cc/ledger
ai coding telemetry

Every prompt has a price.
cc-ledger shows you both.

cc-ledger captures every Claude Code, Cursor, and Copilot session in your repos and turns it into per-user, per-repo metrics — token cost, line attribution, throughput, streaks. So engineering leaders know what their agents are actually doing.

Sign in with GitHubView on GitHub
events.livestreaming
12:04:23prompt.startcc-ledger/api
12:04:24·tool.usebash
12:04:27·tool.useedit src/auth.rs
12:04:31$cost+$0.0142
12:04:32+lines.ai+47
12:04:48·tool.usebash
12:05:02commit7e2c1a3
12:05:11pr.opened#221
12:05:12$cost.session$1.84
12:05:13session.end14m32s
12:04:23prompt.startcc-ledger/api
12:04:24·tool.usebash
12:04:27·tool.useedit src/auth.rs
12:04:31$cost+$0.0142
12:04:32+lines.ai+47
12:04:48·tool.usebash
12:05:02commit7e2c1a3
12:05:11pr.opened#221
12:05:12$cost.session$1.84
12:05:13session.end14m32s
metrics

What cc-ledger tracks

cost · tokens

Spend by user, repo, agent

Per-model token usage in dollars. Cache reads at 10% rate, batch tier auto-applied. Roll up by week, by team, by repo.

$12,847+18.2%· last 7d
attribution

AI lines vs. human lines

Reads commit trailers and diffs to figure out which lines were authored by an agent and which by a human. Per file, per PR, per repo.

cc-ledger/api72%
throughput

Prompts → ship

Where work converts. 14k prompts → 2k commits attributed → 312 PRs touching AI code → 81% acceptance. Surface the leaks.

PROMPTS14kCOMMITS2.0kPRs312SHIP81%
saturation

Activity & streaks

Which engineers haven't started. Which repos are AI-heavy. Daily streaks, session length, message volume — per user, per repo.

audience

Built for engineering leaders

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, attribution, throughput. Drill into any user, any repo, any week.

Cost per AI line$0.014
Active engineers47 / 62
AI acceptance rate81%
setup

How it works

01

Install hooks

One command wires Claude Code lifecycle hooks into your repo. No daemons, no SaaS pings — everything runs locally.

$ cargo install cc-ledger && cc-ledger install
02

Sessions captured

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.

03

Connect & view

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

See your numbers.

Sign in with GitHub