Name: agentcents
Author: labham-llc

What can you do with agentcents?

agentcents — LLM cost consulting skill for Claude

A Claude Skill that turns Claude into a neutral LLM cost advisor: estimate what any call or agent workflow will cost across candidate models, get the cheapest model that clears the task's capability bar, and see the comparison as a Mermaid diagram — with honest ranges, never false point estimates.

Works two ways:

Consult mode (no install): answers from a bundled, hand-verified snapshot of current model prices and Intelligence Index scores.
Live mode: if the agentcents proxy is running locally, the skill uses your real ledger — calibrated forecasts, spend, and accuracy instead of priors.

Install

Claude.ai / Desktop: Settings → Capabilities → Skills → Add → upload this folder (or the packaged .skill).

Claude Code: /plugin marketplace add labham-llc/agentcents-skill then /plugin install agentcents@labham-skills

Then just ask things like:

what would it cost to classify ~500 support emails a day, about 200 tokens each?

I'm building a 5-step research agent — which model should each step use?

What's in the box

SKILL.md                 — the consulting method (measure, range, bar, pick, flag instability)
assets/pricing.json      — price + capability snapshot (see _meta.verified_utc)
references/local-api.md  — live-mode reference for a locally running agentcents

Snapshot verified: 2026-07-15 (see _meta.verified_utc) — refreshed with each agentcents release.

The product behind it

agentcents is a local proxy that meters, forecasts, and budget-enforces LLM API calls — and grades its own forecasting accuracy on a calibration page. pip install agentcents. The skill is free; so is the agentcents free tier.

Install

Add agentcents to your client. Pick the one you use.

claude mcp add agentcents -- uvx agentcents

codex mcp add agentcents -- uvx agentcents

amp mcp add agentcents -- uvx agentcents

{
  "mcpServers": {
    "agentcents": {
      "command": "uvx",
      "args": [
        "agentcents"
      ]
    }
  }
}

Add to `claude_desktop_config.json`, then restart Claude Desktop.

{
  "mcpServers": {
    "agentcents": {
      "command": "uvx",
      "args": [
        "agentcents"
      ]
    }
  }
}

Add to `~/.cursor/mcp.json`, or `.cursor/mcp.json` for a single project.

code --add-mcp '{"name":"agentcents","command":"uvx","args":["agentcents"]}'

Or add the block manually to `.vscode/mcp.json` under `servers`.

{
  "mcpServers": {
    "agentcents": {
      "command": "uvx",
      "args": [
        "agentcents"
      ]
    }
  }
}

Add to `~/.codeium/windsurf/mcp_config.json`.

{
  "mcpServers": {
    "agentcents": {
      "command": "uvx",
      "args": [
        "agentcents"
      ]
    }
  }
}

Add to `cline_mcp_settings.json` via the MCP Servers panel.

{
  "mcpServers": {
    "agentcents": {
      "command": "uvx",
      "args": [
        "agentcents"
      ]
    }
  }
}

Add to `~/.gemini/settings.json`.

{
  "mcpServers": {
    "agentcents": {
      "type": "local",
      "command": "uvx",
      "args": [
        "agentcents"
      ],
      "tools": [
        "*"
      ]
    }
  }
}

Add to `~/.copilot/mcp-config.json`, or run `/mcp add` inside the CLI.

{
  "context_servers": {
    "agentcents": {
      "command": {
        "path": "uvx",
        "args": [
          "agentcents"
        ]
      }
    }
  }
}

Add to your Zed `settings.json`.

uvx agentcents

Run `goose configure`, choose **Add Extension → Command-line Extension**, and paste this command.

Score

39 / 100

Incomplete

Documentation17/25
Maintenance16/25
Trust6/20
Capability0/15
Install experience12/15

Documents what it does and how to connect
Has a resolvable package or endpoint
Exposes at least one tool, prompt or resource
README has substantive content
Includes a code example
Documents its configuration
Mentions credentials or security posture
Last commit 38 days ago
Has a release history
Repository is not archived
No licence detected
Namespace verified in the official MCP registry
Claimed by its owner
Published under an organisation
0 tool(s) documented
Provides prompt templates
Provides resources
12 documented install method(s)
Published to a package registry
Offers a hosted endpoint — no local install

Read the full rubric →

Version history

Versions	Published
1.1.3Latest	Jul 24, 2026