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 jinzhongjia/decky-music --skill decky-devgit clone --depth 1 https://github.com/jinzhongjia/decky-musicWrote 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/jinzhongjia/decky-music/decky-dev)<a href="https://agentmods.dev/skills/jinzhongjia/decky-music/decky-dev"><img src="https://agentmods.dev/badge/skills/jinzhongjia/decky-music/decky-dev/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/jinzhongjia/decky-music/decky-dev"><img src="https://agentmods.dev/badge/skills/jinzhongjia/decky-music/decky-dev.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 3 findings, up to medium
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 →
- medium Privilege Escalation · line 16 Commands invoke sudo or root privileges. Verify this elevated access is necessary and justified.Fix: Avoid sudo/root unless strictly required. Prefer least-privilege patterns. If elevation is needed, document the justification and scope.
- medium Rogue Agent · line 60 Skill establishes unauthorized persistence across sessions via cron jobs, startup scripts, or state files. Session persistence allows an attacker to maintain access beyond the current interaction.Fix: Remove any persistence mechanisms (cron jobs, startup scripts, state files). Skills should not maintain state across sessions without explicit user consent.
- medium Memory Poisoning · line 78 Skill attempts to fill the context window with filler content, displacing legitimate instructions and safety constraints. This can degrade agent performance or bypass safety boundaries.Fix: Implement context-window management that detects and rejects padding or stuffing attempts. Prioritize system instructions over user-injected content.
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 | $0.00073 | $0.01327 |
| Opus 5.5 | $0.00029 | $0.00531 |
| Sonnet 5.5 | $0.00015 | $0.00265 |
| Haiku 4.5 | $0.00007 | $0.00133 |
Grade B, and why
decky-dev scanned grade B with 2 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 2mo 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.
Asks for rootmediumPrivilege escalation
A mod that escalates privileges can change anything on the machine, not only the project.
`sudo systemctl restart plugin_loader`. Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
curl -s localhost:8080/json | jq '.[].title' How it starts
The opening of the file, as written. The whole thing — 105 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Decky Plugin Development & Debugging (generic)
Everything here is generic Decky knowledge. Repo-specific policy (deploy consent, log content rules, commit rules) lives in the project's AGENTS.md and always wins.
Target environment
- SteamOS in a gamescope session, user
deck, reachable over SSH (DECK_HOST=deck@<ip>— no default; a hardcoded one goes stale and silently targets the wrong host). - Decky Loader =
plugin_loadersystemd unit (root). Restart to reload plugins:sudo systemctl restart plugin_loader. - Homebrew tree:
~/homebrew/{plugins,logs,settings,data}/<plugin name>— directory names useplugin.json'snamefield, spaces included.
Plugin anatomy
main.pyPluginclass:asyncmethods are the RPC surface for the frontend (@decky/apicallable);decky.emitpushes events to the UI. Backend runs in Decky's frozen CPython — stdlib only, compiled extensions will break on Decky upgrades.py_modules/is the only extra dir added tosys.pathand packaged by the CLI.- Frontend ships as
dist/index.js(built from@decky/api+@decky/ui). package.jsonremote_binary: assets downloaded at install time intobin/<name>— saved verbatim, never unpacked. Archives (e.g. Nuitka standalone tar.gz) must be self-extracted by plugin code on first use. Pin URLs to a release tag:releases/latest/...404s for prereleases.- Installed permissions: plugin root dir is
root:root(read-only for deck), butbin/andpy_modules/aredeck:deck(writable) — the remote_binary downloader itself writesbin/.
Deploy loop (sideload)
Sideload = build → rsync the plugin subset → restart plugin_loader. Keep it in a repo script
(this repo: scripts/deploy.sh; target is required: DECK_HOST=deck@ip). Two rules that bite:
- Deploy scripts copy prebuilt artifacts, they don't build. Rebuild changed binaries first, or you ship stale ones.
- A sideload
dev_modemarker file (touched by the deploy script, absent from release zips) is a clean way to switch log verbosity; release zips must not contain it.
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.
- 2mo ago First seen · 105 lines · 73 tokens per session scan B 1df49ff93029
decky-dev is a skill published in the GitHub repository jinzhongjia/decky-music (125 stars, last pushed 2d ago), licensed MIT. It adds 73 tokens to every session and 1,327 once invoked, about $0.0003 per session on Opus 5.5. A static security scan graded it B with 2 findings (asks for root, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
decky-dev compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| decky-devjinzhongjia/decky-music | Skill | 125 | 2d ago | MIT | B | 73 | Claude Code, Codex |
| playtest-reportDonchitos/Claude-Code-Game-Studios | Skill | 36k | 18d ago | MIT | A | 20 | Claude Code |
| godot-signals-groupsgamedev-skills/awesome-gamedev-agent-skills | Skill | 6.9k | 9d ago | Apache-2.0 | A | 95 | Claude Code |
| scenario-unreal-gameplayscenario-labs/skills | Skill | 3.2k | yesterday | MIT | A | 121 | Claude Code |
| motionOpenDCAI/GameFactory-3A | Skill | 1.0k | 8d ago | Apache-2.0 | A | 0 | Claude Code, Codex |
| unity-addressablesBesty0728/Unity-Skills | Skill | 1.9k | yesterday | MIT | A | 25 | Claude Code, Codex |
| unity-manual-componentBesty0728/Unity-Skills | Skill | 1.9k | yesterday | MIT | A | 36 | Claude Code, Codex |