fix(pipeline): complete the gitignored-specs refactor (review gaps)

An adversarial review of 08bc2aa found three gaps:

- templates/CLAUDE.md.fragment still described the OLD git-tracked /
  git-rm-at-close model verbatim — the worst place to miss it, since new
  projects import this fragment into their CLAUDE.md. Rewritten to the
  gitignored / shell-rm / ledger-only model.
- INSTALL.md still cited "4-digit naming" — now slug-only.
- The fieldtest cross-cycle deletion rule was self-defeating: it keyed
  the spare/delete decision on the permanent fieldtest- prefix, which
  cannot encode "spare once, then delete." Because fieldtest runs only
  AFTER audit closes, the fresh fieldtest spec never exists at the
  cycle-close sweep, so the rule is simply "audit discards every
  working-tree spec/plan"; the spent fieldtest spec present at N+1's
  close was already consumed and goes with the rest. The prefix is now
  only a working-tree label, not a delete discriminator. Reconciled
  across audit, conventions, pipeline, fieldtest, fieldtester.

docs/pipeline.md

@@ -213,11 +213,10 @@ review-and-commit discipline; the orchestrator inspects and commits.
 Runs at cycle close. Dispatches the architect agent (read-only
 drift review against the design ledger) and the bencher agent
 (regression diagnostics). Reports drift and regress. Once it is
-drift-clean, the orchestrator discards the cycle's spec and plan with a
-plain shell `rm` (nothing to `git rm` — they were never committed),
-sparing any `fieldtest-`-prefixed spec (it belongs to the next cycle);
-the cycle-close commit contains only code and ledger changes (see
-`conventions.md` § Lifecycle).
+drift-clean, the orchestrator discards every working-tree spec and plan
+with a plain shell `rm` (nothing to `git rm` — they were never
+committed); the cycle-close commit contains only code and ledger changes
+(see `conventions.md` § Lifecycle).
 
 ### debug