bulk

bulk is a command for coding agents from Smart-AI-Memory/attune-ai. It costs 11 tokens per session (655 once invoked), scanned A, original, Apache-2.0.

A command for sending many API tasks to Anthropic's Batch API, which processes non-urgent work asynchronously within 24 hours.

In plain words
What is it for?
Use it to submit high-volume tasks, check batch progress, wait for completion, and retrieve the results.
Why use it?
It helps reduce API costs when results do not need to arrive immediately and avoids submitting each task separately.

Command

Install

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.

agentmods
npx agentmods add commands/smart-ai-memory/attune-ai/bulk
Clone the repo
git clone --depth 1 https://github.com/Smart-AI-Memory/attune-ai

Wrote 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.

agentmods badge for bulk

README.md
[![agentmods](https://agentmods.dev/badge/commands/smart-ai-memory/attune-ai/bulk.svg)](https://agentmods.dev/commands/smart-ai-memory/attune-ai/bulk)
Your own site
<a href="https://agentmods.dev/commands/smart-ai-memory/attune-ai/bulk"><img src="https://agentmods.dev/badge/commands/smart-ai-memory/attune-ai/bulk.svg" alt="Measured on agentmods" height="20"></a>
Per session 11 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 655 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00011 $0.00655
Opus 5 $0.00005 $0.00328
Sonnet 5 $0.00002 $0.00131
Haiku 4.5 $0.00001 $0.00065

Measured yesterday against content hash 06b83a114e73, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

bulk 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 yesterday.

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.

src/attune/commands/bulk.md · 91 lines

How it starts

The opening of the file, as written. The whole thing — 91 lines — stays where its author put it; the contents beside it link to each section on GitHub.

bulk

Batch API processing — submit tasks for asynchronous execution at 50% cost savings via the Anthropic Batch API.

Batch requests are processed within 24 hours. Use this for non-urgent, high-volume tasks where cost matters more than latency.

Quick Shortcuts

Shortcut Action
/bulk submit <tasks> Submit tasks for batch processing
/bulk status <id> Check status of a running batch
/bulk results <id> Retrieve completed batch results
/bulk wait <id> Wait for a batch to complete

Natural Language

Describe what you need:

  • "submit these files for bulk review"
  • "check my batch status"
  • "get the results from my last batch"
  • "process these tasks in bulk"

CRITICAL: Workflow Execution Instructions

When this command is invoked with arguments, you MUST execute the workflow, not answer ad-hoc.

Shortcut Routing (EXECUTE THESE)

Input Action
/bulk submit Collect tasks, submit via Anthropic Batch API
/bulk status <id> Query batch status and show progress
/bulk results <id> Fetch and display completed results
/bulk wait <id> Poll until batch completes, then show results

Natural Language Routing (EXECUTE THESE)

Pattern Action
"submit", "queue", "process", "bulk" Submit batch
"status", "progress", "check" Check batch status
"results", "output", "completed" Get batch results
"wait", "block", "until done" Wait for completion

IMPORTANT: When arguments are provided, DO NOT just display documentation. EXECUTE the action.

How It Works

  1. Tasks are serialized and sent to the Anthropic Batch API
  2. Processing happens asynchronously (up to 24 hours)
  3. Cost is 50% less than synchronous API calls
  4. Results are retrieved when processing completes

CLI Reference

uv run attune bulk submit --tasks <file>
uv run attune bulk status --id <batch_id>
uv run attune bulk results --id <batch_id>
uv run attune bulk wait --id <batch_id>

Read the full file on GitHub · 91 lines

Changes

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.

  1. yesterday First seen · 91 lines · 11 tokens per session scan A 06b83a114e73

Subscribe to this mod's changes

bulk is a command published in the GitHub repository Smart-AI-Memory/attune-ai (10 stars, last pushed today), licensed Apache-2.0. It adds 11 tokens to every session and 655 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 2026-09-03.