oc-distilling-learningslisted

# Distilling-Learnings — Routing durable insights into the right native mechanism **Announce at the start (in pt-br):** "Usando distilling-learnings para rotear os aprendizados duráveis dos findings pro mecanismo nativo certo." **Input:** the current transient findings buffer (just consolidated by `oc-recording-findings`). **There is no separate learnings store.** This skill does not create or append to any custom learnings file. Durable knowledge goes to the **native mechanism chosen by blast-radius** — the exact destinations `agents/harvester.md` step 4 routes to. A custom store would just duplicate the native `MEMORY.md` index + nested `AGENTS.md` law, so it is dropped. This skill **owns** the classify-and-route machine below; `skill({ name: "oc-surveying-codebase" })` reuses it unchanged, sourcing insights from the code itself instead of a run's findings buffer. --- ## Pipeline 1. **Read the findings buffer** — scan all entries for the current feature run. 2. **Identify candidates** — a finding qualifies as durable if it is: - A pattern seen in 2+ tasks or explicitly flagged as systemic. - A helper/utility that was missing and had to be improvised. - An implicit convention that the plan did not document but was necessary. - An anti-pattern the adversary or sniper caught that could recur in future features. 3. **Cross-check against the codebase** — use Grep/Glob to confirm the pattern is real and not a one-off. A one-off bug fixed by a `sniper-<tier>` ha