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 psylch/media-master --skill quark-downloadgit clone --depth 1 https://github.com/psylch/media-masterWrote 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/psylch/media-master/quark-download)<a href="https://agentmods.dev/skills/psylch/media-master/quark-download"><img src="https://agentmods.dev/badge/skills/psylch/media-master/quark-download/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/psylch/media-master/quark-download"><img src="https://agentmods.dev/badge/skills/psylch/media-master/quark-download.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 | $0.00100 | $0.02364 |
| Opus 5 | $0.00050 | $0.01182 |
| Sonnet 5 | $0.00020 | $0.00473 |
| Haiku 4.5 | $0.00010 | $0.00236 |
Grade A, and why
quark-download 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 11d 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 — 216 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Quark Search — 网盘资源搜索与下载
Language
Match user's language: Respond in the same language the user uses.
Automate the full workflow: search resources → validate links → save to Quark cloud drive → download locally, by combining the PanSou aggregation API with the local Quark desktop APP.
All operations use the CLI script at ${SKILL_PATH}/scripts/quark_search.py. It outputs JSON to stdout ({"status": "ok", "results": {...}, "hint": "..."}) and errors to stderr ({"error": "code", "message": "...", "hint": "...", "recoverable": true/false}). Exit codes: 0 = success, 1 = recoverable error, 2 = fatal error.
Preflight (MUST run first)
Before any business command (search, validate, save, etc.), run preflight:
python3 ${SKILL_PATH}/scripts/quark_search.py preflight
Response: Standardized JSON with ready: true/false, dependencies, and services status.
- If
ready: true→ proceed to workflow. - If
ready: false→ follow the Check/Fix table below, then re-run preflight until it passes. Do NOT proceed to search or save until preflight passes.
| Check | Fix |
|---|---|
| Quark APP not running | Launch Quark desktop APP and wait a few seconds for it to start |
| Quark APP not logged in | Log in with membership account in the Quark APP |
Why gate on preflight? Search itself works without Quark APP (it calls the PanSou web API), but
saverequires a running, logged-in Quark APP. Running preflight first prevents the frustrating experience of finding resources and then discovering you can't save them.
Workflow — Quick Search (recommended)
Prerequisite: Preflight must have returned ready: true.
A single command searches PanSou, validates all links in parallel, and fetches file details for the top results:
python3 ${SKILL_PATH}/scripts/quark_search.py search "KEYWORD" --top 5
Options:
| Flag | Default | Description |
|---|---|---|
--top N |
5 |
Number of top valid results to return with details |
--no-validate |
off | Skip validation (faster, but may include dead links) |
--limit N |
30 |
PanSou results per page |
--page N |
1 |
PanSou page number |
What ships with it
2 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.
- 11d ago First seen · 216 lines · 100 tokens per session scan A 30f8082ca3cb
quark-download is a skill published in the GitHub repository psylch/media-master (5 stars, last pushed 6mo ago), licensed MIT. It adds 100 tokens to every session and 2,364 once invoked, about $0.0005 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 2026-08-31.
Other skills, from other repositories
edgeone skill scanner
A local static scanner that checks agent-skill files for security risks before they are installed or used. Static analysis examines files without running them.
autoreview
Pre-commit/ship code review: Codex default; optional Claude or Pi.
convex-billing
Add Stripe billing/payments to the Convex app via @convex-dev/stripe (checkout + webhook + gating).
dev-workflow
The complete development workflow for SkillHub contributors including local dev, staging validation, testing, and PR creation. Ensures agents follow the correct sequence of steps.
video-frames
Extract a single frame from a local video at the first frame, a timestamp, or a zero-based frame index using FFmpeg.
convex-performance-audit
Audits Convex performance for reads, subscriptions, write contention, and function limits. Use for slow features, insights findings, OCC conflicts, or read amplification.