AgentPlayback — Development skill for Claude Code
Are you running too few agents, or too many.
How to install AgentPlayback
This entry records only its repository, not the path inside it, so there is no
exact command to give. Open JerryZLiu/AgentPlayback and copy the folder into
~/.claude/skills/, or the file into ~/.claude/agents/.
What AgentPlayback does
Are you running too few agents, or too many? AgentPlayback visualizes your coding agents so you can see when each one ran, when it was blocked on you, and what it cost.
Alternatives in Development
- Agentic Stack — One brain, many harnesses 2.2k ★
- Opik Openclaw — 🦞 Official plugin for OpenClaw that exports agent traces to Opik 725 ★
- Cost Xray — See what Claude Code and Codex actually send to the API — and what each part costs 586 ★
README
AgentPlayback
A local visualization of your coding agents that shows you if you're running too many, or too few at a time.
npx agentplayback
or
bunx agentplayback
AgentPlayback reads existing Codex and Claude Code session logs and turns them into a visual timeline showing:
- When your agents are working versus waiting for your input
- Sessions grouped by task and project
- Time, token usage, and estimated cost
- Daily history across your agents
Data is processed locally and stays local.
Supported agents
AgentPlayback currently supports **Codex** and **Claude Code**.
Contributions adding other agents are welcome. Please include screenshots verifying that the UI and data look right. The interface is intentionally opinionated, though, so integrations that require a substantially different presentation may be better maintained as forks.
Run from source
git clone https://github.com/JerryZLiu/AgentPlayback.git
cd AgentPlayback
npm install
npm run build
npm start
Created by the makers of Dayflow.
Related Skills
Argus Code
See what Claude Code actually did. Local-first observability for every session: which tools ran, what each sub
Thumbgate Blocked
Show what ThumbGate has actually blocked — gate enforcement stats and the full enforcement matrix. Use for "wh
Tmux Claude Session Manager
Run many Claude Code sessions across your projects, each in its own tmux session — then list them, see which a
Satchel
Launcher and window manager for terminal windows — juggle many Claude Code sessions across accounts, or any sh
Lantern
A terminal board for the conversations your coding agents leave behind — Claude Code and five more — grouped b
Proof Of Done
Claude Code plugin that stops a coding agent from ending its turn with 'tests pass', 'build succeeds' or 'depl
Related Agents
Premium Reviewer
Final independent review of a high-risk change, design or diagnosis, on the strongest available model. Use onl
MCP Server Engineer
Own the embedded MCP automation server in unity-explorer — design and implement MCP tools, protocol/transport
Adal CLI
AdaL CLI (SylphAI, named after Ada Lovelace) is a terminal coding agent built for developers who want to see a