recall-reasoning

# Recall Reasoning Locate the Claude Code transcript that produced a given change and extract the implementer's reasoning. Useful for answering reviewer questions, writing post-hoc explanations, or recovering forgotten context. ## Inputs Accept any of: - A commit SHA - A file path, optionally with a line number (`<path>:<line>`) - A reviewer question plus surrounding context (file and line) If only a file is given, `git blame` resolves the commit that last touched the line. ## Step 1: Resolve the Commit and Run the Script Call `scripts/find_transcript.py` with either `--commit <sha>` or `--file <path>[:<line>]`. Pass `--cwd /path/to/repo` when searching a different repo than the current working directory. ```bash python3 <skill-dir>/scripts/find_transcript.py --file <path>:<line> python3 <skill-dir>/scripts/find_transcript.py --commit <sha> ``` The script: 1. Resolves the commit via `git rev-parse` or `git blame` 2. Looks up `~/.claude/projects/<encoded-cwd>/` (slashes and dots become dashes) 3. Ranks candidate transcripts whose mtime is within `--window-days` of the commit (default 14) 4. Scores candidates by mentions of touched files and tool-use edits on them 5. Extracts cleaned user prompts and substantive assistant text from the top candidates The JSON output has `status`, `commit`, `project_dir`, and `candidates` with `session_id`, `score`, `match_reasons`, and `excerpts`. Status values: - `ok` — candidates returned - `no-commit` — couldn't resolve a commit...