cc-ledger captures every Claude Code, Cursor, and Copilot session in your repos and answers the three questions every engineering leader is asking: what does a PR actually cost, which sessions are runaway burns, and where does the spend go — planning or coding?
View source on GitHubToken spend rolled up per merged PR — cache reads at 10%, batch tier applied. Drill in by repo, team, or author.
Session-cost distribution — p50, p95, p99 — so the tail is visible before it shows up on the invoice. Click through to the offender.
Agent turns auto-classified — planning, coding, debugging, review — so leaders see whether spend is exploration or execution.
Directors, VPs, and team leads need to answer one question: is the AI spend justified, and which teams get leverage?
cc-ledger is the dashboard, not the raw logs. No spelunking through JSONL transcripts. Open the page, see cost per PR, the runaway tail, and where planning ends and coding begins. Drill into any user, any repo, any week.
One command wires Claude Code lifecycle hooks into your repo. No daemons, no SaaS pings — everything runs locally.
$ curl -fsSL https://ccledger.dev/install | bashEvery prompt, every tool call, every diff is recorded into a local SQLite ledger and (optionally) committed to a private git branch alongside your code.
Authorize the GitHub App, point cc-ledger at your repos, and the dashboard fills in real time. Cost, attribution, throughput — per user, per repo, per week.