Session Report

Session Report

Produce a self-contained HTML report of Claude Code usage and save it to the current working directory.

Steps

1. Get data. Run the bundled analyzer (default window: last 7 days; honor a different range if the user passed one, e.g. 24h, 30d, or all). The script analyze-sessions.mjs lives in the same directory as this SKILL.md — use its absolute path:

``sh node /analyze-sessions.mjs --json --since 7d > /tmp/session-report.json ` For all-time, omit --since`.

1. Read /tmp/session-report.json. Skim overall, by_project, by_subagent_type, by_skill, cache_breaks, top_prompts.

1. Copy the template (also bundled alongside this SKILL.md) to the output path in the current working directory:

``sh cp /template.html ./session-report-$(date +%Y%m%d-%H%M).html ``

1. Edit the output file (use Edit, not Write — preserve the template's JS/CSS):

• Replace the contents of `` with the full JSON from step 1. The page's JS renders the hero total, all tables, bars, and drill-downs from this blob automatically.
• Fill the ` block with **3–5 one-line findings**. Express figures as a **% of total tokens** wherever possible (total = overall.inputtokens.total + overall.outputtokens`). One line per finding, exact markup:

``html 41.2%cc-monitor consumed 41% of the week across just 3 sessions ` Classes: .take bad for waste/anomalies (red), .take good for healthy signals (green), .take info for neutral facts (blue). The .fig is one short number (a %, a count, or a multiplier like 12×). The .txt is one plain-English sentence naming the project/skill/prompt; wrap the subject in `. Look for: a project or skill eating a disproportionate share, cache-hit 2% of total, subagent types averaging >1M tokens/call, cache breaks clustering.

• Fill the ` block (at the **bottom** of the page) with 1–4 suggestions tied to specific rows (e.g. "/weekly-status` spawned 7 subagents for 8.1% of total — scope it to fewer parallel agents").
• Do not restructure existing sections.

1. Report the saved file path to the user. Do not open it or render it.

Notes

• The template is the source of interactivity (sorting, expand/collapse, block-char bars). Your job is data + narrative, not markup.
• Keep commentary terse and specific — reference actual project names, numbers, timestamps from the JSON.
• top_prompts already includes subagent tokens and rolls task-notification continuations into the originating prompt.
• If the JSON is >2MB, trim top_prompts to 100 entries and cache_breaks to 100 before embedding (they should already be capped).

Source & license

This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.

• Author: thevibeworks
• Source: thevibeworks/claude-code-docs
• License: MIT

Install and usage instructions live in the source repository linked above.