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/OpenAEC-Foundation/OpenAEC-Workspace-Composernpx agentmods add skills/openaec-foundation/openaec-workspace-composer/vite-errors-dev-serverWrote 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/openaec-foundation/openaec-workspace-composer/vite-errors-dev-server)<a href="https://agentmods.dev/skills/openaec-foundation/openaec-workspace-composer/vite-errors-dev-server"><img src="https://agentmods.dev/badge/skills/openaec-foundation/openaec-workspace-composer/vite-errors-dev-server.svg" alt="Measured on agentmods" 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 | $0.00124 | $0.02909 |
| Opus 5 | $0.00062 | $0.01455 |
| Sonnet 5 | $0.00025 | $0.00582 |
| Haiku 4.5 | $0.00012 | $0.00291 |
Grade A, and why
vite-errors-dev-server 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 7d 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 — 382 lines — stays where its author put it; the contents beside it link to each section on GitHub.
vite-errors-dev-server
Quick Diagnostic Table
| Symptom | Cause | Fix |
|---|---|---|
| Full page reload instead of HMR | No HMR boundary — module lacks import.meta.hot.accept() |
Add import.meta.hot.accept() in the changed module or a parent importer |
| HMR accept not detected | Whitespace before ( in import.meta.hot.accept( |
ALWAYS write import.meta.hot.accept( with NO line break between accept and ( |
| WebSocket connection failed | Wrong HMR config behind reverse proxy | Set server.hmr.clientPort, server.hmr.host, server.hmr.protocol |
EADDRINUSE on startup |
Port already in use | Kill the process on that port, or set server.strictPort: false (default) for auto-fallback |
| Proxy returns 500/ECONNREFUSED | Wrong target format or backend not running |
Verify target URL includes protocol (http://), add changeOrigin: true |
| CORS blocked request | Default server.cors allows only localhost origins |
Set server.cors: true for any origin, or configure specific origin |
| "Outside of Vite serving allow list" | server.fs.strict blocks files outside workspace root |
Add the directory to server.fs.allow |
| HTTPS certificate errors | Missing or invalid cert/key files | Pass valid key and cert to server.https, or use @vitejs/plugin-basic-ssl |
| Module not found / alias not working | Alias path uses wrong format | Use absolute paths with path.resolve() or /src/... root-relative format |
| File changes not detected | Chokidar fails in Docker/WSL2 | Set server.watch.usePolling: true |
| 403 Forbidden on all requests | server.allowedHosts blocks the hostname |
Add the hostname to server.allowedHosts array, or set to true |
| Slow initial page load | Modules transformed on-demand on first request | Configure server.warmup.clientFiles with frequently used entry files |
| Middleware mode errors | Missing appType: 'custom' |
ALWAYS set appType: 'custom' when using server.middlewareMode: true |
| Browser errors not in terminal | server.forwardConsole not enabled |
Set server.forwardConsole: true (v8+ only, auto-enabled for AI agents) |
What ships with it
3 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.
- 7d ago First seen · 382 lines · 124 tokens per session scan A 219c9f8baffa
vite-errors-dev-server is a skill published in the GitHub repository OpenAEC-Foundation/OpenAEC-Workspace-Composer (5 stars, last pushed 5mo ago), licensed MIT. It adds 124 tokens to every session and 2,909 once invoked, about $0.0006 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
aios-arch-health
Deterministic architecture-health governance for repositories. Use when a project needs complexity, duplication, dependency, test, coverage, mutation, QA, performance, database, concurrency, or failure-injection evidence; evidence provenance and artifact digests; protected specification, test, quality-profile, or QA…
aios-exec
A controlled workflow for carrying out clearly defined changes and checks in a project workspace. It covers code, bug fixes, documentation, scripts, tests, linting, type checks, builds, interface changes, and deployment preparation.
ha-logs
A read-only troubleshooting skill for querying Hope Agent’s local SQLite databases, which store logs, conversations, and background-job status.
ha-self-diagnosis
Self-understanding and issue reporting for Hope Agent itself. Use when the user asks how Hope Agent works internally, asks about its own source code/docs/runtime behavior, reports a bug/failure/slowness/crash, asks to diagnose logs, or asks to create/submit a GitHub issue for a bug, feature request, or improvement…
ha-debug
Hope-native debugging for code failures, regressions, crashes, flaky behavior, and bad output: reproduce or characterize, rank falsifiable hypotheses, fix the smallest root cause, and prove the failing path.
schema-validation
JSON/data schema validation for construction data exchange: API payloads, file imports, BIM exports. Ensure data structure compliance before processing.