Agent Expenditure
- 80 installs
- 325 repo stars
- Updated August 2, 2026
- athola/claude-night-market
Agent expenditure is an agent skill that defines detection criteria for five categories of token waste in parallel agent dispatch workflows.
About
Agent expenditure (waste-signals) is a compact reference skill for solo builders orchestrating parallel agent dispatches in Claude Code–style workflows. It names five waste categories—ghost agents that burn tokens without evidenced findings, redundant readers that re-load the same files, duplicate workers with overlapping reviews, token hogs that exceed median spend without proportional value, and related dispatch inefficiencies—and gives testable criteria rather than vague “use fewer tokens” advice. You invoke it when batching security, performance, or exploration agents and want guardrails before bills spike. It pairs with conserve:agent-expenditure as parent context and treats zero-finding low-risk scans as valid exceptions. The skill is procedural knowledge for reviewers and lead agents: compare medians by task type, require citations (paths, lines), and assign non-overlapping scopes up front. Intermediate complexity; no MCP install—paste into agent context when tuning multi-agent reviews or CI-style agent batches.
- Defines five agent token waste categories with explicit detection rules (ghost agent, redundant reader, duplicate worker
- Ghost agent rule: >1.5× median tokens, <30% median findings, and weak evidence citations
- Redundant reader detection via cross-agent file access logs and overlapping scopes
- Duplicate worker when semantic finding overlap exceeds 50% across agents
- Mitigations: distinct file scopes and separated review dimensions before dispatch
Agent Expenditure by the numbers
- 80 all-time installs (skills.sh)
- Ranked #5,222 of 16,546 AI & Agent Building skills by installs in the Skillselion catalog
- Security screen: LOW risk (skills.sh audit)
- Data as of Aug 5, 2026 (Skillselion catalog sync)
npx skills add https://github.com/athola/claude-night-market --skill agent-expenditureAdd your badge
Show developers this skill is listed on Skillselion. Paste this into your README.
| Installs | 80 |
|---|---|
| repo stars | ★ 325 |
| Security audit | 3 / 3 scanners passed |
| Last updated | August 2, 2026 |
| Repository | athola/claude-night-market ↗ |
What it does
Spot wasted tokens when you dispatch multiple coding agents in parallel and need clear pass/fail criteria before scaling runs.
Who is it for?
Best when you're batching parallel code review or exploration agents and want objective waste labels tied to tokens, findings count, and evidence quality.
Skip if: Single-agent chats with no parallel dispatch logs, or runs where you have not defined task-type medians and agent roles yet.
When should I use this skill?
Auditing parallel agent dispatches for token efficiency, overlapping scopes, or weakly evidenced outputs.
What you get
You label each run against concrete waste signals and adjust scopes and review dimensions before the next dispatch.
- Waste classification per agent run (ghost, redundant reader, duplicate worker, token hog, etc.)
- Scope and dimension adjustments for the next dispatch wave
By the numbers
- 5 categories of agent token waste defined with detection criteria
- Ghost agent threshold: >1.5× median tokens and <30% median findings count
- Duplicate worker when findings overlap >50% semantically across agents
Files
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.mdfor the 4+ agent
planning requirement
conserve:token-conservationfor session-level token budgetingconjure:agent-teamsfor dispatch coordination
Waste Signal Definitions
1. Ghost Agent
An agent that consumes tokens without producing actionable output.
Detection criteria (ALL must be true):
- Token expenditure >1.5x median for task type
- Findings count <30% of median for agent type
- Findings lack evidence citations (no code refs, no line numbers, no
file paths)
Exception: Zero-finding results from low-risk scans (e.g., security audit of already-linted code) are valid, not waste.
2. Redundant Reader
An agent that re-reads files already loaded by another agent in the same dispatch.
Detection: Compare file access logs across agents. If agent B reads the same files as agent A and produces overlapping findings, agent B's reads were redundant.
Mitigation: Assign distinct file scopes to each agent before dispatch.
3. Duplicate Worker
An agent whose findings overlap >50% with another agent's output.
Detection: Compare finding descriptions across agents. Semantic overlap (same issue described differently) counts as duplication.
Mitigation: Assign distinct review dimensions (e.g., one agent reviews security, another reviews performance).
4. Token Hog
An agent that exceeds 3x the median token count for its task type without proportional output.
Detection: Compare agent token usage to historical median for the same task type. If output quality or quantity does not justify the excess, flag as waste.
Mitigation: Set token budgets per agent. Use haiku for well-scoped tasks (see conjure cheapest-capable model selection).
5. Coordination Overhead
When N > 5 agents and shared-file conflicts exceed 20% of total agent runtime.
Detection: Count concurrent Read/Write operations on the same file by different agents, as percentage of total runtime.
Mitigation: Reduce agent count, use git worktrees for isolation, or assign non-overlapping file scopes.
Related skills
Setup Matt Pocock SkillsScaffold the per-repo configuration that Matt Pocock’s engineering agent skills rely on so they understand the issue tracker, triage labels, and domain documentation la495k196k
Lark AppsConnect Claude, Cursor or custom agents directly to Lark (Feishu) for messaging, document automation, approval workflows and enterprise data access.402k
CavemanSlash token usage by roughly 75% while keeping every technical detail intact when working with Claude Code, Cursor or similar agents.391k94.7k
Lark Skill MakerQuickly turn any Lark/Feishu OpenAPI call or multi-step workflow into a reusable agent skill with its own SKILL.md.386k16k
Running Claude Code Via Litellm CopilotRun Claude Code at a fraction of the cost by routing requests through LiteLLM to the GitHub Copilot Chat API.270k72
Codex PetGenerate a complete Codex Pet spritesheet and metadata from one reference image without needing an OpenAI key or Codex Pro.246k10How it compares
Use as a rubric for dispatch hygiene, not as a substitute for pytest coverage or static security scanners.
FAQ
Who is agent-expenditure for?
Developers and small teams running multiple Claude, Cursor, or Codex agents in one session who need shared vocabulary for wasted spend.
When should I use agent-expenditure?
During Build when designing agent-tooling playbooks, during Ship when triaging overlapping review outputs, and during Operate when monitoring token budgets after parallel tasks.
Is agent-expenditure safe to install?
It is documentation-only criteria with no shell or network hooks; review the Security Audits panel on this Prism page before adding any repo skill to your agent.