Prompt Contribution Graph — Development skill for Claude Code
Track your daily prompt contributions across CLI coding agents.
How to install Prompt Contribution Graph
This entry records only its repository, not the path inside it, so there is no
exact command to give. Open chintan-diwakar/prompt-contribution-graph and copy the folder into
~/.claude/skills/, or the file into ~/.claude/agents/.
What Prompt Contribution Graph does
Track your daily prompt contributions across CLI coding agents.
Alternatives in Development
- Understand Anything — Graphs that teach graphs that impress 80.7k ★
- Ccusage — CLI for analyzing Claude Code/Codex usage from local JSONL files 11.8k ★
- Code Review Graph — Local knowledge graph for Claude Code 3.7k ★
README
Prompt Contribution Graph
Track your daily prompt contributions across CLI coding agents.
GitHub tracks code commits. Prompt Contribution Graph tracks your contributions to coding agents.
Prompts, final responses, and safe tool metadata. Stored locally. No account. No telemetry.
[!NOTE] The current release supports Claude Code and Codex. Prompt Contribution Graph is an unofficial community project that is not affiliated with Anthropic or OpenAI.

Features
- Captures prompts and final responses through official Claude Code and Codex hooks.
- Records tool names, status, duration, and safe targets such as file paths.
- Stores activity and session details in a local SQLite database.
- Displays a 53-week contribution chart.
- Calculates the current streak, longest streak, and
Related Skills
Contribute Loop
Run N sequential contributions. Different from /contribution-fleet (parallel). Stops early on suspicious_halt
AgentsUsage
A lightweight Windows system tray application that parses local Claude CLI and Codex usage logs, hosting an em
Skill Evaluation Graph
Description Evidence-driven evaluation, benchmarking, and verified repair for Agent Skills across Codex, Claud
OSS Autopilot
Open source contribution manager — tracks PRs across repos, discovers issues, diagnoses CI failures, drafts ma
Contribution Fleet
Launch N opensource-contributor runs in parallel across different repos. Each run gets its own state directory
Xiaoyaoclaw Agent Orchestrator
OpenClaw multi-agent daily collaboration orchestrator - split tasks, dispatch via sessions_send, track progres
Related Agents
Cost Governor
Track aggregate token spend and API costs across all agent operations. Enforce budget constraints, detect cost
Template Validator
Validates that agent and command templates follow Claude Code best practices and standards. Use when reviewing
Referee
Simulated blind peer reviewer. Evaluates papers across 5 dimensions (contribution, identification, data, writi