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/itallstartedwithaidea/agent-skills/batch-processingnpx skills add itallstartedwithaidea/agent-skills --skill batch-processinggit clone --depth 1 https://github.com/itallstartedwithaidea/agent-skillsWhat 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 | $0.00024 | $0.01606 |
| Opus 5 | $0.00012 | $0.00803 |
| Sonnet 5 | $0.00005 | $0.00321 |
| Haiku 4.5 | $0.00002 | $0.00161 |
Grade A, and why
batch-processing 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 — 183 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Batch Processing
Part of Agent Skills™ by googleadsagent.ai™
Description
Batch Processing enables parallel AI task execution with progress tracking, error handling, rate limiting, and result aggregation. The agent processes large collections of items—documents, images, code files, API requests—through AI pipelines concurrently, managing throughput, failures, and partial results without losing work.
Single-item AI processing is straightforward; batch processing at scale introduces failures, rate limits, memory constraints, and the need for resumability. This skill handles these production realities: configurable concurrency limits, exponential backoff on rate limit errors, checkpoint-based resumability after crashes, and structured progress reporting that shows exactly which items succeeded, failed, or are pending.
The skill supports both homogeneous batches (same operation on every item) and heterogeneous batches (different operations routed by item type). Results are aggregated into structured reports with per-item status, timing, and error details. Failed items are automatically retried with backoff, and permanently failed items are collected into a dead-letter queue for manual inspection.
Use When
- Processing hundreds or thousands of items through an AI pipeline
- Translating, summarizing, or classifying large document collections
- Generating embeddings for a corpus of documents
- Running code analysis across an entire repository
- Batch-generating images, descriptions, or metadata
- Any task that processes items sequentially but could benefit from parallelism
How It Works
graph TD
A[Input Batch: N Items] --> B[Load Checkpoint: Resume if Exists]
B --> C[Partition into Work Chunks]
C --> D[Parallel Workers: Concurrency Limit]
D --> E[Worker 1: Process Item]
D --> F[Worker 2: Process Item]
D --> G[Worker K: Process Item]
E --> H{Success?}
F --> H
G --> H
H -->|Yes| I[Record Result]
H -->|Rate Limited| J[Backoff + Retry]
H -->|Failed| K[Retry Queue]
J --> D
K --> L{Retries Exhausted?}
L -->|No| D
L -->|Yes| M[Dead Letter Queue]
I --> N[Save Checkpoint]
N --> O[Progress Report]
O --> P{All Done?}
P -->|No| D
P -->|Yes| Q[Final Aggregation Report]
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 · 183 lines · 24 tokens per session scan A ac15cc695ff9
batch-processing is a skill published in the GitHub repository itallstartedwithaidea/agent-skills (35 stars, last pushed 4mo ago), licensed MIT. It adds 24 tokens to every session and 1,606 once invoked, about $0.0001 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
update-saasmail
Sync the local saasmail repo with the latest upstream changes from https://github.com/choyiny/saasmail. Use this skill whenever the user wants to update saasmail, pull upstream changes, sync with upstream, rebase on upstream, get the latest saasmail, or says "/update-saasmail". Handles adding the upstream remote if…
story-html-publisher
Final step of the AI Storybook pipeline. Consolidates the scenes, images, and per-scene audio into ONE self-contained HTML storybook — a swipe/tap player with every image and audio clip embedded as base64 so the single file works offline and can be shared as-is. Reads {slug}scenes.json, {slug}images.json, and…
tracking-health
Preventive audit of conversion tracking across all configured ad platforms — Meta pixels + CAPI, Google Ads conversion actions, and final-URL tracking-parameter consistency on every platform — with a GA4 cross-check. Use when the user asks to check tracking, audit conversion measurement, verify pixels / tags, check…
learn
Save a marketing diagnosis insight to the pro-diagnosis knowledge base so it is applied in future operations across all platforms. Use when the user runs /learn, explicitly teaches the agent a marketing insight, corrects the agent's analysis, or asks to remember/record an operational learning for next time. Also use…
sealeap-amazon-product-targeting
Research, diagnose, and draft Amazon Ads ASIN and category product-targeting plans that complement keyword targeting, including audience expansion, competitor and category traffic, cross-sell, upsell, self-defense, negative targeting, placement analysis, and single-variable experiments. Use for 商品投放, ASIN 定向, 品类定向…
weekly-report
Generate a weekly summary report across all platforms. Use when the user asks for a weekly report, summary, recap, end-of-week review, or weekly digest. Also use when the user asks in Japanese (週次レポート / 今週のまとめ / 週報を作成して).