What is claudette-debug?

A development-only debugger for the Claudette desktop app, which runs on Tauri. It can execute JavaScript in the app’s web view and inspect its current state while the app is running.

Use it to inspect stored data, trace state changes, send chat messages, take screenshots, run end-to-end checks, and investigate interface bugs in Claudette development builds.

It helps find interface and state problems without guessing from source code alone. You can observe changes, wait for agent activity, and reproduce user actions in the live app.

How utensils/claudette configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to utensils/claudette. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file

curl -O https://raw.githubusercontent.com/utensils/claudette/main/.claude/skills/claudette-debug/SKILL.md

Clone the repo

git clone --depth 1 https://github.com/utensils/claudette

Made for: Claude Code.

Wrote 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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/utensils/claudette/claudette-debug/github.svg)](https://agentmods.dev/skills/utensils/claudette/claudette-debug)

Your own site

<a href="https://agentmods.dev/skills/utensils/claudette/claudette-debug"><img src="https://agentmods.dev/badge/skills/utensils/claudette/claudette-debug/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.

Your own site · 80×15

<a href="https://agentmods.dev/skills/utensils/claudette/claudette-debug"><img src="https://agentmods.dev/badge/skills/utensils/claudette/claudette-debug.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 62 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 6,064 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe. Third-party audits

NVIDIA SkillSpector warn 7 Sept 2026

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 Tool Misuse · line 94
Tool parameters are crafted to achieve unintended or unsafe behavior. Parameter abuse can bypass intended safety checks (e.g. shell=True, --force, dangerous glob patterns).

Fix: Validate all tool parameters against an allowlist. Reject dangerous parameter values (shell=True, --force, -rf /) and use safe defaults.
high Data Exfiltration · line 223
Code or instructions that leak agent conversation context to external services, potentially exposing sensitive user interactions.

Fix: Remove any code that sends prompts, responses, or session data externally. Preserve user privacy; never exfiltrate conversation content.

How audits are shown

Origin original No closer match found in the catalogue.

Token cost

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	$0.00062	$0.06064
Opus 5.5	$0.00025	$0.02426
Sonnet 5.5	$0.00012	$0.01213
Haiku 4.5	$0.00006	$0.00606

Measured 1mo ago against content hash 52b3faee90be, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

claudette-debug 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.

The scan reads SKILL.md. This mod also ships 5 executable files (scripts/debug-eval.sh, scripts/debug-monitor.sh, scripts/debug-screenshot.ps1, …), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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.

.claude/skills/claudette-debug/SKILL.md · 544 lines

How it starts

The opening of the file, as written. The whole thing — 544 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Claudette Debug

Execute JavaScript inside the running Claudette Tauri webview via a TCP debug server on 127.0.0.1. Dev-build only (#[cfg(debug_assertions)]).

The server listens on port 19432 by default, but the devshell dev helper auto-selects a free port (and writes a discovery file) so multiple dev instances can run in parallel against different branches. debug-eval.sh discovers the right instance automatically — you do not need to know the port. Details in Port discovery below.

Quick Start

/claudette-debug status                   # One-shot workspace status (agent, messages, scroll, tools)
/claudette-debug discover actions         # List all store functions with parameter names
/claudette-debug discover state           # List all state slices with types and values
/claudette-debug send "read README.md"    # Send a chat message to the active workspace
/claudette-debug wait                     # Block until agent goes idle (run_in_background)
/claudette-debug screenshot               # Capture screen, return image path for Read tool
/claudette-debug state                    # Contextual store overview
/claudette-debug eval 'return 1+1'        # Execute arbitrary JS
/claudette-debug monitor start            # Start background session monitor

Prerequisites

App running via the devshell dev helper (or cargo tauri dev) — debug TCP server starts automatically
python3 in PATH (used by eval helper)

Do NOT launch the installed app. Never run osascript -e 'tell application "Claudette" to activate', open -a Claudette, or double-click /Applications/Claudette.app. The debug TCP server only exists in dev builds (gated by #[cfg(debug_assertions)]); the installed release build has no debug server and eval calls against it will fail or silently target the wrong process. If the dev build is not already running, ask the user to start dev — do not start it yourself and do not fall back to the installed app.

Read the full file on GitHub · 544 lines

Files

What ships with it

8 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.

Changes

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 · 544 lines · 62 tokens per session scan A 52b3faee90be

Subscribe to this mod's changes

claudette-debug is a skill published in the GitHub repository utensils/claudette (83 stars, last pushed 1mo ago), licensed MIT. It adds 62 tokens to every session and 6,064 once invoked, about $0.0002 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 2026-08-30.

Claude Code Debugging E2E testing Testing agent-orchestration ai-agents remote-workspace worktree-manager worktrees

test-runner

Use this skill when orchestrating agentic end-to-end tests. Resolves target + profile, dispatches the right driver(s) (playwright for web today, peekaboo for macOS (issue #381)), invokes the ux-evaluator agent (opus, read-only) against driver artifacts, reconciles findings with the open issue tracker via…

Kanevry/session-orchestrator · 124 tokens

reengineering-vibe-code

Rescues an existing vibe-coded prototype: audits the running app, builds a characterization test safety net, consolidates specs/REQS.md, extracts a pure domain layer and migrates vertical slices with independent certification. Use when the user says "harden our local prototype", "rescue this vibe-coded app", "I have a…

richfrem/agent-plugins-skills · 124 tokens

browser-test-self-healing

Build an AgentWorks workflow that diagnoses a browser-test failure, proposes a test-only repair, verifies it in isolation, obtains the configured review, and updates canonical tests and application knowledge. Use for stale or flaky browser automation, not product defects.

manishiitg/coding-agent-loop · 54 tokens

flaky-test-detection-stabilization

Build AgentWorks browser-test flake detection and reviewed stabilization using repeated isolated attempts and evidence comparison. Use when identical test inputs produce inconsistent outcomes.

manishiitg/coding-agent-loop · 37 tokens

verify-omnigent

Drive Omnigent the way a user does and prove a behavior with recorded evidence, using an isolated server, runner, and mock model plus a feature map of every user entry point. Load before reproducing a user-facing bug, before claiming a fix works, or when reviewing whether a change covered every surface (session vs.…

omnigent-ai/omnigent · 100 tokens

verify

Exercise the real app/API/CLI and collect observable evidence; tests alone do not count as end-to-end verification.

Hmbown/CodeWhale · 25 tokens

claudette: Skill for Claude Code