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 agentmods add skills/developerz-ai/ui-debugger-mcp/claudenpx skills add developerz-ai/ui-debugger-mcp --skill claudegit clone --depth 1 https://github.com/developerz-ai/ui-debugger-mcpWrote 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/developerz-ai/ui-debugger-mcp/claude)<a href="https://agentmods.dev/skills/developerz-ai/ui-debugger-mcp/claude"><img src="https://agentmods.dev/badge/skills/developerz-ai/ui-debugger-mcp/claude.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 | $0.00061 | $0.00859 |
| Opus 5 | $0.00030 | $0.00430 |
| Sonnet 5 | $0.00012 | $0.00172 |
| Haiku 4.5 | $0.00006 | $0.00086 |
Grade A, and why
using-claude-cli scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 3d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 77 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Using claude as a tool
claude (Claude Code) is interactive by default, but it's also a scriptable CLI:
give it a prompt, let it run autonomously, capture the result. This is how you
spawn a Claude "sub-agent" from a script, a hook, or another Claude.
One-shot (headless) runs
claude -p "Summarize the failing tests in this repo" # print result, exit
-p, --print— run once, print the final message, exit (no REPL).--output-format text|json|stream-json—text(default) for humans;jsonfor a single structured result;stream-jsonto read events live (pair with--verbose).--model <id>— pick the model for this run (e.g. a fast model for cheap jobs).- Prompt can come from an arg, a file, or stdin:
claude -p "$(cat task.txt)" echo "explain this error" | claude -p
Permissions (the usual headless gotcha)
Headless runs can't show permission prompts, so a tool that needs approval just stalls. Choose one:
--permission-mode acceptEdits— auto-accept file edits, still gate the rest.--allowedTools "Bash(git*) mcp__myserver__*"— allowlist exactly what may run.--dangerously-skip-permissions— bypass ALL checks. Only in a sandbox / on a throwaway target you trust. Never against production or with secrets in reach.
MCP servers
claude -p "Use the debugger to QA the app" \
--mcp-config ./.mcp.json --strict-mcp-config \
--allowedTools "mcp__ui-debugger__*"
--mcp-config <file...>— load MCP servers from explicit JSON files.--strict-mcp-config— use ONLY those, ignoring auto-discovered project configs (reproducible, no surprise servers).- MCP tools are named
mcp__<server>__<tool>— match that in--allowedTools. - The MCP server inherits the spawned process's env + cwd; put per-run secrets in
the
.mcp.jsonenvblock (and keep that file out of git).
Sessions
--continue— resume the most recent session in this directory.--resume <session-id>— resume a specific one.- Each working directory is its own session context.
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.
- 3d ago First seen · 77 lines · 61 tokens per session scan A 9920fc486fa3
using-claude-cli is a skill published in the GitHub repository developerz-ai/ui-debugger-mcp (2 stars, last pushed yesterday), licensed MIT. It adds 61 tokens to every session and 859 once invoked, about $0.0003 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
rust-mcp-server-generator
Generate a complete Rust Model Context Protocol server project with tools, prompts, resources, and tests using the official rmcp SDK.
scraper-recipe
Génère un scraper Bxc complet (profil choisi + extraction typée Zod + sortie JSONL). À utiliser quand l'utilisateur demande "scrape X", "extract Y from URL Z", ou veut un nouveau scraper one-shot dans examples/ ou un sub-package dans packages/.
bxc Core
This skill should be used when the user asks to work on bxc (or similar Bun + Rust FFI native browser/X/Grok/agent engine projects), "bxc stack", "zero-spawn", native X client, Grok xAI high-level, bxc-mcp, scraper packages, rust-bridge FFI, autopilot, CLAUDE.md rules, cross-platform Bun/Rust builds, or needs patterns…
bxc Grok xAI High-Level Client
This skill should be used for anything involving @aphrody/xai (high-level Chat.createChat/append/sample/stream/executeToolCalls/sampleStructured), XTools for native X fulfillment, SuperGrok / OIDC keyless (SUPERGROKTOKEN or /.grok/auth.json), reasoningeffort, structured outputs, tool calling loops with real @aphrody/x…
bxc Rust FFI Bridge
This skill should be used when working on rust-bridge/, FFI between Bun and Rust (cdylib, nomangle extern "C", lolhtml, V8, x-client, x-algorithm), rusqlite workspace constraints, tokio async blocks for FFI, cross-platform cdylib (.so/.dylib/.dll), bxcx symbols, Cargo workspace for rust-bridge crates, or porting Rust…
rust-native-scanner
Expertise in high-performance native codebase scanning and validation using Rust. Trigger this skill when asked to "scan the codebase natively", "run rust scanner", or "validate bxc core using rust".