prompt-miner

# prompt-miner Mine the harness's own session history to learn which prompt traits produce the best sessions, and feed those learnings back into memory/identity. This skill is the **judgment layer** on top of the deterministic `mine-traces.mjs` engine: the engine collects, scores, and ranks; this skill correlates prompt features against outcome, mines **falsifiable markers**, and proposes durable lessons for approval. It is a cross-session, data-driven cousin of `/retro`. Where `/retro` reflects on the *current* conversation, `/prompt-miner` reflects on the *corpus* of past sessions across both harnesses. > `disable-model-invocation: true` suppresses **auto**-invocation only — the model > will not fire this skill on its own. A user-typed `/prompt-miner` still runs the > full body below, including the Step-3 LLM marker synthesis. There is no conflict: > the deterministic engine produces an objective dataset; the LLM step interprets > it. ## Privacy contract This skill reads real session transcripts, which can contain secrets and private content. The contract is non-negotiable: - **Default output is feature vectors + metadata only — never raw prompt text.** The engine omits `promptText` unless `--include-prompt-text` is passed. - `--include-prompt-text` applies a redaction pass (line-level token patterns + block-level key bodies) and prints a `WARNING` banner. Use it only when you must read the prompt wording, and never commit the result. - All artifacts land in the...