Stats
Actions
Tags
Help us improve
Share bugs, ideas, or general feedback.
From conserve
Tracks per-agent token usage in parallel workflows, flags waste like duplication, and checks if spend matches value. Use after multi-agent dispatches for efficiency review.
npx claudepluginhub athola/claude-night-market --plugin conserveHow this skill is triggered — by the user, by Claude, or both
Slash command
/conserve:agent-expenditureThe summary Claude sees in its skill listing — used to decide when to auto-load this skill
- After parallel agent dispatch completes
Tracks token usage and estimates agent session costs. Use when monitoring spend, approaching budget limits, or generating cost reports.
Designs observability for multi-agent systems with per-agent metrics, aggregate stats, agent cards, and event streams to monitor execution, track costs, log activities, and debug workflows.
Audits token waste across agent systems (Claude Code, Codex, OpenClaw, Hermes, OpenCode). Detects idle burns, model misrouting, config bloat with dollar savings estimates. Use for multi-agent cost audits spending $2-5/day.
Share bugs, ideas, or general feedback.
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.
After parallel agent runs, evaluate:
If 2+ questions answer no, reduce agent count in future dispatches of the same type.
See modules/waste-signals.md for the 5 waste signal categories and
detection criteria.
.claude/rules/plan-before-large-dispatch.md for the 4+ agent
planning requirementconserve:token-conservation for session-level token budgetingconjure:agent-teams for dispatch coordination