uv run ./scripts/list_sessions.py --json

TMPDIR=$(python3 -c "import tempfile; print(tempfile.gettempdir())")
uv run ./scripts/extract_batches.py <session_jsonl_path> --out-dir "$TMPDIR/rtfp-batches-<sessionid>"

Read the batch JSON file at <batch_file_path>.
Scan all user messages for strong emotional reactions targeted at the assistant:
frustration, disbelief, insults, argument, rage, or clearly negative emotional
responses aimed at the AI's behavior.

Determine the platform temp directory first:
TMPDIR=$(python3 -c "import tempfile; print(tempfile.gettempdir())")

Produce TWO outputs:

1. Write a JSON file to $TMPDIR/rtfp-flagged-<batch_index>.json with this format:
   {"source_file": "<original_session_jsonl_path>", "flagged_indexes": [N, ...]}
   Use the source_file field from the batch JSON header (the original session JSONL path, not the batch file path).
   Write an empty flagged_indexes array if no reactions are found.

2. Print a plain list of flagged entries to your output:
   each line: <message_index> | <full content> (no truncation)

You have a merged set of flagged message indexes from a Claude Code session transcript.
Session JSONL file: <session_jsonl_path>
Flagged indexes: <merged_working_set_as_json>

1. Read the full session JSONL file.
2. Read every flagged user message at the given indexes.
3. Choose the single most emotional, rage-filled response as the winner.
   Optionally identify one runner-up.
4. Determine what the user was currently doing when the reaction occurred —
   write one dry background line describing the activity, not the incident.
   CORRECT:   "writing a Claude Code plugin"
   CORRECT:   "refactoring test fixtures"
   INCORRECT: "the assistant ignored the constraint about scoring"
   INCORRECT: "failure to follow the instruction to omit scoring"
5. Inspect nearby transcript entries and identify the assistant message(s) that triggered the winning reaction. Do not assume it is always the single immediately preceding message — look at the surrounding context window.
6. Determine the platform temp directory:
   TMPDIR=$(python3 -c "import tempfile; print(tempfile.gettempdir())")
   Write $TMPDIR/rtfp-result.json with exactly these fields:
   {
     "task_summary": "<dry one-line activity description>",
     "triggering_assistant_output": "<triggering assistant output>",
     "user_reaction": "<winning emotional user reply>"
   }

TMPDIR=$(python3 -c "import tempfile; print(tempfile.gettempdir())")
uv run ./scripts/render_artifact.py --input-file "$TMPDIR/rtfp-result.json" --output rtfp_artifact.png

task:      <dry activity line>
claude:    <assistant excerpt>
user:      <emotional reply>

PNG: rtfp_artifact.png