.dev/skills/maplecity1314/vite-browser/vite-browser-network-regression"><img src="https://agentmods.dev/badge/skills/maplecity1314/vite-browser/vite-browser-network-regression/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/maplecity1314/vite-browser/vite-browser-network-regression"><img src="https://agentmods.dev/badge/skills/maplecity1314/vite-browser/vite-browser-network-regression.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.00117 | $0.00475 |
| Opus 5.5 | $0.00047 | $0.00190 |
| Sonnet 5.5 | $0.00023 | $0.00095 |
| Haiku 4.5 | $0.00012 | $0.00047 |
Grade A, and why
vite-browser-network-regression 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 1mo 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.
What it actually says
vite-browser-network-regression
Use this skill to isolate request/response regressions quickly.
Workflow
- Open page and reproduce action.
- List network traffic and identify suspicious entries (4xx/5xx/FAIL/slow).
- Inspect target request in detail.
- Correlate with UI state and console errors.
- If the request failure appears only after a hot update or reload loop, switch to
vite-browser-runtime-diagnostics.
Commands
vite-browser open <url>
vite-browser errors --mapped
vite-browser logs
vite-browser network
vite-browser network <idx>
vite-browser eval '<state-probe>'
vite-browser screenshot
Analysis checklist
For each failed/suspicious request:
- URL and method correct?
- Status and response body expected?
- Request headers/body complete?
- CORS/auth/cookie mismatch?
- UI state consistent with response?
- Did the failure start only after a recent HMR update?
Output format
Always include:
- Failing request index and endpoint
- Concrete mismatch (request or response)
- Likely ownership (frontend request build vs backend response)
- Confidence:
high,medium, orlow - Exact re-test command sequence
When to switch skills
If diagnosis reveals the root cause is actually:
- HMR/runtime issue (failure only after hot update, module errors) → switch to
vite-browser-runtime-diagnostics - Component state or framework-specific issue → switch to
vite-browser-core-debug - Need final pre-release validation → switch to
vite-browser-release-smoke
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.
- 1mo ago First seen · 64 lines · 117 tokens per session scan A 90ac34288360
vite-browser-network-regression is a skill published in the GitHub repository MapleCity1314/vite-browser (9 stars, last pushed 6mo ago), licensed MIT. It adds 117 tokens to every session and 475 once invoked, about $0.0005 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 2026-08-31.
Other skills, from other repositories
surf
Drive the user's logged-in Chrome from the shell. Use for browser automation (open, read, click, fill, upload, screenshot), reading a site's feed or API, or asking ChatGPT, Gemini, Perplexity or Grok through the browser.
agent-inspect
Local evidence debugger and trajectory-test toolkit for TypeScript AI agents. Use when capturing framework-faithful traces, asserting TraceContract/TraceFacts, packaging Evidence v2, or inspecting local runs over read-only MCP (gettracefacts).
rewynd-backend-debugging
Use when debugging, verifying, or investigating backend runtime behavior — HTTP 500s, wrong responses, slow endpoints, suspected N+1 or duplicate queries, "why did this request do that" — in a project running under rewynd. Reads the actual recorded request trace (SQL with params, outbound calls, logs, exceptions…
code_explorer
Explores the repository to locate primary source files, coupled UI components, and test files for bug reports or feature requests.
test-failure-explorer
Import and query an existing Vitest 3.2 JSON report to explore test failures, file-level errors and original diagnostic evidence.
feedback
Skill "feedback" from Hmbown/Codewhale, covering feedback, when to use, setup, workflow and non-goals.