360 Secure SkillHub
360 安全技能中心

agent-expenditure

面向并行 agent 分派的事后审查技能:依据 Brooks 定律评估协调开销(同一文件并发读写占运行时的比例),提供 4 项审查清单和 5 类浪费信号,并给出是否减少 agent 数量的建议;不执行监控脚本,也不做会话级 token 预算。

athola
athola
热度 62.87
最近更新 2026-08-26 21:10:14
分类:数据依赖:纯提示词应用场景:报告撰写 / 工作流

安装技能

复制下面的话术发给你的 Agent,它会通过 secure-skills 检索并安装该技能。

执行命令安装此 skill: npx secure-skills-cli add nm-conserve-agent-expenditure
Metadata
name
agent-expenditure
description
Tracks per-agent token usage and flags waste in parallel dispatch
version
1.9.8
triggers
["token-waste","agent-coordination","brooks-law","parallel-dispatch","evaluating parallel agent efficiency or after a multi-agent run"]
metadata
{"openclaw":{"homepage":"https://github.com/athola/claude-night-market/tree/master/plugins/conserve","emoji":"🦞"}}
source
claude-night-market
source_plugin
conserve

Night Market Skill — ported from claude-night-market/conserve. For the full experience with agents, hooks, and commands, install the Claude Code plugin.

Agent Token Waste Monitoring

When To Use

  • After parallel agent dispatch completes
  • When evaluating whether to increase agent count
  • During retrospectives on agent-heavy workflows
  • When plan-before-large-dispatch rule triggers

When NOT To Use

  • Single-agent workflows (no coordination overhead)
  • During active agent execution (post-hoc analysis)
  • For token budgeting (use token-conservation instead)

Brooks's Law for Agents

Dispatching more agents does not always help. Coordination overhead grows with agent count:

Agent Count Expected Overhead Guidance
1-3 Negligible Dispatch freely
4-5 10-15% Acceptable; plan first
6-8 20-30% Monitor closely
9+ 30%+ Likely counterproductive

Coordination overhead is measured as shared-file conflicts: concurrent Read/Write operations on the same file by different agents, as a percentage of total agent runtime.

Post-Dispatch Review Checklist

After parallel agent runs, evaluate:

  1. Did each agent produce unique findings?
  2. Was total token expenditure proportional to value?
  3. Did any agent duplicate another's work?
  4. Would fewer agents have produced the same result?

If 2+ questions answer no, reduce agent count in future dispatches of the same type.

Waste Signals

See modules/waste-signals.md for the 5 waste signal categories and detection criteria.

Cross-References

  • .claude/rules/plan-before-large-dispatch.md for the 4+ agent planning requirement
  • conserve:token-conservation for session-level token budgeting
  • conjure:agent-teams for dispatch coordination