Ccledger — Development skill for Claude Code
Team usage ledger for Claude Code.
How to install Ccledger
This entry records only its repository, not the path inside it, so there is no
exact command to give. Open shakibbinkabir/ccledger and copy the folder into
~/.claude/skills/, or the file into ~/.claude/agents/.
What Ccledger does
Team usage ledger for Claude Code. Self-hosted OTLP ingest into SQLite, with a per-person dashboard. Independent project, not affiliated with Anthropic.
Alternatives in Development
- Microsandbox — Open-source self-hosted MicroVM sandboxes with sub-200ms startup, hardware-level isolation via libkrun 5k ★
- Harnessrouter — HarnessRouter Community Edition: the self-hosted, Apache-2.0 edition of the unified interface for agent harnes 618 ★
- Netclode — Self hosted cloud coding agent with k3s + kata containers + cloud hypervisor microVMs + tailscale + any harnes 249 ★
README
ccledger
Team usage ledger for Claude Code. See who is using how many tokens.
[](https://github.com/shakibbinkabir/ccledger/actions/workflows/ci.yml) [](https://www.npmjs.com/package/@thisissbk/ccledger) [](LICENSE) [](package.json)

**ccledger is an independent open source project. It is not affiliated with, endorsed by, or sponsored by Anthropic.**
What it does
Claude Code can export OpenTelemetry data about its own API calls. ccledger runs a server that receives that data from everyone on your team, stores it in one SQLite file, and shows per-person token usage, a model breakdown, and trends over a date range.
It is built for teams of two to ten who share Claude Code access and cannot see who is using what. Anthropic's per-user analytics is an Enterprise feature; this covers the same question for everyone else.
ccledger vs ccusage / CCMeter
Those tools read the session logs already on your disk and show you your own usage on one machine. They are good at that, they need no server, and if that is what you want you should use one of them.
ccledger is the team version. Every machine reports to one server you run, so you get per-person attribution across the whole team in one place.
In production at
[Neovogent AI](https://www.neovogent.com) — a UK company building specialized AI assistants that run inside a client's own environment rather than a public cloud — runs ccledger self-hosted on a $5 AWS Lightsail instance to see how its team's Claude Code usage divides up.
That is the whole inte
Related Skills
Sup Mem
Memory for Claude Code that measures whether its memories helped — outcome ledger, self-tuning retrieval, bite
MCP Memory
🧠 Memoria local para agentes IA vía MCP. Drop-in para Claude Code, OpenCode, Cursor, Continue. Python + FastM
Hardware Assets Inventory Tool
Self-hosted hardware asset inventory for IT teams — track devices, who holds them, and the full ownership hist
Otherside CLI
Totally Free Claude Code inspired terminal coding agent. Multi-provider: Anthropic, Codex, Gemini, Kimi, DeepS
Anthropic Agent SDK Relay
Anthropic Messages API endpoint answered by the Claude Agent SDK, so self-hosted n8n can use a Claude subscrip
Q Agent
Self-hosted llama.cpp stack for Qwen + MTP (multi-token prediction): a 125B MoE read from ≥ 80 GB of RAM, or a
Related Agents
Team Executor
Agent-teams executor. Implements one independent unit of an approved plan from a self-contained spawn prompt,
Data SQL
Use PROACTIVELY and automatically — do not wait to be asked — for SQL/data-pipeline work on the operator's loc
Build Be
Backend engineer for Flotion. Use to implement FastAPI + SQLite changes in apps/flotion/backend per the plan —