PulseAugur
EN
LIVE 19:13:03

New tool `agent-cost` separates AI usage from task attribution

By PulseAugur Editorial · [1 sources] ·

The author developed a tool called `agent-cost` to address the limitations of existing usage trackers for AI models like Claude Code and Codex. Unlike broader CLIs or dashboards, `agent-cost` focuses on providing auditable, machine-readable facts about AI usage directly from local logs, without network calls during runtime. This approach separates observable session usage from the separate claim of task attribution, preventing the inaccurate apportionment of costs based solely on elapsed time or commit counts. AI

IMPACT Provides a more granular and auditable method for tracking AI model costs, separating usage from task attribution.

RANK_REASON The item describes a new software tool for tracking AI model usage.

Read on dev.to — Claude Code tag →

AI-generated summary · Google Gemini · from 1 sources. How we write summaries →

New tool `agent-cost` separates AI usage from task attribution

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 item describes a new software tool for tracking AI model usage.
Source corroboration
Single-source cluster
Only one publisher covered this so far. Single-source stories can still rank when the publisher is high-authority, but they lack cross-source corroboration.
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
46 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 [1]

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

    I Could Measure Claude and Codex Usage. I Still Couldn't Honestly Assign It to a Task.

    <p>Once you use Claude Code or Codex for real work, a total usage number stops being enough. You want to know which change consumed it.</p> <p>I did not build <code>agent-cost</code> because I had missed the existing token and cost trackers. I knew about multi-agent reporting CLI…

RELATED ENTITIES

RELATED TOPICS