Add looper lint: rubric anti-pattern checks as a static command

CHANGELOG.md

@@ -4,6 +4,29 @@ All notable changes to Looper are documented here. Versions follow
 [Semantic Versioning](https://semver.org/); the loop spec format is versioned
 separately via `version:` in `loop.yaml` (currently `1`).
 
+## Unreleased
+
+### Added — `looper lint`
+- `looper.py lint <loop.yaml>` — the design rubrics as a static checker, no
+  wizard required. Compiles the spec first (compile rejections exit 2), then
+  reports findings in two severities: **errors** for specs that will not
+  behave the way they read at runtime (`judge-criterion-unreachable` — judge
+  criteria on a `fixed_passes` gate are never evaluated; `unscoped-egress` —
+  a gate-referenced cross-vendor member with no `privacy.egress` declaration;
+  `egress-unknown-member` — an egress entry naming nobody) and **warnings**
+  for rubric coaching (`all-vibe-verification`, `no-verification-criteria`,
+  `same-family-judge`, `delivery-gate-no-programmatic`,
+  `non-local-member-without-egress`, `egress-consent-pregranted`,
+  `unreferenced-council-member`, `unhonored-human-checkpoint`,
+  `missing-max-revisions`, `no-wall-clock-cap`, `no-stop-conditions`,
+  `shell-string-check`, `unresolved-placeholders`). Exit 1 on errors, or on
+  any finding with `--strict`; `--json` emits machine-readable findings for
+  CI (exit 2 compile failures print to stderr, no JSON).
+- The wizard now runs `lint` after every compile and treats errors as
+  blockers, warnings as coaching to relay (SKILL.md step 10).
+- 10 new tests (37 total), including a sweep asserting all five shipped
+  templates and the example lint with zero errors.
+
 ## 0.3.0 — 2026-07-05
 
 ### Added — loop pattern library

README.md

@@ -201,6 +201,25 @@ what's installed, and still runs its full critique, privacy, and preview flow
 before emitting. See [`templates/loops/`](templates/loops/) for the catalog
 and per-template docs — including how to add your own.
 
+### Lint any loop.yaml
+
+The design rubrics also exist as a static checker — no wizard, no interview:
+
+```bash
+python scripts/looper.py lint path/to/loop.yaml
+```
+
+`lint` compiles the spec, then checks it for the anti-patterns the rubrics
+coach against: all-vibe verification (no programmatic checks), judge criteria
+a runner would never evaluate, undeclared cross-vendor egress, a judge that
+shares the host's model family, missing caps, and unresolved `{{PLACEHOLDER}}`
+tokens. **Errors** mean the spec won't behave the way it reads (exit 1);
+**warnings** are design coaching (exit 0, or exit 1 with `--strict`). A spec
+that doesn't compile exits 2 with the compile error on stderr — in that case
+`--json` emits nothing, so CI wrappers should check the exit code before
+parsing. Add `--json` for tooling, and wire `lint --strict` into CI to gate
+loop specs in PRs the same way you lint code.
+
 ### Easy: run in the same session
 
 The default path is to let Looper continue in the same conversation. It follows

SKILL.md

@@ -66,6 +66,11 @@ advanced external runner.
 10. After writing `loop.yaml`, resolve the helper Python (see Helper Python
    below) and run:
    `"$LOOPER_PYTHON" ${CLAUDE_SKILL_DIR}/scripts/looper.py compile <target>/loop.yaml --out <target>/loop.resolved.json --render <target>/LOOP.md --session-prompt <target>/RUN_IN_SESSION.md`
+   Then run
+   `"$LOOPER_PYTHON" ${CLAUDE_SKILL_DIR}/scripts/looper.py lint <target>/loop.yaml`
+   and relay the findings: fix any `error[...]` before continuing (the spec
+   would not behave as written), and surface `warning[...]` lines to the user
+   as design coaching they may accept or address.
 11. Ask whether the user wants to run the loop now in this session. If yes,
    follow `RUN_IN_SESSION.md` directly as the active task. If no, explain that
    the same file is the easy restart path and `run-loop.py` is available for
@@ -148,6 +153,8 @@ same shell invocation:
   `"$LOOPER_PYTHON" ${CLAUDE_SKILL_DIR}/scripts/looper.py register-model <id> --invoke "<cmd> [args...]"`
 - Compile and render:
   `"$LOOPER_PYTHON" ${CLAUDE_SKILL_DIR}/scripts/looper.py compile <target>/loop.yaml --out <target>/loop.resolved.json --render <target>/LOOP.md --session-prompt <target>/RUN_IN_SESSION.md`
+- Lint against the design-rubric anti-patterns (add `--strict` to fail on warnings, `--json` for tooling):
+  `"$LOOPER_PYTHON" ${CLAUDE_SKILL_DIR}/scripts/looper.py lint <target>/loop.yaml`
 - Render only the in-session handoff:
   `"$LOOPER_PYTHON" ${CLAUDE_SKILL_DIR}/scripts/looper.py session-prompt <target>/loop.resolved.json --out <target>/RUN_IN_SESSION.md`