Merge upstream v2.67.0 with fork customizations preserved

Synced 79 commits from EveryInc/compound-engineering-plugin upstream while
preserving fork-specific customizations (Python/FastAPI pivot, Zoominfo-internal
review agents, deploy-wiring operational lessons, custom personas).

## Triage decisions (15 conflicts resolved)

Keep deleted (7) -- fork already removed these in prior cleanups:
- agents/design/{design-implementation-reviewer,design-iterator,figma-design-sync}
  (no fork successor; backend-Python focus doesn't need UI/Figma agents)
- agents/docs/ankane-readme-writer (replaced by python-package-readme-writer)
- agents/review/{data-migration-expert,performance-oracle,security-sentinel}
  (replaced by *-reviewer naming convention: data-migrations-reviewer,
  performance-reviewer, security-reviewer)

Keep local (1):
- agents/workflow/lint.md (Python tooling: ruff/mypy/djlint/bandit; upstream
  deleted the file). Fixed pre-existing duplicate "2." numbering bug.

Restore from upstream (1):
- agents/review/data-integrity-guardian.md (kept for GDPR/CCPA privacy
  compliance angle not covered by data-migrations-reviewer)

Merge both (6) -- upstream structural wins layered with fork intent:
- agents/research/best-practices-researcher.md (upstream <examples> removal +
  fork's Rails/Ruby -> Python/FastAPI translations)
- skills/ce-brainstorm/SKILL.md (universal-brainstorming routing + Slack
  context + non-obvious angles + fork's Deploy wiring flag)
- skills/ce-plan/SKILL.md (universal-planning routing + planning-bootstrap +
  fork's two Deploy wiring check bullets)
- skills/ce-review/SKILL.md (Run ID, model tiering haiku->sonnet, compact-JSON
  artifact contract, file-type awareness, cli-readiness-reviewer + fork's
  zip-agent-validator, design-conformance-reviewer, Stage 6 Zip Agent
  Validation)
- skills/ce-review/references/persona-catalog.md (cli-readiness row + adversarial
  refinement + fork's Language & Framework Conditional layer; 22 personas total)
- skills/ce-work/SKILL.md (Parallel Safety Check, parallel-subagent constraints,
  Phase 3-4 compression + fork's deploy-values self-review row, with duplicate
  checklist bullet collapsed to single occurrence)

## Auto-applied (no triage needed)

- 225 remote-only files: accepted as-is (new docs, brainstorms, plans,
  upstream skills, tests, scripts)
- 70 local-only files: 46 preserved as-is (kieran-python, tiangolo-fastapi,
  zip-agent-validator, design-conformance-reviewer, essay/proof commands,
  excalidraw-png-export, etc.); 24 stayed deleted (dhh-rails-style,
  andrew-kane-gem-writer, dspy-ruby Ruby skills no longer needed)

## README updated

- Removed Design section (3 deleted agents)
- Removed deleted Review entries (data-migration-expert, dhh-rails-reviewer,
  kieran-rails-reviewer, performance-oracle, security-sentinel)
- Added new Review entries: design-conformance-reviewer, previous-comments-reviewer,
  tiangolo-fastapi-reviewer, zip-agent-validator
- Workflow: added lint
- Docs: replaced ankane-readme-writer with python-package-readme-writer

## Known issues (not introduced by merge decisions)

- 9 detect-project-type.sh tests fail on macOS bash 3.2 (script uses
  `declare -A` which requires bash 4+). Upstream regression in commit 070092d
  (#568). Resolution: install bash 4+ via `brew install bash` locally;
  upstream fix tracked separately.
- 2 review-skill-contract tests reference deleted agents (dhh-rails-reviewer,
  data-migration-expert). Pre-existing fork inconsistency, not new.

bun run release:validate: passes (46 agents, 51 skills, 0 MCP servers)

plugins/compound-engineering/skills/ce-review/SKILL.md

@@ -137,12 +137,14 @@ Routing rules:
 | `compound-engineering:review:kieran-typescript-reviewer` | TypeScript components, services, hooks, utilities, or shared types |
 | `compound-engineering:review:julik-frontend-races-reviewer` | Stimulus/Turbo controllers, DOM events, timers, animations, or async UI flows |
 
-**CE conditional (migration-specific):**
+**CE conditional (migration & external review):**
 
-| Agent | Select when diff includes migration files |
-|-------|------------------------------------------|
-| `compound-engineering:review:schema-drift-detector` | Cross-references schema.rb against included migrations |
-| `compound-engineering:review:deployment-verification-agent` | Produces deployment checklist with SQL verification queries |
+| Agent | Select when... |
+|-------|----------------|
+| `compound-engineering:review:design-conformance-reviewer` | Repo contains design documents or active plan matching current branch |
+| `compound-engineering:review:schema-drift-detector` | Diff includes migration files -- cross-references schema.rb against included migrations |
+| `compound-engineering:review:deployment-verification-agent` | Diff includes migration files -- produces deployment checklist with SQL verification queries |
+| `compound-engineering:review:zip-agent-validator` | PR URL contains `git.zoominfo.com` -- pressure-tests zip-agent comments for validity |
 
 ## Review Scope
 
@@ -345,7 +347,7 @@ Read the diff and file list from Stage 1. The 4 always-on personas and 2 CE alwa
 
 Stack-specific personas are additive. A Rails UI change may warrant `kieran-rails` plus `julik-frontend-races`; a TypeScript API diff may warrant `kieran-typescript` plus `api-contract` and `reliability`.
 
-For CE conditional agents, check if the diff includes files matching `db/migrate/*.rb`, `db/schema.rb`, or data backfill scripts.
+For CE conditional agents, check if the diff includes files matching `db/migrate/*.rb`, `db/schema.rb`, or data backfill scripts. If the repo contains design documents (`docs/`, `docs/design/`, `docs/architecture/`, `docs/specs/`) or an active plan matching the current branch, select `design-conformance-reviewer`. If the PR URL contains `git.zoominfo.com`, select `zip-agent-validator`.
 
 Announce the team before spawning:
 
@@ -383,7 +385,7 @@ Persona sub-agents do focused, scoped work and should use a fast mid-tier model
 
 Use the platform's mid-tier model for all persona and CE sub-agents. In Claude Code, pass `model: "sonnet"` in the Agent tool call. On other platforms, use the equivalent mid-tier (e.g., `gpt-4o` in Codex). If the platform has no model override mechanism or the available model names are unknown, omit the model parameter and let agents inherit the default -- a working review on the parent model is better than a broken dispatch from an unrecognized model name.
 
-CE always-on agents (agent-native-reviewer, learnings-researcher) and CE conditional agents (schema-drift-detector, deployment-verification-agent) also use the mid-tier model since they perform scoped, focused work.
+CE always-on agents (agent-native-reviewer, learnings-researcher) and CE conditional agents (design-conformance-reviewer, schema-drift-detector, deployment-verification-agent, zip-agent-validator) also use the mid-tier model since they perform scoped, focused work.
 
 The orchestrator (this skill) stays on the default model because it handles intent discovery, reviewer selection, finding merge/dedup, and synthesis -- tasks that benefit from stronger reasoning.
 
@@ -446,7 +448,7 @@ Detail-tier fields (`why_it_matters`, `evidence`) are in the artifact file only.
 
 **CE always-on agents** (agent-native-reviewer, learnings-researcher) are dispatched as standard Agent calls in parallel with the persona agents. Give them the same review context bundle the personas receive: entry mode, any PR metadata gathered in Stage 1, intent summary, review base branch name when known, `BASE:` marker, file list, diff, and `UNTRACKED:` scope notes. Do not invoke them with a generic "review this" prompt. Their output is unstructured and synthesized separately in Stage 6.
 
-**CE conditional agents** (schema-drift-detector, deployment-verification-agent) are also dispatched as standard Agent calls when applicable. Pass the same review context bundle plus the applicability reason (for example, which migration files triggered the agent). For schema-drift-detector specifically, pass the resolved review base branch explicitly so it never assumes `main`. Their output is unstructured and must be preserved for Stage 6 synthesis just like the CE always-on agents.
+**CE conditional agents** (design-conformance-reviewer, schema-drift-detector, deployment-verification-agent, zip-agent-validator) are also dispatched as standard Agent calls when applicable. Pass the same review context bundle plus the applicability reason (for example, which migration files triggered the agent, which design docs were found, or that the PR URL matched `git.zoominfo.com`). For schema-drift-detector specifically, pass the resolved review base branch explicitly so it never assumes `main`. For zip-agent-validator, pass the full PR URL and the PR number so it can fetch comments from the GHE API. Their output is unstructured and must be preserved for Stage 6 synthesis just like the CE always-on agents.
 
 ### Stage 5: Merge findings
 
@@ -475,7 +477,7 @@ Convert multiple reviewer compact JSON returns into one deduplicated, confidence
    - report-only queue: `advisory` findings plus anything owned by `human` or `release`
 9. **Sort.** Order by severity (P0 first) -> confidence (descending) -> file path -> line number.
 10. **Collect coverage data.** Union residual_risks and testing_gaps across reviewers.
-11. **Preserve CE agent artifacts.** Keep the learnings, agent-native, schema-drift, and deployment-verification outputs alongside the merged finding set. Do not drop unstructured agent output just because it does not match the persona JSON schema.
+11. **Preserve CE agent artifacts.** Keep the learnings, agent-native, design-conformance, schema-drift, deployment-verification, and zip-agent-validator outputs alongside the merged finding set. Do not drop unstructured agent output just because it does not match the persona JSON schema. For zip-agent-validator specifically, its validated findings use the standard findings schema and enter the merge pipeline (steps 1-7) like persona findings. Its `residual_risks` entries (collapsed zip-agent comments) are preserved separately for the Zip Agent Validation section in Stage 6.
 
 ### Stage 6: Synthesize and present
 
@@ -494,8 +496,9 @@ Assemble the final report using **pipe-delimited markdown tables for findings**
 8. **Agent-Native Gaps.** Surface agent-native-reviewer results. Omit section if no gaps found.
 9. **Schema Drift Check.** If schema-drift-detector ran, summarize whether drift was found. If drift exists, list the unrelated schema objects and the required cleanup command. If clean, say so briefly.
 10. **Deployment Notes.** If deployment-verification-agent ran, surface the key Go/No-Go items: blocking pre-deploy checks, the most important verification queries, rollback caveats, and monitoring focus areas. Keep the checklist actionable rather than dropping it into Coverage.
-11. **Coverage.** Suppressed count, residual risks, testing gaps, failed/timed-out reviewers, and any intent uncertainty carried by non-interactive modes.
-12. **Verdict.** Ready to merge / Ready with fixes / Not ready. Fix order if applicable. When an `explicit` plan has unaddressed requirements, the verdict must reflect it — a PR that's code-clean but missing planned requirements is "Not ready" unless the omission is intentional. When an `inferred` plan has unaddressed requirements, note it in the verdict reasoning but do not block on it alone.
+11. **Zip Agent Validation.** If zip-agent-validator ran, summarize the results: how many zip-agent comments were evaluated, how many validated (these appear as findings in the severity-grouped tables above), and how many collapsed with reasons. This section provides traceability -- reviewers can see that zip-agent comments were evaluated, not ignored.
+12. **Coverage.** Suppressed count, residual risks, testing gaps, failed/timed-out reviewers, and any intent uncertainty carried by non-interactive modes.
+13. **Verdict.** Ready to merge / Ready with fixes / Not ready. Fix order if applicable. When an `explicit` plan has unaddressed requirements, the verdict must reflect it — a PR that's code-clean but missing planned requirements is "Not ready" unless the omission is intentional. When an `inferred` plan has unaddressed requirements, note it in the verdict reasoning but do not block on it alone.
 
 Do not include time estimates.