codex-usage-tracker — Claude Code plugin: install and use
codex-usage-tracker is a Claude Code plugin that reads local Codex session logs for token summaries, session details, CSV exports, and dashboards.
MIT ★ 1,596 updated 2026-10-29
/plugin marketplace add hashgraph-online/awesome-codex-plugins
/plugin install codex-usage-tracker@awesome-codex-pluginsWhat codex-usage-tracker does
codex-usage-tracker turns local Codex session metadata into MCP results for aggregate usage summaries, session-level inspection, CSV export, and dashboard generation. It works with evidence from local logs rather than a hosted usage feed.
The runtime needs the Python package codex-usage-tracking==0.28.0 installed through pipx. Add the plugin from the Claude Code marketplace, then start a fresh task so the new MCP tool catalog is discovered. Its supported runtime uses SQLite; the replacement runtime does not open or migrate the old database.
What it helps with
- summarize token use across local Codex sessions
- inspect one session and its tool calls
- export Codex usage records as CSV
- generate a dashboard from session logs
Example prompts for the agent
- Summarize Codex token usage across my recent local sessions.
- Show the details and tool calls for this Codex session.
- Export the Codex usage data to CSV and generate a dashboard.
How to install codex-usage-tracker
Plugin marketplace
/plugin marketplace add hashgraph-online/awesome-codex-plugins/plugin install codex-usage-tracker@awesome-codex-pluginsStep by step, with commands for each platform: Claude Code plugins: marketplaces, installing, and building your own
Questions about codex-usage-tracker
How do I install codex-usage-tracker in Claude Code?
Run /plugin marketplace add hashgraph-online/awesome-codex-plugins, then /plugin install codex-usage-tracker@awesome-codex-plugins. Start a fresh Claude Code task after installation.
What does codex-usage-tracker do?
It reads local Codex session metadata through MCP tools and produces aggregate summaries, session details, CSV exports, and dashboards.
What does codex-usage-tracker need to run?
It needs the Python package codex-usage-tracking==0.28.0 installed with pipx, plus local Codex session logs. A fresh task is required after installation so Claude Code discovers the plugin tool catalog.
Source text
codex-usage-tracker · MIT
# Codex Usage Tracker [](https://pypi.org/project/codex-usage-tracking/) [](https://pypi.org/project/codex-usage-tracking/) [](https://github.com/douglasmonsky/codex-usage-tracker/actions/workflows/ci.yml) [](LICENSE) Codex Usage Tracker is a local usage-data product for answering questions about how Codex work consumes tokens, time, tools, allowance, credits, and cost. It turns local session metadata into exact, bounded facts and stable evidence that an agent can explore and explain. ## Current release and next direction Version 0.28.0 is the current public release. Its six-tool MCP surface, Evidence Console, and SQLite kernel remain supported while the replacement is qualified. The next product is a clean, agent-first kernel rather than a larger dashboard: - fast recent-history setup with explicit 24-hour through all-time coverage; - incremental reuse on every later invocation; - exact session, turn, call, tool, resource, allowance, token, credit, and cost facts; - compact named queries and stable evidence selectors; - agent-owned interpretation instead of server-authored narrative findings; - installed Codex qualification measured for latency, MCP calls, response bytes, model tokens, accuracy, and usefulness. The 0.28 code remains a frozen oracle during the rewrite and is removed before the clean replacement release. The new runtime does not migrate or open its database. Start with the [documentation authority](docs/INDEX.md), read the [product direction](docs/decisions/PRODUCT_DIRECTION.md), or follow the [clean-cutover roadmap](docs/roadmap/AGENT_FIRST_CLEAN_CUTOVER.md). Progress is tracked in the [checkbox ledger](docs/roadmap/TASK_PACKETS.md), with one complete contract per file under [`docs/roadmap/tasks/`](docs/roadmap/tasks/). ## Install 0.28.0 Install the Python runtime into an isolated executable environment, then add the matching tagged repository as a Codex plugin marketplace: ```bash pipx install "codex-usage-tracking==0.28.0" codex plugin marketplace add douglasmonsky/codex-usage-tracker --ref v0.28.0 codex plugin add codex-usage-tracker@codex-usage-tracker ``` The plugin launches the `codex-usage-tracker` executable from the pipx environment. Start a fresh Codex task after installation so it discovers the new plugin tool catalog. ## Develop ```bash python3 -m venv .venv .venv/bin/python -m pip install -e ".[dev]" just v ``` Use synthetic fixtures only. Do not commit or share real Codex logs, prompts, responses, tool-output bodies, credentials, private paths, or local databases.
© Douglas Monsky · MIT · hashgraph-online/awesome-codex-plugins