Skip to content
Agentmart
Submit a tool

cost-report

Show AI/LLM spending, budget usage, and operational cost metrics.

Skill by Glad-Labs

IndexedApache-2.0★ 6
Write a review

Install

Works with Claude Code, Claude apps, Codex, Cursor, Gemini CLI, GitHub Copilot, VS Code, OpenCode, Goose, Windsurf. Read the repository before you give any tool access to your data.

npx agentmarket install skill/glad-labs-cost-report

Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.

Get the weekly diff

The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.

We use your email only for this newsletter. Privacy

About

Show AI/LLM spending, budget usage, and operational cost metrics. Use when the user says "how much have we spent", "cost report", "show costs", "budget status", or "spending breakdown".

Use cases: documents, ml, finance

Reviews

Write a review

No reviews yet. Installed it? Reviews come from verified installers only. How reviews work

Permissions

What this skill can do and what it asks for, from its SKILL.md and code. Checked Oct 25, 2026.

Tools
No tools found
Secrets
None asked for
Install scripts
None found
Runs as
Shell scripts

Network hosts it talks to 1

  • codeload.github.com · found in install command

Files it touches

  • ~/.claude/skills/cost-report

What's inside

Skill name
cost-report
Description
Show AI/LLM spending, budget usage, and operational cost metrics. Use when the user says "how much have we spent", "cost report", "show costs", "budget status", or "spending breakdown".
License
Apache-2.0
Instructions
31 lines in SKILL.md · view on GitHub

Before installing

  • Ships executable scripts

Files (2)

  • SKILL.md
  • run.sh · scripts/

SKILL.md (first lines)

# Cost Report

Shows Glad Labs pipeline spending and budget consumption by combining two API endpoints:

- `GET /api/metrics/costs/budget` — daily/monthly spend vs. configured limits
- `GET /api/metrics/operational` — task counts and throughput metrics that indirectly reflect cost

Costs are primarily electricity for local GPU inference (Ollama + image-gen on RTX 5090).
Per-token "cost" is calculated from GPU power draw × duration × `electricity_rate_kwh`
(currently $0.2552/kWh, Rhode Island residential).

## Usage

```bash
scripts/run.sh                # Full report (budget + operational)
scripts/run.sh budget         # Budget status only
scripts/run.sh operational    # Operational metrics only
```

## Parameters

None.

## Output

- **Budget**: month-to-date spend, monthly limit, daily spend, daily limit, headroom left.
- **Operational**: pending / in_progress / awaiting_approval / failed task counts, worker running status, last-run timestamps.

The two endpoints are independent — budget shows money, operational shows throughput. Read them together to answer "are we on track this month and is the worker actually doing anything".

From Glad-Labs/poindexter, Apache-2.0.

More from Glad-Labs/poindexter

Signals

Stars
6
Forks
2
Open issues
31
Last commit (this folder)
Jul 26, 2026 (3 months ago)
Last release
Oct 21, 2026 (7 days ago)

From GitHub (fetched Oct 24, 2026).

Details

License
Apache-2.0
Repository
github.com/Glad-Labs/poindexter
Website
www.gladlabs.io
First seen
Oct 24, 2026
Last checked
Oct 24, 2026
Source
GitHubgithub-graphql

More from Glad-Labs

Cite this page

cost-report skill. Agent Mart. https://agentmart.dev/skills/glad-labs-cost-report (last updated 2026-10-24)