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/zju-real/easel/batch-processnpx skills add ZJU-REAL/Easel --skill batch-processgit clone --depth 1 https://github.com/ZJU-REAL/EaselWhat 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 | $0.00153 | $0.00940 |
| Opus 5 | $0.00077 | $0.00470 |
| Sonnet 5 | $0.00031 | $0.00188 |
| Haiku 4.5 | $0.00015 | $0.00094 |
Grade A, and why
batch-process 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 3d 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.
What it actually says
批量处理（目录级）
对整个目录的图片/视频/音频统一套用同一操作。走
skills/shared/scripts/batch_process.py， 逐个委派给对应确定性脚本（image_ops / video_ops / audio_ops）。
单文件处理见 image-editing / video-editing / audio-editing；本 SKILL 是它们的目录批量版。
输入
| 字段 | 必填 | 说明 |
|---|---|---|
| 目录 | 是 | 待处理文件所在目录 |
| 类型 | 是 | image / video / audio（决定用哪个 ops 脚本 + 文件筛选） |
| 操作 | 是 | ops 子命令（如 resize/compress/watermark/aspect/convert/normalize） |
| 操作参数 | 视操作 | 写在 -- 之后，原样透传给 ops 脚本 |
输出（默认 <目录>/batch_out/）
- 处理后的同名文件；报告成功/失败数。
执行
脚本路径（相对项目根）：skills/shared/scripts/batch_process.py（run -h / list -h）。
# 先预览会处理哪些文件
python skills/shared/scripts/batch_process.py list --dir imgs --type image
# 批量压缩图片到 500KB
python skills/shared/scripts/batch_process.py run --dir imgs --type image --op compress \
--out-dir out -- --max-kb 500
# 批量加水印
python skills/shared/scripts/batch_process.py run --dir imgs --type image --op watermark \
-- --text "@我的账号" --position bottom-right
# 批量视频转竖版 9:16
python skills/shared/scripts/batch_process.py run --dir clips --type video --op aspect \
--out-dir out -- --ratio 9:16 --mode pad
# 批量音频转 mp3（改扩展名用 --ext）
python skills/shared/scripts/batch_process.py run --dir raw --type audio --op convert \
--out-dir out --ext .mp3 -- --bitrate 192k
可用操作（透传给 ops 脚本，<脚本> <op> -h 看参数）
- image（image_ops）：resize / crop / pad / convert / compress / watermark / round / thumbnail
- video（video_ops）：compress / aspect / watermark / speed / gif / frame
- audio（audio_ops）：convert / normalize / denoise / fade / speed / trim
规则
- 先
list预览文件范围，确认无误再run。 --之后的参数原样透传给 ops 脚本；不确定参数先跑单文件版（image-editing 等）验证一次。- 改输出格式用
--ext（如.mp3/.png），否则沿用原扩展名。 - 批处理串行执行（避免高负载）；量大时耐心等，失败文件会单独列出不中断整体。
- 默认输出到
<目录>/batch_out/，不覆盖原文件。
参考来源
复用项目既有确定性脚本（image_ops/video_ops/audio_ops），本 SKILL 只做目录遍历 + 逐文件 委派 + 结果汇总，不重复实现处理逻辑。
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.
- 3d ago First seen · 70 lines · 153 tokens per session scan A 86e85cdbf537
batch-process is a skill published in the GitHub repository ZJU-REAL/Easel (56 stars, last pushed 3d ago), licensed Apache-2.0. It adds 153 tokens to every session and 940 once invoked, about $0.0008 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.
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…