/cs-run-forensics

Answer a question about a past agent run from its recorded transcript - find the run, walk back from the step, separate recorded from inferred.

BOOST

Guide

alirezarezvani@alirezarezvani

GitHub

From plugin

claude-skills

30k169 skills127 agents169 commands2 MCP

$ npx -y skills add alirezarezvani/claude-skills --agent claude-code

Command definition

cs-run-forensics.md

disable-model-invocation: true
description: Answer a question about a past agent run from its recorded transcript - find the run, walk back from the step, separate recorded from inferred.
argument-hint: "<question> [--session ID | --trace PATH]"

/cs-run-forensics

Answer `$ARGUMENTS` from the recording, not from memory.

S=${CLAUDE_PLUGIN_ROOT}/skills/agent-run-forensics/scripts
python3 $S/trace_finder.py --since 7d                     # add --touched PATH or --grep TEXT; skip for this session
python3 $S/trace_timeline.py --trace <path> --files
python3 $S/trace_timeline.py --trace <path> --grep <TEXT> # or --errors, --file PATH
python3 $S/trace_timeline.py --trace <path> --why <STEP>

If the finder exits 2, say the run is not recorded here and stop.

Report

1. The run: session id, harness, time, source path. 2. The answer, from recorded steps only, each with its step number. 3. The likely cause, labelled inferred, with its rule. 4. What the trace cannot answer.

Read it on GitHub ↗

Stats

Python JavaScript HTML Bash GCP Git GitHub Playwright Markdown Anthropic Gemini MCP

29,589

Stars

4,104

Forks

Active

Maintenance

Python

Language

MIT

License

12h ago

Last commit

1y ago

Created

Repo: alirezarezvani/claude-skills

Ships withclaude-skills

411 production-ready skills for Claude Code and 12 other coding agents, covering engineering, product, marketing, compliance, finance and the C-suite. We test whether each skill loads when you ask in plain words, and publish the results.