discoverlisted

# Discover You receive a task: **discover the essence of the registered sources, then write reference files for the parts that matter**. The named checks in `verify.sh` (plus the permalink-density lint for SHA-pinning) validate your output; the four reference invariants are your authoring targets — not all are machine-checked (see § Output contract). How you reason about the corpus is your call — there is no Stage 0/1/2 prescription, no fixed keystroke menu, no required worker dispatch. Vary your approach by what the corpus rewards. ## Contextualizer root Engine workflows operate inside a contextualizer installed as a project skill at one of three install levels: - **User-level:** `~/.claude/skills/<slug>-context/` - **Local-user-level:** `~/.claude/local/skills/<slug>-context/` (when in use) - **Project-level:** `<repo>/.claude/skills/<slug>-context/` Every path below — `research/...`, `references/...`, `verify.sh` — resolves relative to whichever directory matches. Before reading or writing anything, locate the root by searching all three install levels in order: Run the script in [`shared/locator-block.md`](../../shared/locator-block.md) verbatim before proceeding. ```bash CTX_PROPOSED="${CTX_ROOT}.proposed" ``` Multi-contextualizer disambiguation and the full staging-directory model — the `$CTX_PROPOSED` manifest schema, removed-detection, and the review/apply/discard handoff — are documented in [`references/staging-and-contextualizer-model.md`](references/staging