
Session Viewer
Render Codex, Claude Code, OpenClaw, or Pi session JSONL transcripts as a searchable...
Install
npx skills add openclaw/agent-skills --skill session-viewer -g -a claude-code -y- Repository
- openclaw/agent-skills1.1k
- Category
- AI and agents
- Updated
- 3d ago
- License
- MIT
- Context cost
- Lightabout 876 tokens
- Runs scripts
- Yes, review before use
What it does
Render Codex, Claude Code, OpenClaw, or Pi session JSONL transcripts as a searchable, shareable single-file HTML viewer.
Session Viewer
Use when asked to view, export, inspect, or share a Codex, Claude Code, OpenClaw, or Pi session transcript in a browser.
Commands
When the session path is not known and the agent-transcript skill is available, use it first to find the likely JSONL session:
.agents/skills/agent-transcript/scripts/agent-transcript find \
--query "$USER_GOAL_OR_TITLE $BRANCH_OR_URL" \
--cwd "$PWD" \
--since-days 14
Pick the highest-confidence file result, then render it with session-viewer.
From a repo that has this skill:
node skills/session-viewer/scripts/session-viewer.ts <session.jsonl> --out /tmp/session.html --open
Useful modes:
node skills/session-viewer/scripts/session-viewer.ts <session.jsonl> --out session.html
node skills/session-viewer/scripts/session-viewer.ts <session.jsonl> --raw --out session.html
node skills/session-viewer/scripts/session-viewer.ts --blank --out viewer.html --open
In a downstream repo that syncs shared skills under .agents/skills, replace
skills/session-viewer with .agents/skills/session-viewer.
Defaults:
- detects
codex,claude, orpi-openclaw - embeds normalized session data into one HTML file
- keeps tool input/output text in the DOM so browser search can find it
- reads the complete session file, preserving full history in both export modes
--rawembeds the original JSONL and lets the browser parse it--blankcreates a reusable file-picker viewer
For an explicitly partial export, use --max-read-bytes N with a positive integer byte limit (for example, --max-read-bytes 8388608 for 8 MiB). Oversized files retain the head and tail, with a visible omission warning in the CLI and exported viewer. Truncated boundary records may be omitted; --raw embeds only the retained JSONL. Files at or below the limit remain complete. Short reads are retried; an unexpected end of file fails the export instead of reporting a complete read.

