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 fanfan-de/anybox --skill bilibili-creatorgit clone --depth 1 https://github.com/fanfan-de/anyboxWrote 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/fanfan-de/anybox/bilibili-creator)<a href="https://agentmods.dev/skills/fanfan-de/anybox/bilibili-creator"><img src="https://agentmods.dev/badge/skills/fanfan-de/anybox/bilibili-creator/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/fanfan-de/anybox/bilibili-creator"><img src="https://agentmods.dev/badge/skills/fanfan-de/anybox/bilibili-creator.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, 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 18 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.
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 | $0.00039 | $0.00693 |
| Opus 5 | $0.00019 | $0.00347 |
| Sonnet 5 | $0.00008 | $0.00139 |
| Haiku 4.5 | $0.00004 | $0.00069 |
Grade A, and why
bilibili-creator 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 12d 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 — 47 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Bilibili Creator
Use this skill when the user asks to inspect or manage the connected Bilibili creator account through the installed plugin.
Start with bilibili_test_auth when the connection is new, recently changed, or returning permission errors. The complete V1 workflow expects USER_INFO, USER_DATA, ARC_BASE, ARC_DATA, ATC_BASE, and ATC_DATA.
Metrics workflow
- Use
bilibili_account_getfor the current profile, follower count, following count, approved video count, and granted scopes. - Use
bilibili_dashboard_summaryfor a current read-only summary. State the scan bound when the response reportstruncated=true; do not describe a partial scan as an all-time total for the whole account. - Use
bilibili_metrics_snapshotonly when the user wants follower-change tracking or a saved measurement. It writes a minimal numeric snapshot locally. - Use
bilibili_metrics_historyto calculate change over time from saved snapshots. bilibili_metrics_clearpermanently removes the local history file. Call it only after the user explicitly asks to clear history, and passconfirm=true.
Video workflow
- Use
bilibili_video_categoriesbefore publishing when a valid category ID is not already known. - Use
bilibili_video_list,bilibili_video_get, andbilibili_video_statsfor read-only inspection. - Before
bilibili_video_publish, verify the absolute local file path, title, category, tags, copyright status, repost source when applicable, description, and optional cover. - A publish call uploads the file and submits a new稿件 for Bilibili review. Report the returned
resource_idand make clear that submission is not the same as public approval. - Never infer permission to publish merely because the user asked for a draft, metadata review, or upload plan.
Article workflow
- Use
bilibili_article_categoriesto obtain a child category ID. - Use
bilibili_article_upload_imagefor images referenced in article HTML. bilibili_article_publishrequires Bilibili-compatible HTML through exactly one ofcontent_htmlorcontent_path. Do not silently convert Markdown when formatting fidelity is uncertain.- Validate the selected template: template 3 needs at least three cover image URLs; template 4 needs a cover, banner, or top video; template 5 uses a generated default cover.
- Report the returned article ID and make clear that the article enters review.
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.
- 12d ago First seen · 47 lines · 39 tokens per session scan A 39e8a6112d90
bilibili-creator is a skill published in the GitHub repository fanfan-de/anybox (57 stars, last pushed 29d ago), licensed MIT. It adds 39 tokens to every session and 693 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 2026-08-30.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…
next-partial-prefetching-adoption
Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…