create-implementation-plan: require unique identifiers (#1989) (#2142)

* create-implementation-plan: require unique identifiers (#1989)

The skill template tells the agent to use REQ-, TASK-, GOAL-, and
similar prefixed identifiers, but never says they have to be unique
or how to check. @basilevs reported plans coming back with duplicate
TASK IDs and proposed three POSIX one-liners that catch the two real
collision modes (table rows and bullet declarations) plus a broad
diagnostic scan.

Document the uniqueness rule under the existing Template Validation
Rules, then add a new "Identifier Uniqueness Check" section with all
three bash commands and instructions on which must come back empty
before the plan is finalized.

DEP-* references intentionally allowed in multiple sections per the
reporter's note.

Closes #1989.

* codespell: ignore GUD identifier prefix (#1989)

Upstream skills/create-implementation-plan/SKILL.md already uses
GUD-001 in the template body. Codespell currently slips past it on
word-boundary, but the regex alternation (GUD|RISK|...) added in the
previous commit on this branch makes codespell flag it as a misspelling
of GOOD.

GUD is the documented "Guideline" identifier prefix alongside REQ,
SEC, CON, PAT, etc. Add it to the ignore-words-list, matching the
pattern every other technical-token exemption in .codespellrc uses.

* create-implementation-plan: clarify declaration vs reference (#1989 review)

basilevs flagged that calling out DEP-* specifically was misleading,
because any identifier can appear as a reference. A TASK body can
cite a REQ, one TASK can cite another, and so on. The original
phrasing made it sound like DEP-* was the only prefix allowed to
recur.

Rewrite the rule to lead with "uniquely declared":
- Define declaration as the leading bullet/cell ID (e.g., the table
  row in Implementation Phase N, or '- **REQ-001**:').
- Say explicitly that references elsewhere in the plan are expected
  and not collisions, with concrete examples (TASK citing REQ,
  TASK citing TASK, Dependencies pointing at a DEP declared upstream).
- Tighten the check intro to call (1) and (2) declaration-targeted
  gates and (3) a broad informational scan that will see references.

Bash checks unchanged; they already encode the declaration-vs-reference
distinction via the table-cell and bullet-prefix anchors.

skills/create-implementation-plan/SKILL.md

@@ -60,6 +60,34 @@ All implementation plans must strictly adhere to the following template. Each se
 - All identifier prefixes must follow the specified format
 - Tables must include all required columns
 - No placeholder text may remain in the final output
+- **Identifiers must be uniquely declared.** Every identifier (`REQ-NNN`, `SEC-NNN`, `CON-NNN`, `GUD-NNN`, `PAT-NNN`, `GOAL-NNN`, `TASK-NNN`, `ALT-NNN`, `DEP-NNN`, `FILE-NNN`, `TEST-NNN`, `RISK-NNN`, `ASSUMPTION-NNN`) must be **declared exactly once**. A declaration is where the identifier introduces a row: the leading cell in a TASK/GOAL table row, or the bolded prefix in a bullet line like `- **REQ-001**: ...`. The same identifier may then appear any number of times as a **reference** elsewhere in the plan (a `TASK` body citing a `REQ`, one `TASK` citing another `TASK`, the Dependencies section pointing at a `DEP` already declared upstream, etc.). References are expected and not collisions.
+
+## Identifier Uniqueness Check
+
+Run these checks before finalizing the plan. Checks (1) and (2) target declarations and must return zero rows. Check (3) is a broad informational scan: it will surface valid references too, so use it for awareness rather than as a gate.
+
+```bash
+# Set PLAN_FILE to the plan being validated.
+PLAN_FILE="/plan/<purpose>-<component>-<version>.md"
+
+# 1) Duplicate TASK / GOAL declarations in table rows.
+grep -oE '\| (TASK|GOAL)-[0-9]+ \|' "$PLAN_FILE" \
+  | sed -E 's/.*((TASK|GOAL)-[0-9]+).*/\1/' \
+  | sort | uniq -d
+
+# 2) Duplicate declaration IDs in bullet-style spec lines.
+grep -oE '^- \*\*(REQ|SEC|CON|GUD|RISK|ASSUMPTION|TASK|GOAL|FILE|TEST|PAT|ALT|DEP)-[0-9]+\*\*:' "$PLAN_FILE" \
+  | sed -E 's/^- \*\*([A-Z]+-[0-9]+)\*\*:.*/\1/' \
+  | sort | uniq -d
+
+# 3) Broad duplicate scan (diagnostic only; may include valid references).
+grep -oE '(REQ|SEC|CON|GUD|RISK|ASSUMPTION|TASK|GOAL|FILE|TEST|PAT|ALT|DEP)-[0-9]+' "$PLAN_FILE" \
+  | sort | uniq -d
+```
+
+Prerequisites: a POSIX-compatible shell (`sh` / `bash`) with `grep`, `sed`, `sort`, and `uniq`. On Windows without these tools, use equivalent platform-native commands and preserve the same declaration-vs-reference logic.
+
+If check (1) or (2) returns any row, re-number the duplicate so each identifier is declared exactly once, then re-run the checks until both are empty.
 
 ## Status