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 krzysztofsurdy/code-virtuoso --skill godotgit clone --depth 1 https://github.com/krzysztofsurdy/code-virtuosoWrote 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/krzysztofsurdy/code-virtuoso/godot)<a href="https://agentmods.dev/skills/krzysztofsurdy/code-virtuoso/godot"><img src="https://agentmods.dev/badge/skills/krzysztofsurdy/code-virtuoso/godot/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/krzysztofsurdy/code-virtuoso/godot"><img src="https://agentmods.dev/badge/skills/krzysztofsurdy/code-virtuoso/godot.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 | $0.00069 | $0.01851 |
| Opus 5.5 | $0.00028 | $0.00740 |
| Sonnet 5.5 | $0.00014 | $0.00370 |
| Haiku 4.5 | $0.00007 | $0.00185 |
Grade A, and why
godot 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 today.
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 — 99 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Godot
Godot reports success when the project is broken. A headless import and a parse check both exit 0 with broken scripts, a failed assert() can hang a script run, and push_error does not change the exit code. An agent that trusts exit codes or "it compiles" reports done on a game that does not run. This skill gives the loop that proves a change, and the traps that make the usual checks lie.
Facts here are for Godot 4.x and name the version where behavior differs. Run godot --version first, and use the godot-upgrade skill when the project crosses versions.
Verify loop
Run it after every change. Done means seen working in the running game.
| Step | How | Pass when |
|---|---|---|
| 1. Import | godot --headless --path <dir> --import |
Run it on a clean checkout too: .godot/ is not committed, and without an import class_name types do not resolve |
| 2. Parse | godot --headless --path <dir> --check-only --script res://file.gd per script |
The output has no SCRIPT ERROR or Parse Error. The exit code is 0 either way |
| 3. Run and read the log | Run the game and read its output | No ERROR or WARNING from your code |
| 4. Screenshot | Capture a frame of the running game and look at it | The change is visible |
| 5. Input | Simulate an input action, not a raw key | The action fires |
| 6. Live state | Read a value from the running scene tree (position, health, scene name) before and after the input | The value changed as intended. A screenshot alone is not proof |
| 7. Stop, commit | Stop the game, then commit |
scripts/check.sh runs steps 1 and 2 for a whole project and exits 1 on errors, because it reads the output instead of the exit code. Set GODOT to the binary. Its self-test is scripts/test-check.sh.
Steps 3 to 6 need a way to run the game and drive it. An MCP server for Godot or the CLI can provide this (see Platform notes). Without an MCP server: godot --path <dir> --write-movie out.png --fixed-fps 30 --quit-after 60 writes numbered PNG frames from a windowed run (it cannot run headless), and read the last one. A --script run can print live state and call quit(code) itself.
What ships with it
7 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.
- today First seen · 99 lines · 69 tokens per session scan A b98ae73e9edf
godot is a skill published in the GitHub repository krzysztofsurdy/code-virtuoso (36 stars, last pushed today), licensed MIT. It adds 69 tokens to every session and 1,851 once invoked, about $0.0003 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 2026-10-23.
Other skills, from other repositories
hz-vr-debug
Debugs Meta VR and Horizon OS VR, MR, and Android applications using the metavr CLI — view logs, capture screenshots, and diagnose common issues. Use when troubleshooting crashes, errors, or unexpected behavior on Meta VR devices. Build paths: All; use hz-quest-verify-first if the path is unclear.
hz-perfetto-debug
Analyzes Meta VR and Horizon OS VR performance using Perfetto traces — frame timing, CPU/GPU bottlenecks, render pass analysis. Use when profiling frame drops, jank, or thermal issues on Meta VR devices. Build paths: all Meta VR app stacks; use hz-quest-verify-first if the build path is unclear.
unity-validation
Use when users want to find missing scripts, validate references, or check project health.
unity-console
Use when users want to capture, filter, or clear console logs.
django-ticket-triage
Analyze a Django Trac ticket and produce a triage recommendation report — duplicate search, related PRs, forum threads, and the affected source code. Use when the user gives a Django ticket number, or asks whether a ticket is valid, a duplicate, or ready for a triage stage.
gh-issues
Fetch GitHub issues, spawn sub-agents to implement fixes and open PRs, then monitor and address PR review comments. Usage: /gh-issues [owner/repo] [--label bug] [--limit 5] [--milestone v1.0] [--assignee @me] [--fork user/repo] [--watch] [--interval 5] [--reviews-only] [--cron] [--dry-run] [--model glm-5]…