DEV Community: 黑暗森林

Batch Worker — 100 AI Agents in Parallel, Zero-Token Cleanup

黑暗森林 — Mon, 22 Jun 2026 22:21:25 +0000

Batch Worker: 100 AI Agents Running in Parallel

The Problem

Auditing a codebase takes hours when you go file by file. Content creation, search, fixes — every task is bottlenecked by sequential execution.

The Solution

Batch Worker is an OpenClaw skill that dispatches up to 100 AI agents in parallel with staggered launch to avoid rate limits.

Three-Step Pipeline

1. ai_planner -> Analyze project, generate audit plan with 100 soldier prompts
2. core_taskPipeline -> Dispatch 100 agents in staggered batches (10/batch x 20ms)
3. ai_collector -> Collect reports, deduplicate, rank by severity — zero LLM tokens

104 Audit Dimensions

Domain	Dimensions
Security	42 (injection, XSS, CSRF, auth, encryption...)
Architecture	12 (boundaries, cycles, idempotency, resilience)
Performance	12 (N+1, caching, memory leaks, lock contention)
Code Quality	10 (complexity, error handling, dead code)
Language-specific	10 (Promise, async, EventEmitter, Stream)
DevOps	8 (observability, CI/CD, config, containers)
Compliance	4 (data privacy, audit trail, accessibility)

83 Task Types

From code audit to content creation, search to fix, translation to analysis — batch-worker handles them all.

Zero-Token Cleanup

After 100 agents finish, ai_collector automatically extracts JSON findings, deduplicates, and merges — using zero LLM tokens. Pure script, no hallucination.

GitHub: https://github.com/haoyun18881-beep/batch-worker
Docs: https://haoyun18881-beep.github.io/batch-worker/

QA Logger — OpenClaw Plugin to Turn AI Chats into a Searchable Diary

黑暗森林 — Mon, 22 Jun 2026 22:21:00 +0000

QA Logger: Turn Every AI Chat Into a Searchable Diary\n\n## The Problem\n\nOpenClaw sessions generate tons of conversations. They're stored as raw JSON — great for machines, terrible for humans to browse or search.\n\n## The Solution\n\nQA Logger is a lightweight OpenClaw plugin that converts every Q&A pair into a human-readable diary file, organized by date.\n\n`\n2026-06-19 17:30:00\n\nUser(Q):\nWhat's the weather?\n\nAI(A):\nSunny, 25°C\n`\n\n## Why It Matters\n\n- Better Vector Search — Natural language diaries produce much better semantic matches than raw JSON\n- Pairs with memory-keeper — Use both together for an unstoppable memory pipeline\n- Zero Config — Clone, drop into plugins, restart, done\n\n## Install\n\n`ash\ngit clone https://github.com/haoyun18881-beep/qa-logger.git\n# Drop into your OpenClaw plugins directory\n# Restart Gateway\n# Enable in plugin panel\n`\n\n## Compatible\n\nOpenClaw 5.27 through 6.x. Tested on Windows, macOS, Linux.\n\nGitHub: https://github.com/haoyun18881-beep/qa-logger\nDocs: https://haoyun18881-beep.github.io/qa-logger/

memory-keeper: Stop paying for empty context. 3-tier archive for 99.9% DeepSeek cache hit.

黑暗森林 — Mon, 22 Jun 2026 20:20:17 +0000