PulseAugur
EN
LIVE 22:10:20

Claude Code users track agent usage to prune unused definitions · 2 sources tracked

By PulseAugur Editorial · [2 sources] ·

Developers are creating systems to track agent usage within the Claude Code environment to identify and prune unused agents. These systems leverage Claude Code's Stop hook, which triggers upon session completion and provides a transcript path. By parsing this transcript, developers can log agent invocations, including details like agent type, description, and duration. A daily summary script then analyzes this log to report on agent usage over 7-day and 30-day windows, highlighting agents that have not been invoked and can potentially be deleted. AI

IMPACT Enables better management of custom agent definitions within LLM development environments.

RANK_REASON The cluster describes a custom tooling solution built by a user for a specific environment (Claude Code), rather than a release from the core AI provider.

Read on dev.to — Claude Code tag →

AI-generated summary · Google Gemini · from 2 sources. How we write summaries →

Claude Code users track agent usage to prune unused definitions · 2 sources tracked

How we ranked this

Signal score
0 / 100
Composite score across the factors below. Higher = stronger signal that this story matters right now.
Newsworthiness bucket
Tool
The cluster describes a custom tooling solution built by a user for a specific environment (Claude Code), rather than a release from the core AI provider.
Source corroboration
2 independent sources
Multiple independent publishers reporting the same story raises confidence that it's real and newsworthy.
Topics
product, infra
Editorial topic classification. Feeds into how the story surfaces on /topic/<slug> hub pages and into the per-entity coverage mix.
AI-industry relevance
High
Clearly on-topic for AI-industry coverage.
Story freshness
51 days old
Aged out of breaking-news scoring windows; ranking reflects the durable signal from the full source set.

Full methodology in our editorial standards.

COVERAGE [2]

  1. dev.to — Claude Code tag TIER_1 English(EN) · Lily ·

    Log Every Agent Invocation: Building Usage Analytics with Claude Code's Stop Hook and transcript_path

    <p>In the previous post in my "Claude Code environment" series, <a href="https://zenn.dev/bokuwalily/articles/zombie-agent-pruner" rel="noopener noreferrer">automatically pruning zombie agents</a>, I wrote about finding agents that are defined but never used. But where did those …

  2. dev.to — LLM tag TIER_1 English(EN) · Lily ·

    Hunting Down Zombie Agents: Logging Subagent Usage with a Claude Code Stop Hook

    <p>Quick question: how many of the subagents you've defined in <code>~/.claude/agents/</code> have actually been called this month? I couldn't have told you — until I started measuring, and this morning's tally revealed <strong>44 agents that hadn't been invoked even once in 30 d…

RELATED ENTITIES

RELATED TOPICS