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 steam-cdpgit 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/steam-cdp)<a href="https://agentmods.dev/skills/jinzhongjia/decky-music/steam-cdp"><img src="https://agentmods.dev/badge/skills/jinzhongjia/decky-music/steam-cdp/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/steam-cdp"><img src="https://agentmods.dev/badge/skills/jinzhongjia/decky-music/steam-cdp.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
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 Memory Poisoning · line 89 Skill manipulates agent memory, state, or stored context. Memory corruption can alter personality, override safety rules, or cause unpredictable behavior.Fix: Protect agent memory and state from modification by untrusted content. Use read-only memory for critical instructions and validate all state changes.
- medium Memory Poisoning · line 84 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 | $0.00082 | $0.01433 |
| Opus 5.5 | $0.00033 | $0.00573 |
| Sonnet 5.5 | $0.00016 | $0.00287 |
| Haiku 4.5 | $0.00008 | $0.00143 |
Grade A, and why
steam-cdp 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 19d 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 — 111 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Steam CDP Automation
Steam's embedded Chromium (CEF) exposes remote debugging on localhost:8080 on the device
(enabled by default in Decky environments; desktop Steam needs -cef-enable-debugging).
Everything here is read-only diagnosis and test driving — never ship CDP tricks inside a
plugin. The bundled scripts live in scripts/ next to this file and are dependency-free
(Node ≥ 21 for global fetch/WebSocket).
Setup (once per machine session)
ssh -N -L 8080:localhost:8080 deck@<ip> & # tunnel; survives plugin_loader restarts
node scripts/cdp.mjs targets # list targets, sanity-check the tunnel
Targets
| Alias | Target | Use for |
|---|---|---|
bp |
gamepad-UI main window ("Steam Big Picture Mode" / localized) | the visible screen: screenshots, DOM clicks, key input |
qam |
QuickAccess | Quick Access Menu overlay |
mainmenu |
MainMenu | left Steam main menu overlay |
shared / sjc |
SharedJSContext | main JS context (no pixels) — webpack/module probing |
Script inventory
node scripts/cdp.mjs targets # list targets with aliases
node scripts/cdp.mjs <target> <probe.js> # Runtime.evaluate a JS file, print its return value
node scripts/cdp-nav.mjs /your-route # navigate the gamepad UI to a route
node scripts/cdp-shot.mjs bp /tmp/ui.png # screenshot a target to PNG
node scripts/cdp-key.mjs bp ArrowDown Enter # dispatch keyDown/keyUp pairs
node scripts/cdp-console.mjs shared 30 # stream console warnings/errors for N seconds
node scripts/cdp.mjs mainmenu scripts/probe-mainmenu.js # example probe: menu patch anchors
cdp-lib.mjs is the shared helper (target resolution, sessions, evaluate, screenshot, keys) —
import it to build new drivers.
Writing probes
A probe is an IIFE evaluated in the target page. Return a JSON-serializable value instead of printing from inside the page. Reuse the bundled probes before writing another React-fiber walk.
What ships with it
9 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.
- scripts/cdp-console.mjs 2.3 KB runs code
- scripts/cdp-key.mjs 594 B runs code
- scripts/cdp-lib.mjs 7.1 KB runs code
- scripts/cdp-nav.mjs 1.6 KB runs code
- scripts/cdp-shot.mjs 781 B runs code
- scripts/cdp.mjs 1.6 KB runs code
- scripts/probe-callables.js 1.6 KB runs code
- scripts/probe-mainmenu.js 3.0 KB runs code
- scripts/probe-menu-items.js 1.4 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.
- 19d ago Changed · +5 lines 6af81cca8eb6
- 2mo ago First seen · 106 lines · 82 tokens per session scan A 1aea64ad4b42
steam-cdp is a skill published in the GitHub repository jinzhongjia/decky-music (125 stars, last pushed 2d ago), licensed MIT. It adds 82 tokens to every session and 1,433 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 2026-08-30.
steam-cdp compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| steam-cdpjinzhongjia/decky-music | Skill | 125 | 2d ago | MIT | A | 82 | Claude Code, Codex |
| interactive-loginyc-software/qm | Skill | 16k | yesterday | MIT | A | 46 | Claude Code, Codex |
| pinchtab-mcppinchtab/pinchtab | Skill | 11k | 10d ago | MIT | A | 52 | Claude Code, Codex |
| azure-messaging-webpubsub-javamicrosoft/skills | Skill | 3.2k | yesterday | MIT | A | 43 | Claude Code |
| cua-driverdavidondrej/skills | Skill | 4.3k | 3d ago | MIT | A | 68 | Claude Code, Codex |
| open-design-browsercompozy/compozy | Skill | 2.8k | yesterday | MIT | A | 56 | Claude Code, Codex |
| southwestborski/travel-hacking-toolkit | Skill | 895 | yesterday | MIT | A | 40 | Claude Code |