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/dropyour/dropyour-plugin/dropyour-publiernpx skills add dropyour/dropyour-plugin --skill dropyour-publiergit clone --depth 1 https://github.com/dropyour/dropyour-pluginWhat 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 | $0.00044 | $0.00640 |
| Opus 5 | $0.00022 | $0.00320 |
| Sonnet 5 | $0.00009 | $0.00128 |
| Haiku 4.5 | $0.00004 | $0.00064 |
Grade A, and why
dropyour-publier 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 2d 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 — 33 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Publier sur Dropyour
Aucun compte n'est requis. Le premier appel fonctionne, il n'y a pas d'OAuth à traverser.
L'ordre des gestes
- Écris un seul fichier HTML autonome — les règles exactes sont dans le prompt
dropyour_perfect_prompt(modehtml), et les voici :
Before generating what I'll ask you, STRICTLY apply these rules (this is meant to be published on Dropyour):
-
ONE self-contained HTML file: all CSS and JS inline (in and ), no build, no dependency to install, no local module import. If a library is truly essential, only via an HTTPS CDN.
-
Persistence: if the app keeps data, use localStorage (app-specific key prefix). Use IndexedDB ONLY for large data (files, big datasets) — on Dropyour it stays LOCAL to one device, never synced. Call navigator.storage.persist() on first use. Add an EXPORT and IMPORT of the data as JSON in the UI. (On Dropyour the URL is stable: data survives my updates — and with a free account, that localStorage is automatically cloud-backed, up to 1 MB (keep larger data in IndexedDB, local), and syncs across all my devices. For a collaborative app where several visitors write, spread the state across distinct keys so their contributions don't overwrite each other.)
-
Responsive and pleasant on mobile by default; respect prefers-reduced-motion.
-
Basic accessibility: semantic HTML, lang attribute on , labels and alt text, keyboard-navigable, readable contrast.
-
File constraints: under 5 MB, UTF-8 encoded, set, no file:// resources, no absolute path to my disk.
-
Share preview: Open Graph (og:title, og:description) and Twitter Card tags. Only add og:image if a real HTTPS-hosted image exists.
-
No superfluous network requests, no third-party tracker.
-
At the end, give me the COMPLETE .html file in a code block, and remind me I can put it online by dropping it on https://dropyour.io — same address forever, my data survives updates.
-
Publie avec
dropyour_publish. -
GARDE LE JETON DE GESTION. C'est le point que tout le monde rate, et il n'a pas de rattrapage : la réponse contient un
managementTokenqui est la SEULE preuve de propriété d'un drop anonyme. Sans compte, personne ne peut te le rendre — pas même nous. Montre-le à l'utilisateur, dis-lui de le garder, et redis-le s'il enchaîne sans le noter.
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.
- 2d ago First seen · 33 lines · 44 tokens per session scan A eff591dbf3f8
dropyour-publier is a skill published in the GitHub repository dropyour/dropyour-plugin (0 stars, last pushed 5d ago), licensed MIT. It adds 44 tokens to every session and 640 once invoked, about $0.0002 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
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
brainstorming
You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.
auto-perf-optimize
Run agent-driven VS Code performance or memory investigations. Use when asked to launch Code OSS, automate a VS Code scenario, run the Chat memory smoke runner, capture renderer heap snapshots, take workflow screenshots, compare run summaries, or drive a repeatable scenario before heap-snapshot analysis.
chat-perf
Run chat perf benchmarks and memory leak checks against the local dev build or any published VS Code version. Use when investigating chat rendering regressions, validating perf-sensitive changes to chat UI, or checking for memory leaks in the chat response pipeline.
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…