assaylisted

# Assay — Research & Spec Read `${CLAUDE_PLUGIN_ROOT}/references/creed.md` and `${CLAUDE_PLUGIN_ROOT}/references/memory.md` first. Resolve memory first: `export SMITHY_MEM="$(bash ${CLAUDE_PLUGIN_ROOT}/scripts/paths.sh mem)"` — every smithy path below is relative to it, and it need NOT be inside the repo. If that dir does not exist, bootstrap per `${CLAUDE_PLUGIN_ROOT}/references/memory.md` § Location. Pick a kebab-case job slug from the request; log: `bash ${CLAUDE_PLUGIN_ROOT}/scripts/ledger.sh append assay <slug> spec STARTED -` Resolve your own effort: `bash ${CLAUDE_PLUGIN_ROOT}/scripts/routing.sh research` — apply that effort level to your exploration and thinking in this skill. ## Anti-pattern: "This request is too clear to need a spec" Every job goes through assay — a rename, a config change, a one-endpoint feature. "Clear" requests are where unexamined assumptions do the most damage, because nobody expects them there. For a genuinely trivial job the spec is five lines and costs two minutes; for a job that only LOOKED trivial, those two minutes are the cheapest save available. The spec can be short. It cannot be skipped. ## Checklist (create a todo per item) 1. Restate the request; confirm the restatement 2. Enumerate every would-be assumption → question or recommendation 3. Explore the codebase; findings with file:line evidence 4. Write spec.md; open-questions section empty 5. Log decisions; update STATE.md + ledger; hand off ## Process 1. **Restate the reque