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 tranfu-labs/tranfu-skills --skill wechat-sketch-covergit clone --depth 1 https://github.com/tranfu-labs/tranfu-skillsWrote 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/tranfu-labs/tranfu-skills/wechat-sketch-cover)<a href="https://agentmods.dev/skills/tranfu-labs/tranfu-skills/wechat-sketch-cover"><img src="https://agentmods.dev/badge/skills/tranfu-labs/tranfu-skills/wechat-sketch-cover/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/tranfu-labs/tranfu-skills/wechat-sketch-cover"><img src="https://agentmods.dev/badge/skills/tranfu-labs/tranfu-skills/wechat-sketch-cover.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 | $0.00171 | $0.04842 |
| Opus 5 | $0.00086 | $0.02421 |
| Sonnet 5 | $0.00034 | $0.00968 |
| Haiku 4.5 | $0.00017 | $0.00484 |
Grade A, and why
wechat-sketch-cover 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 — 268 lines — stays where its author put it; the contents beside it link to each section on GitHub.
WeChat Sketch Cover
Create exactly one fixed-format WeChat article cover. The style, layout, dimensions, text policy, and output contract are not configurable. The candidate-generation backend is open.
Orchestrated provider route
Before the standalone workflow, inspect structured requests. If a request contains any of
contract: content-production-provider/v2, capability: wechat_cover,
provider_contract: wechat-cover-v1, or content-production-provider: wechat-cover-v1, MUST read
references/orchestrated-provider.md and use
scripts/provider-contract.mjs. A partial, conflicting, or invalid provider marker returns a
structured BLOCKED result and NEVER falls back to standalone behavior.
Provider mode treats the approved WeChat selection as the only title authority; the bound draft H1 is content context and may differ. Without a provider marker, ignore the provider reference and run the standalone workflow below unchanged.
Fixed contract
- MUST generate one raster cover with an available image-generation or programmatic rendering backend.
- MUST use the fixed style in references/style-spec.md.
- MUST use the fixed Chinese handwritten title treatment defined there: bold brush strokes, hand-written Chinese calligraphy title forms, and marker / brush handwritten Chinese lettering.
- MUST render the supplied title verbatim on the left for a passing candidate. After attempt 03 only, an otherwise compliant candidate may be delivered as BEST_EFFORT when the title remains readable in the required left two-or-three-line layout and title accuracy is the sole failed gate; that explicit exception overrides only the verbatim-title gate and MUST be reported.
- MUST normalize every candidate to a PNG measuring exactly 1923 x 818 pixels.
- MUST allow only the supplied title as readable text. Decorative scribble lines may imply interface content but MUST NOT form additional words.
- MUST NOT offer style, palette, aspect-ratio, font, branding, or layout choices.
- MAY use installed image skills, built-in generation, CLI, API, SVG, HTML, CSS, Canvas, or any other available image backend for candidate creation.
- MAY compose, edit, overlay, replace, or repair candidate content programmatically, including exact title rendering, provided the resulting candidate still passes every fixed visual and output gate.
What ships with it
12 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.
- agents/openai.yaml 422 B
- assets/icon.png 509 B
- assets/icon.svg 435 B
- assets/style-reference.png 1018 KB
- LICENSE 1.1 KB
- NOTICE 1.1 KB
- README.md 2.5 KB
- README.zh.md 2.2 KB
- references/orchestrated-provider.md 4.9 KB
- references/style-spec.md 9.7 KB
- scripts/normalize_cover.py 2.9 KB runs code
- scripts/provider-contract.mjs 35 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.
- 12d ago First seen · 268 lines · 171 tokens per session scan A 0c830d1943e6
wechat-sketch-cover is a skill published in the GitHub repository tranfu-labs/tranfu-skills (2 stars, last pushed 2d ago), licensed MIT. It adds 171 tokens to every session and 4,842 once invoked, about $0.0009 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.
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…
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…
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…