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/utensils/claudette/claudette-debugnpx skills add utensils/claudette --skill claudette-debuggit clone --depth 1 https://github.com/utensils/claudetteWrote 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/utensils/claudette/claudette-debug)<a href="https://agentmods.dev/skills/utensils/claudette/claudette-debug"><img src="https://agentmods.dev/badge/skills/utensils/claudette/claudette-debug.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 | $0.00062 | $0.06064 |
| Opus 5 | $0.00031 | $0.03032 |
| Sonnet 5 | $0.00012 | $0.01213 |
| Haiku 4.5 | $0.00006 | $0.00606 |
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 5d 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 — 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
devhelper (orcargo tauri dev) — debug TCP server starts automatically python3in 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.
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.
- reference/recipes.md 3.6 KB
- reference/store-actions.md 5.6 KB
- reference/tauri-commands.md 4.3 KB
- scripts/debug-eval.sh 3.9 KB runs code
- scripts/debug-monitor.sh 2.8 KB runs code
- scripts/debug-screenshot.ps1 2.8 KB runs code
- scripts/debug-screenshot.sh 2.4 KB runs code
- scripts/debug-wait.sh 3.3 KB runs code
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.
- 5d ago First seen · 544 lines · 62 tokens per session scan A 52b3faee90be
claudette-debug is a skill published in the GitHub repository utensils/claudette (75 stars, last pushed 3d ago), licensed MIT. It adds 62 tokens to every session and 6,064 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 2026-08-30.
Other skills, from other repositories
verify
Exercise the real app/API/CLI and collect observable evidence; tests alone do not count as end-to-end verification.
webapp-testing
Start/reuse a local app, wait for readiness, inspect rendered state/console/network, act from observed selectors, and verify with evidence.
tutti-record-agent-session-replay
From a Tutti checkout, run, audit, freshly replay, publish, or diagnose Session Replay cassettes that are driven by case-repository scenario scripts (CDP), not by interactive UI recording. Use for real-Provider capture while a scenario.mjs executes, cassette transport or semantic-state mismatches, fresh replay…
local-frontend-check
Smoke-test or verify UI behaviour on the local Jarvis Registry frontend running at http://localhost/gateway. Use for manual regression checks, bug-fix verification, and end-to-end confirmation of specific flows without running the automated test suite.
qa
Browser-based QA verification. Launches a real browser, navigates the app, clicks buttons, fills forms, and tests user flows. Works as a standalone skill or as a phase end condition in campaigns. Requires Playwright (optional dependency, graceful skip if not installed).
live-preview
Mid-build visual verification loop. Takes screenshots of components during construction, not just after. Catches visual regressions and invisible features before they compound. Requires Playwright or similar screenshot tool.