plugin official · Anthropic

session-report — Claude Code plugin: session usage reports

Q: How do I install session-report in Claude?

Add the marketplace first: `/plugin marketplace add anthropics/claude-plugins-official`. Then install the plugin: `/plugin install session-report@claude-plugins-official`.

Q: Where does session-report get its data?

From the local transcripts in `~/.claude/projects` on your machine. That's why it targets Claude and won't work where that directory doesn't exist.

Turns your Claude sessions into an explorable HTML report: token spend, cache efficiency, subagents, skills and the priciest prompts.

Install into Claude Code · Plugin marketplace All methods and platforms ↓

/plugin install session-report@claude-plugins-official
/plugin marketplace add anthropics/claude-plugins-official

Open on GitHub

What session-report does

The plugin reads local transcripts from ~/.claude/projects and builds an HTML page you can click through. You get token counts, how the cache behaved, which subagents and skills fired, and which prompts cost the most.

Handy when the API bill climbs and you can't tell why. Open the report, look at the expensive prompts, decide what to rewrite. Nothing leaves your machine — it all comes off disk.

It only runs in Claude. Other editors and CLIs won't work because the plugin depends on the ~/.claude/projects layout. Installation goes through the claude-plugins-official marketplace.

What it helps with

see how many tokens a session burned
find the most expensive prompts
check how well the cache performed
spot which subagents and skills ran
trace where the API spend is coming from

Example prompts for the agent

show me a report for the last session
generate an HTML report of token usage
which prompts cost the most in this session

How to install session-report

Plugin marketplace

/plugin install session-report@claude-plugins-official

/plugin marketplace add anthropics/claude-plugins-official

Step by step, with commands for each platform: Claude Code plugins: marketplaces, installing, and building your own

Questions about session-report

How do I install session-report in Claude?

Add the marketplace first: /plugin marketplace add anthropics/claude-plugins-official. Then install the plugin: /plugin install session-report@claude-plugins-official.

What does session-report do?

It builds an HTML report from your Claude session transcripts in ~/.claude/projects, covering tokens, cache efficiency, subagents, skills and the most expensive prompts.

Where does session-report get its data?

From the local transcripts in ~/.claude/projects on your machine. That's why it targets Claude and won't work where that directory doesn't exist.

Source text

session-report · Apache-2.0

Generate an explorable HTML report of Claude Code session usage — tokens, cache efficiency, subagents, skills, and the most expensive prompts — from local ~/.claude/projects transcripts.

caveman JuliusBrussee Cuts filler and polite greetings from agent responses while keeping technical facts and code exact. Stays active until turned off. CX Codex +1 593,100installs session-history rohitg00 Shows recent project sessions as a clean timeline. Use it to recover past decisions, observations, and session status. CX Codex +1 13,900installs plannotator-compound backnotprop Reads a Plannotator plan archive, pulls out denial patterns and feedback, then builds an HTML dashboard with findings. CX Codex +1 11,500installs earnings-preview-single official anthropics Generates a 4-5 page HTML equity research earnings preview for a single company: analyzes the latest earnings transcript, competitors, valuation multiples, and recent news. CX Codex +1 1,800installs session-guard Adit Jain session-guard monitors long sessions and rule drift. Use it for multi-step tasks or after a context compaction event. CX Codex 2,800installs ponytail DietrichGebert ponytail steers Claude Code toward small, direct solutions and away from abstractions nobody asked for. Use it when you want the agent to build on what the project already has. ★ 176,443repo stars impeccable pbakaus Hands your agent a designer's vocabulary: 24 commands like polish, audit and bolder, so UI feedback stops being “make it pretty”. ★ 88,212repo stars last-30-days-skill mvanhorn Searches the web for what people posted about a topic in the last month and turns it into one structured brief. ★ 65,508repo stars

From the same set123

The whole set →

terraform Adds the Terraform MCP server to Claude, so the agent can work with Terraform configs and Infrastructure as Code without leaving the chat. ★ 44,635repo stars telegram Wires a Telegram bot into your Claude session through an MCP server, so the assistant replies, reacts and edits messages. ★ 44,635repo stars swift-lsp Connects SourceKit-LSP to Claude Code for Swift code intelligence. It helps the agent parse symbols and navigate .swift files. ★ 44,635repo stars skill-creator Create or improve skills, run evals, and measure performance with variance analysis. Use it when a skill needs testing before adoption. ★ 44,635repo stars serena Semantic code analysis MCP server with Language Server Protocol integration. Helps explore codebases and suggest refactorings. ★ 44,635repo stars security-guidance Three layers of review for code Claude writes: instant regex warnings, an LLM pass over the diff, and an agentic commit reviewer. ★ 44,635repo stars rust-analyzer-lsp Wires the rust-analyzer language server into Claude so the agent can navigate and analyse Rust code. ★ 44,635repo stars ruby-lsp Connects the Ruby language server to Claude Code for code intelligence across .rb, .rake, .gemspec, .ru, and .erb files. ★ 44,635repo stars