cc-ledger — Every prompt has a price.<br>ai coding telemetry<br>Every prompt has a price.<br>cc-ledger shows you both.<br>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?<br>View source on GitHub<br>events.livestreaming<br>12:04:23→prompt.startcc-ledger/api<br>12:04:24·tool.usebash<br>12:04:27·tool.useedit src/auth.rs<br>12:04:31$cost+$0.0142<br>12:04:32+lines.ai+47<br>12:04:48·tool.usebash<br>12:05:02⇒commit7e2c1a3<br>12:05:11⇒pr.opened#221<br>12:05:12$cost.session$1.84<br>12:05:13◇session.end14m32s<br>12:04:23→prompt.startcc-ledger/api<br>12:04:24·tool.usebash<br>12:04:27·tool.useedit src/auth.rs<br>12:04:31$cost+$0.0142<br>12:04:32+lines.ai+47<br>12:04:48·tool.usebash<br>12:05:02⇒commit7e2c1a3<br>12:05:11⇒pr.opened#221<br>12:05:12$cost.session$1.84<br>12:05:13◇session.end14m32s

metrics<br>What cc-ledger tracks

cost · per pr<br>What does a PR actually cost?<br>Token spend rolled up per merged PR — cache reads at 10%, batch tier applied. Drill in by repo, team, or author.

$4.82−12% w/w· avg / merged PR

runaway · p99<br>Which sessions are burning?<br>Session-cost distribution — p50, p95, p99 — so the tail is visible before it shows up on the invoice. Click through to the offender.

P50$0.42P95$3.10P99$18.40

category · split<br>Where the dollars go<br>Agent turns auto-classified — planning, coding, debugging, review — so leaders see whether spend is exploration or execution.

planning38%coding47%debug10%other5%

audience<br>Built for engineering leaders

Directors, VPs, and team leads need to answer one question: is the AI spend justified, and which teams get leverage?<br>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.

Avg cost per PR$4.82

p99 session cost$18.40

Planning vs. coding38 / 47

setup<br>How it works

01Install hooks<br>One command wires Claude Code lifecycle hooks into your repo. No daemons, no SaaS pings — everything runs locally.<br>$ curl -fsSL https://ccledger.dev/install | bashcopy

02Sessions captured<br>Every prompt, every tool call, every diff is recorded into a local SQLite ledger and (optionally) committed to a private git branch alongside your code.

03Connect & view<br>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.

ready when you are<br>See your numbers.<br>View source on GitHub