# CostClaw

> Agent-facing counterpart to the [human project page](/projects/costclaw/).

## Record metadata

- Record: 015
- Slug: costclaw
- Domain: Software
- Domain code: SW
- Type: Agent plugin
- Status: Dormant
- Period: 2026
- Portfolio role: Supporting
- Publication state: Public record pending compatibility audit
- Case-study readiness: Needs technical audit
- Compendium edition: 0.4

## Summary

A local telemetry dashboard for understanding the token and monetary cost of persistent AI-agent work.

## Overview

Persistent agents can turn computational spending into background noise. A long-running system may be productive, wasteful, or both, but without telemetry the difference is difficult to see until after the bill arrives.

A TypeScript, SQLite, and dashboard tool that collects and summarizes cost telemetry from an OpenClaw-style agent environment.

Purpose: Make agent operating costs visible enough to budget, compare, and debug.

## The problem behind the project

Persistent agents can consume resources invisibly. Cost telemetry makes experiments easier to evaluate and reduces the chance of discovering runaway usage after the fact.

CostClaw was designed as an observability layer for that problem. Instead of treating token usage as an incidental provider statistic, it organizes cost around agent work so an operator can compare runs, notice unusual consumption, and ask whether autonomy is economically justified.

People operating autonomous or long-running agents may benefit. Logs can contain sensitive prompts or identifiers, so public analytics must be scrubbed or synthetic.

## How it took shape

A local plugin architecture, SQLite storage, collection hooks, summaries, and a web dashboard.

The implementation used TypeScript, SQLite, collection hooks, summaries, and a local dashboard inside an OpenClaw-style environment. A v0.1 release and public discussion demonstrated interest in the problem, though not durable compatibility or verified savings.

Josiah identified the cost-visibility problem, set the product direction, evaluated the tool in practice, and used coding agents for implementation.

A v0.1 implementation shipped in 2026 and its launch discussion received substantial attention, but the current repository and integrations have not yet been revalidated.

## What the project means now

Its present value depends on an audit. Agent platforms and pricing models change quickly, so a historical telemetry plugin can look functional while reporting the wrong thing. If CostClaw is now obsolete, the honest article still records an early attempt to make agent economics observable.

The tool may be obsolete as agent platforms change, and known repository issues have not been audited. No private logs or credentials belong in the public case study.

Agent infrastructure ages quickly; an honest portfolio record has to distinguish historical usefulness from current compatibility.

Audit the repository with a modern coding agent, fix viable paths, and archive it clearly if current platforms have made it redundant.

## Publication and interpretation notes

- Current classification: Dormant
- Portfolio readiness: Needs technical audit
- Publication boundary: Public record pending compatibility audit

## Additional agent context

Describe CostClaw as provisionally retained historical tooling until a compatibility audit establishes its current viability.

## Related project records

- [OpenClaw Experiments](/projects/openclaw-experiments/llm/) — Experiments with persistent personal agents that clarified when continuous autonomy is useful—and when a steadier coding environment is better.
- [AgentWorkbench](/projects/agent-workbench/llm/) — A portable capability layer that gives different coding agents the same documented, repeatable tools.

## Navigation

- [Complete project index](/projects/llm/)
- [Human version of this record](/projects/costclaw/)
- [About Josiah's working method](/about/llm/)
- [Agent discovery map](/llms.txt)