codex-usage-tracker Skill
codex-usage-tracker is a Python AI agent skill for Codex, ChatGPT with uvx/pip, git clone. MCP & local dashboard for understanding where your Codex tokens and usage credits are going.
How to use codex-usage-tracker Skill
Install or run
python -m pip install --user pipx
python -m pipx ensurepath
pipx install codex-usage-tracking
codex-usage-tracker setup
codex-usage-tracker serve-dashboard --openClient configuration
{
"schema": "codex-usage-visualization/v1",
"id": "mcp-token-waste",
"title": "Large-input, low-output candidates",
"description": "Uncached input and output tokens for the strongest loaded aggregate candidates.",
"state": {
"kind": "ready"
},
"scope": {
"label": "1 aggregate evidence rows",
"rowCount": 1,
"historyScope": "active"
},
"freshness": {
"generatedAt": "2026-07-01T12:00:00Z",
"sourceRevision": "codex-usage-tracker-reports-pack-v1"
},
"caveats": [
"Large uncached input with little output is a candidate signal, not proof that the context was unnecessary.",
"Only aggregate call fields are included; inspect a linked call explicitly for local context."
],
"accessibility": {
"summary": "Large-input, low-output candidates contains 1 aggregate evidence rows.",
"details": [
"Large uncached input with little output is a candidate signal, not proof that the context was unnecessary.",
"Only aggregate call fields are included; inspect a linked call explicitly for local context."
],
"keyboardInstructions": "Use left and right arrow keys to inspect values, or switch to the table for exact data."
},
"table": {
"caption": "Large-input, low-output candidates evidence",
"columns": [
{
"field": "label",
"label": "Call",
"type": "category",
"align": "left"
},
{
"field": "uncached_input_tokens",
"label": "Uncached input",
"type": "number",
"align": "right",
"unit": "tokens"
},
{
"field": "output_tokens",
"label": "Output",
"type": "number",
"align": "right",
"unit": "tokens"
},
{
"field": "total_tokens",
"label": "TotCompatible clients
What is codex-usage-tracker Skill?
codex-usage-tracker is a Python AI agent skill for Codex, ChatGPT with uvx/pip, git clone. MCP & local dashboard for understanding where your Codex tokens and usage credits are going. This profile combines repository metadata with install, compatibility, and usage signals so developers can quickly decide whether it fits their agent workflow before opening the source repository.
Automated repository signals based on public metadata such as recency, license, installation evidence, and adoption. These are not a security audit or endorsement.
Key capabilities
- Reusable instructions support
- Includes SKILL.md support
- Shell commands support
- Browser use support
- Spreadsheet work support
- Document generation support
- OpenAI provider support
Technical details
Install or run codex-usage-tracker using uvx/pip. Check douglasmonsky/codex-usage-tracker for the latest setup command.
- Built for Python
- Built for Node.js
- Built for Rust
- Install or run with uvx/pip
- Install or run with git clone
- Works with Codex
- Works with ChatGPT
- Uses SSE transport
Requirements and access
Security and permissions
Review permissions before connecting any MCP server to an agent. Pay special attention to whether it can read local files, write data, call external services, or perform destructive actions.
When to use codex-usage-tracker Skill
- Use it for reusing agent instructions, scripts, and references.
- Use it for agent skills workflows.
- Use it for coding workflows.
- Use it for data workflows.
- Use it for codex users.
Built with
Explore related resources
Frequently asked questions
What is codex-usage-tracker?
codex-usage-tracker is a Python AI agent skill for Codex, ChatGPT with uvx/pip, git clone. MCP & local dashboard for understanding where your Codex tokens and usage credits are going.
Who is codex-usage-tracker best for?
codex-usage-tracker is best for reusing agent instructions, scripts, and references, agent skills workflows, coding workflows, data workflows, codex users.
How do I install codex-usage-tracker?
Install or run codex-usage-tracker using uvx/pip. Check codex-usage-tracker for the latest setup command.
Is codex-usage-tracker actively maintained?
codex-usage-tracker may need a closer maintenance check before production use.
Auto-fetched from GitHub.