编程

agent-expenditure

试用

Tracks per-agent token usage and flags waste in parallel dispatch

它能做什么

Tracks per-agent token usage and flags waste in parallel dispatch

技能文档

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 CountExpected OverheadGuidance
1-3NegligibleDispatch freely
4-510-15%Acceptable; plan first
6-820-30%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

相关技能

Manages context overflow by handing off to a fresh subagent at 80% usage

21 次安装

Enforces token quota management at session start with conservation and compression checks. Use at the start of every session or before large context loads

22 次安装

Compresses verbose responses by removing filler and framing to save 200-400 tokens

23 次安装

Implements structured usage logging and audit trails for cost and session tracking

21 次安装