More screenshots
Works with the AI Agents you already use
Agent Trace Debugger — replay a Claude agent step by step
Turn a Claude tool-use conversation (messages array) into a readable timeline of thoughts, tool calls and results, and flag errors, orphaned calls, loops and unrecovered failures with a concrete fix for each.
Free
About this skill
An agent answer is really a loop: think, call a tool, read the result, decide, repeat. Make that loop readable.
userturnthinkingblock- assistant
text tool_use(name, input)tool_result(resolved back to its tool throughtool_use_id; mark errors whenis_erroris true)
Render as a compact timeline, one line per step, with the tool name on results.
Replaying beats re-running: https://agentreplay.vercel.app lets the user scrub the same trace visually (no key, runs in the browser). Source: github.com/ferhatatagun/agent-replay.
Find more skills like this on the Claude Skills Marketplace, the Codex Skills Marketplace and the Gemini Skills Marketplace, or browse All Claude Skills.
Analyses a finished trace in the Anthropic Messages API shape (text, thinking, tool_use, tool_result blocks). It does not re-run the agent and cannot see steps missing from the trace.
How to use
- 1
Connect your agent to the Agensi MCP
Copy the prompt and paste it into Claude, ChatGPT, Cursor or any agent that supports MCP. It sets up the connection for you. Manual setup
- 2
Sign in to Agensi
Your agent shows a sign-in link. Sign in and click Allow.
- 3
Ask for what you need
Your agent loads this skill and uses it on your task. It always asks before buying a skill.
Reviews
No reviews yet
Be one of the first to try it. Every listed skill goes through the trust checks below.
Security scanned
Checked by our 8-point scan before listing
Fresh listing
Recently published to Agensi
Free to use
No account required to browse
Trust & safety
Security scan
Security scan passed 3 days ago
- Free with an Agensi account
Requires
Nothing to install.
Permissions
No special permissions declared or detected