audit(specify): close cycle — repair planner, grounding-check, schema drift

Architect drift review (cycle 9e8b9ec..HEAD) returned drift_found. Three
cycle-introduced items, all repaired here as tidy edits:

- planner/SKILL.md: the cycle never touched it (recon never scoped it,
  the feat commit body's "every pipeline rendering agrees" over-claimed).
  Its Handoff Contract still named `brainstorm → planner` and the bounce
  `planner → brainstorm`; the Input-source cross-ref and two
  rationalisation rows still pointed at brainstorm as the spec producer.
  All repointed to specify (specify produces and owns the spec; brainstorm
  is the optional discovery stage upstream of it). The skip rule now lists
  specify in the design path tdd bypasses.
- specify/agents/grounding-check.md: the agent move left one stale pair —
  "self-review (Step 7) and user-approval (Step 8)" were brainstorm's old
  numbers; in specify they are Step 4 and Step 6.
- profile-schema + template: the `optional: true` per-phase key I
  introduced in the plan was undocumented AND rested on a semantic error —
  `brainstorm: { gates: [specify] }` reads as "specify cannot start until
  brainstorm has run", which is false (specify enters directly from
  sources). Corrected to `brainstorm: {}` (an active phase with no hard
  gate of its own, like implement); specify keeps `gates: [planner]` as
  the one real hard gate. The optional key is gone; brainstorm's
  optionality lives in the skip rules and SKILL prose, where it belongs.

Why these escaped the cycle's own grep suite: the consistency greps used
`brainstorm *-> *planner`, which does not match the real renderings
`` `brainstorm` -> `planner` `` (backticks between the words). The same
filter-string blind spot recurred twice this session; the verification
greps here tolerate optional backticks.

Pre-existing debt (NOT cycle-introduced), filed as backlog Brummel/Skills
issue #5 rather than fixed here: docs/migration.md's layout tree and
README's migration-status both predate tdd/glossary/pseudo/issue/
postmortem and misdescribe the roster.

Verdict: cycle drift-clean after these repairs (carry-on). No regression
gate (prose repo, no scripts). Not a milestone close.

docs/profile-schema.md

@@ -187,9 +187,7 @@ Per-phase configuration. Each phase has its own sub-map.
 
 ```yaml
 pipeline:
-  brainstorm:
+  brainstorm: {}                  # optional discovery front-end; no hard gate of its own
-    gates: [specify]              # optional discovery; hands ratified design to specify
-    optional: true                # skipped when the design is settled in the sources
   specify:
     gates: [planner]              # core node — planner cannot start until the spec is approved
   planner:
@@ -255,7 +253,7 @@ git:
     close_marker: "closes #N"
 
 pipeline:
-  brainstorm: { gates: [specify], optional: true }
+  brainstorm: {}                              # optional discovery; no hard gate
   specify:    { gates: [planner] }
   planner:    { gates: [implement] }
   implement:  {}

planner/SKILL.md

@@ -38,8 +38,8 @@ May be skipped when:
   the plan (handoff goes straight to `implement` mini-mode).
 - The work is a test-specifiable feature routed through `tdd`,
   where the RED executable-spec IS the plan (handoff goes
-  straight to `implement` mini-mode). `tdd` skips both
+  straight to `implement` mini-mode). `tdd` skips the whole
-  `brainstorm` and `planner`.
+  design path — `brainstorm`, `specify`, and `planner`.
 - The work is a trivial mechanical edit (per the project's
   CLAUDE.md "trivial mechanical edits" carve-out).
 
@@ -253,9 +253,9 @@ The planner skill does not perform the commit itself.
 
 | Direction | Carrier |
 |-----------|---------|
-| `brainstorm` → `planner` | path to the spec under `paths.spec_dir` + iteration scope ("this iteration covers spec section X+Y") |
+| `specify` → `planner` | path to the spec under `paths.spec_dir` + iteration scope ("this iteration covers spec section X+Y") |
 | `planner` → `implement` | path to the plan under `paths.plan_dir` + optional task-range focus |
-| `planner` → `brainstorm` (bounce) | spec contains placeholders or contradictions: name the offending section, request revision |
+| `planner` → `specify` (bounce) | spec contains placeholders or contradictions: name the offending section, request revision |
 
 ## Common Rationalisations
 
@@ -266,8 +266,8 @@ The planner skill does not perform the commit itself.
 | "Spec is recent, I wrote it, plan from memory" | Memory diverges from disk. 15 minutes of re-reading is the cheapest insurance in the cycle. |
 | "Step 5 'implement the parser' is fine, I'll detail it at execution time" | Then it's not a step, it's a wish. Steps are bite-sized OR the plan isn't done. |
 | "Task 7 is similar to Task 4, just say so" | The executor may read tasks out of order. Repeat the code. |
-| "The spec has a TBD too, I can pass it through" | Bounce back to `brainstorm`. Plans inherit spec gaps; spec gaps are not plan placeholders. |
+| "The spec has a TBD too, I can pass it through" | Bounce back to `specify`. Plans inherit spec gaps; spec gaps are not plan placeholders. |
-| "The example program came straight from the spec, it must be valid" | The spec's code blocks are hypotheses, not verified bytes — brainstorm's parse gate can be skipped and a post-spec edit can break them. Re-parse every surface-language body you inline; this is the last line before the implementer hits it (issue #1 Fix 4). |
+| "The example program came straight from the spec, it must be valid" | The spec's code blocks are hypotheses, not verified bytes — specify's parse gate can be skipped and a post-spec edit can break them. Re-parse every surface-language body you inline; this is the last line before the implementer hits it (issue #1 Fix 4). |
 
 ## Red Flags — STOP
 
@@ -284,8 +284,9 @@ The planner skill does not perform the commit itself.
 
 ## Cross-references
 
-- **Input source:** `../brainstorm/SKILL.md` — produces the
+- **Input source:** `../specify/SKILL.md` — produces the
-  spec this skill consumes.
+  spec this skill consumes (reached directly from settled
+  sources, or via the optional `../brainstorm` discovery stage).
 - **Output target:** `../implement/SKILL.md` — runs the plan
   task-by-task.
 - **Agents dispatched:**

specify/agents/grounding-check.md

@@ -19,7 +19,7 @@ demands that the spec — not the plan — be corrected at the
 root.
 
 This agent is dispatched between specify's linguistic
-self-review (Step 7) and user-approval (Step 8). The
+self-review (Step 4) and user-approval (Step 6). The
 specify-driven orchestrator has spent its budget building
 the spec and is biased toward shipping it. You, by contrast,
 arrive fresh: no sunk-cost, no investment in the framing.

templates/project-profile.yml

@@ -67,7 +67,7 @@ notifications:
   # command: ""                           # e.g. "~/.claude/notify.sh"; boss falls back to chat if empty
 
 pipeline:
-  brainstorm: { gates: [specify], optional: true }  # optional discovery; skipped when design is settled
+  brainstorm: {}                                    # optional discovery front-end; no hard gate of its own
   specify:    { gates: [planner] }                  # core node: spec-production gate before planner
   planner:    { gates: [implement] }
   implement:  {}