OpenAI Codex CLI session log viewer for JSONL files in ~/.codex/sessions. Browse conversations, tool calls, tokens, collaboration chains, and live sessions on desktop and web.
# Add to your Claude Code skills
git clone https://github.com/PixelPaw-Labs/codex-traceGuides for using cli tools skills like codex-trace.
Last scanned: 9/11/2026
{
"issues": [],
"status": "PASSED",
"scannedAt": "2026-09-11T08:37:07.683Z",
"npmAuditRan": true,
"pipAuditRan": true,
"promptInjectionRan": true
}codex-trace is an open-source cli tools skill for AI coding assistants such as Claude Code, Codex CLI, and ChatGPT, built by PixelPaw-Labs. OpenAI Codex CLI session log viewer for JSONL files in ~/.codex/sessions. Browse conversations, tool calls, tokens, collaboration chains, and live sessions on desktop and web. It has 101 GitHub stars.
Yes. codex-trace passed SkillsLLM's automated security scan — a dependency vulnerability audit plus prompt-injection heuristics — with no high-severity issues. You can read the full report in the Security Report section on this page.
Clone the repository with "git clone https://github.com/PixelPaw-Labs/codex-trace" and add it to your Claude Code skills directory (see the Installation section above).
codex-trace is primarily written in Rust. It is open-source under PixelPaw-Labs on GitHub, so you can review or fork the full source.
Yes. SkillsLLM lists many other CLI Tools skills you can browse and compare side by side. Open the CLI Tools category from the badge at the top of this page, or use the Related Skills and comparison links further down to weigh codex-trace against similar tools.
No comments yet. Be the first to share your thoughts!
Top skills in this category by stars
⚠️ Third-Party Software Notice
This skill is third-party open-source software developed and hosted independently on GitHub. SkillsLLM is an informational directory and does not control or maintain the underlying repository.
Any security checks, ratings, or warnings displayed by SkillsLLM are automated and limited in scope. They do not constitute a security certification or guarantee that the software is safe, error-free, or free from malicious code, vulnerabilities, compromised dependencies, or prompt-injection risks.
Review the source code, permissions, dependencies, and configuration before installing or running any third-party skill. Use is at your own risk. To the maximum extent permitted by applicable law, SkillsLLM is not liable for losses arising from third-party software.
Codex Trace is an OpenAI Codex CLI session log viewer for local JSONL files stored in ~/.codex/sessions/.
Browse, search, live-tail, and inspect Codex CLI conversations in a native desktop app and web UI. Codex Trace renders Codex CLI JSONL session files as readable turns with tool calls, token counts, timestamps, collaboration chains, and live SSE tailing for ongoing sessions.
Use Codex Trace when you want to:
~/.codex/sessions/Codex Trace is also used to support and build DovePaw Lite, a personal AI harness platform for orchestrating local agents.
Claude Code user? See claude-code-trace instead.

~/.codex/sessions/Codex CLI stores local session history as JSONL files. Those files are useful for debugging and reviewing AI coding sessions, but they are difficult to read directly. Codex Trace turns Codex CLI logs into an interactive session viewer so you can search conversations, inspect tool usage, review token counts, follow collaboration chains, and debug Codex workflows faster.
Unlike general observability platforms, Codex Trace focuses on local Codex CLI session logs from ~/.codex/sessions/. It does not require sending traces to an external service.
Codex Trace is especially useful when building personal AI harnesses and local agent platforms. It helps inspect Codex CLI sessions, understand tool usage, follow collaboration chains, and debug the workflows that power projects like DovePaw Lite.
Use this option if you want to build Codex Trace locally on macOS, Linux, or Windows with Rust and Node.js installed.
git clone https://github.com/PixelPaw-Labs/codex-trace.git
cd codex-trace
./script/install.sh # macOS → Codex Trace.app in /Applications; Linux → cargo binary
# Launch the desktop app:
# macOS: open -a "Codex Trace" (or from Launchpad/Applications)
# Linux: codex-trace
codex-trace --web # web mode (opens browser)
git clone https://github.com/PixelPaw-Labs/codex-trace.git
cd codex-trace
npm install
npm run tauri dev # desktop app with hot reload
npm run dev:web # web mode (opens browser)
Docker is supported for web mode only.
docker build -t codex-trace .
docker run --rm -p 1422:1422 \
-v "$HOME/.codex/sessions:/home/app/.codex/sessions:ro" \
codex-trace
# then open http://localhost:1422
Or with Docker Compose:
docker compose up --build
Codex Trace reads session files from this default path:
~/.codex/sessions/YYYY/MM/DD/rollout-{ISO_TIMESTAMP}-{UUID}.jsonl
The sidebar reflects the folder structure exactly. Date groups in YYYY/MM/DD format can be collapsed and expanded, with Codex CLI sessions shown underneath.
Press , to open Settings and change the sessions directory.
Default sessions directory:
~/.codex/sessions
Environment variables for headless and Docker mode:
| Variable | Default | Description |
|---|---|---|
CODEXTRACE_HTTP_HOST |
127.0.0.1 |
Bind host |
CODEXTRACE_HTTP_PORT |
11424 |
Bind port |
CODEXTRACE_STATIC_DIR |
— | Path to built frontend dist/ |
npm install
npm run dev # Vite dev server, frontend only
npm run tauri dev # full Tauri app
npm run check # tsc + oxlint + oxfmt + cargo clippy/fmt/test
Run checks before submitting a pull request.
Bug reports, feature requests, and pull requests are welcome. Run npm run check before submitting — it covers TypeScript, linting, formatting, Clippy, Rust formatting, and Rust tests.