Agent Run Post-Mortem: Trace Root Cause and Prompt or Tool Fixes
Analyzes a pasted agent trace to find the first real failure and proposes exact prompt rewrites or tool changes, each with a test.
74 prompts
Prompts for coding agents and agent workflows, from Claude Code, Codex and Cursor to multi-agent pipelines. They read like task briefs: the goal, the scope, the tools allowed and the checks that prove the work is done.
3 results
Analyzes a pasted agent trace to find the first real failure and proposes exact prompt rewrites or tool changes, each with a test.
Writes a ready-to-deploy orchestrator system prompt that delegates to your workers, tracks progress in a ledger, merges results and stops on defined conditions.
Turns a pasted feature spec into independent coding-agent tasks with file ownership, interface contracts, a merge order and a done command for each task.
An agent acts: it reads files, runs commands and edits code. So the prompt sets limits and a way to verify the result, not only the answer you want.
Coding agents such as Claude Code, Codex, Cursor and Copilot's agent mode, plus prompts for designing your own multi-agent pipelines. Each prompt lists its tools.
Yes. Run agents in a branch or a sandbox, read the diff and the commands they ran, and keep approval on for anything that deletes data or deploys.