buildanything 1.7.1 → 2.0.0

package/commands/fix.md

@@ -9,6 +9,15 @@ Input: $ARGUMENTS
 
 ---
 
+## Project-type branching
+
+Read `docs/plans/.build-state.md` → `project_type`.
+
+- **If `project_type=web`** (or unset): continue with the web flow below (Steps 1-5, unchanged).
+- **If `project_type=ios`**: jump to **§ iOS Fix (project_type=ios)** at the bottom of this file and run that twin instead. Do not run the web steps.
+
+---
+
 ## Step 1: Scope the Bug
 
 Parse the user's description. Identify:
@@ -87,3 +96,59 @@ State concisely:
 - **Cause**: why it was broken (one sentence)
 - **Fix**: what was changed and in which files
 - **Evidence**: before and after screenshots taken in Steps 2 and 4
+
+---
+
+## iOS Fix (project_type=ios)
+
+Load `protocols/ios-context.md` as your persona. Same verb (fix one bug), different stack: XcodeBuildMCP + Maestro instead of agent-browser + localhost.
+
+### i1. Preflight
+**Run iOS preflight:** see `protocols/ios-preflight.md`. If any check fails, stop and report — do not try to scaffold.
+
+### i2. Reproduce
+- Boot the target simulator via XcodeBuildMCP.
+- Install + launch the app (`BuildProject` if needed, then install the `.app`).
+- Trigger the bug via ONE of:
+  1. **Existing Maestro flow** — replay the failing flow in `maestro/` if one exists.
+  2. **Ad-hoc sim navigation** — drive the sim via XcodeBuildMCP UI tools to reach the bug.
+  3. **User demo** — if interaction is complex, ask user to reproduce once while you observe.
+- Capture evidence: sim screenshot (`before-fix.png`) + crash log / console output (if any) via XcodeBuildMCP.
+- If the bug cannot be reproduced: save screenshot, report observed state, stop.
+
+### i3. Classify
+Match the symptom to exactly one row. Dispatch the skill in the rightmost column.
+
+| Symptom | Classification | Fix skill / agent |
+|---|---|---|
+| View renders wrong, modifier order, missing `@State`/`@Binding`, layout broken | SwiftUI bug | `skills/ios/swiftui-pro` |
+| Data race, actor isolation warning, `Sendable` violation, hang on main | Concurrency | `skills/ios/swift-concurrency` |
+| `@Query` not updating, predicate wrong, migration failure, CloudKit sync | SwiftData | `skills/ios/swiftdata-pro` |
+| VoiceOver silent/wrong, Dynamic Type clipping, contrast fail, Reduce Motion ignored | Accessibility | `skills/ios/swift-accessibility` |
+| Touch target <44pt, no dark mode, hard-coded padding, HIG violation | HIG | `skills/ios/hig-foundations` |
+| Build fails, signing error, entitlement / Info.plist / provisioning | Build/infra | dispatch `build-error-resolver` agent |
+| Keychain/Crypto misuse, ATS exception, insecure storage, secret leak | Security | `skills/ios/swift-security-expert` |
+
+If symptom doesn't match any row, pick the closest and note the gap in the fix report.
+
+### i4. Fix
+Dispatch the classified skill with mode "bypassPermissions". Pass as input:
+- Bug description (from `$ARGUMENTS`)
+- Reproduction evidence (screenshot path, crash log excerpt)
+- Affected file(s) — scope tightly, do not dump the whole project
+- Expected behavior (one sentence)
+
+### i5. Verify loop
+1. `BuildProject` via XcodeBuildMCP — must succeed with zero warnings/errors.
+2. Re-install on sim, re-run the Maestro flow OR re-trigger via sim nav.
+3. Capture `after-fix.png` sim screenshot.
+4. Visual diff: compare before/after against expected.
+5. Spot-check one adjacent screen/flow for regression.
+6. If still failing → return to **i3. Classify** (bug may be mis-classified). **Max 3 fix-verify iterations** per locked plan; after that, report what's fixed, what remains, stop.
+
+### i6. Output
+Append to `docs/plans/.build-state.md`:
+- **Bug**: what was broken
+- **Classification**: which row from i3
+- **Fix**: files changed + skill used
+- **Evidence**: `before-fix.png`, `after-fix.png`, build status

package/commands/self-check.md

@@ -0,0 +1,121 @@
+---
+description: "Plugin maintainer self-check — runs schema sanity, manifest sync, V.H.P. regression proof, and silent-skip detection before publish"
+---
+
+# /buildanything:self-check
+
+Run before `git push` / `npm publish` to catch plugin regressions locally. Takes ~10-30 seconds.
+
+This is **plugin-maintainer tooling**, not a user-facing build command. It does not build any user project; it validates the plugin itself. Zero external dependencies — no git hosting, no CI, no nightly runs. Just one command, executed on the maintainer's laptop.
+
+## What it checks
+
+Four sequential checks, **stop on first FAIL** (except Check 3, which may SKIP without failing if its fixture is unavailable):
+
+1. **Schema sanity** — every protocol and command file parses cleanly and all cross-references resolve.
+2. **Manifest sync** — agent count on disk matches the claim in `.claude-plugin/plugin.json`.
+3. **V.H.P. regression check** — the Layer C stub detector still flags a known-stub Swift test file from the capdotai project. This is the deterministic proof that the V.H.P. fix still works.
+4. **Silent-skip detection** — no forbidden "skip silently" phrases have been reintroduced into the protocols.
+
+You are the orchestrator. Run each check via the Bash tool, record the result, and proceed to the next unless a FAIL aborts the run.
+
+---
+
+## Check 1: Schema Sanity
+
+**Goal:** every file in `protocols/` and `commands/` parses as valid markdown with valid cross-references.
+
+For every file in `/Users/sujit/projects/oneshot-claude-plugin/protocols/*.md`:
+
+1. First non-blank line must start with `# ` (top-level heading).
+2. Count of ` ``` ` (triple-backtick) fences must be even — no unclosed code fences.
+
+For every file in `/Users/sujit/projects/oneshot-claude-plugin/commands/*.md`:
+
+1. Must begin with a `---` frontmatter block that contains a `description:` field. `argument-hint:` is optional.
+2. Must have at least one `# ` heading after the frontmatter.
+3. Same even-count rule for code fences.
+
+For every protocol and command file, grep for references of the form `protocols/<name>.md` and `commands/<name>.md`. For each match, resolve the target relative to the plugin root and confirm the file exists on disk. A broken reference is a FAIL.
+
+Use Bash + Grep for the walk. Report PASS with file counts (e.g., `PASS — 15 protocols, 10 commands, 47 cross-refs, all resolve`) or FAIL with the offending file and specific reason.
+
+---
+
+## Check 2: Manifest Sync
+
+**Goal:** the on-disk agent roster matches the plugin's advertised count.
+
+1. Run `ls /Users/sujit/projects/oneshot-claude-plugin/agents/ | wc -l` to get the actual count.
+2. Read `/Users/sujit/projects/oneshot-claude-plugin/.claude-plugin/plugin.json` and extract any integer from the `description` field (e.g., "73 specialist agents"). If `plugin.json` has a dedicated `agent_count` field, prefer that.
+3. If the two numbers disagree, FAIL with both values.
+4. If no agent count is claimed anywhere in `plugin.json`, report PASS with a warning: `PASS — 44 agents on disk, no claim in manifest to check against`.
+
+Report format: `PASS — 44 agents on disk, manifest claims 44` or `FAIL — 44 agents on disk, manifest claims 73`.
+
+---
+
+## Check 3: V.H.P. Regression Check
+
+**Goal:** prove that the V.H.P. Layer C stub detector still correctly flags Apple-template Swift test files as STUB. This is the deterministic regression proof that the verification fix is intact.
+
+**Fixture dependency:** this check requires `/Users/sujit/projects/capdotai/cap/capTests/capTests.swift` to exist on disk. If the fixture path is missing (the maintainer doesn't have capdotai checked out), **SKIP this check** with the explanatory note `SKIPPED — capdotai fixture not present at /Users/sujit/projects/capdotai/; clone capdotai locally to enable V.H.P. regression proof`. A SKIP here does NOT cause the overall self-check to fail — it's a legitimate absence, not a regression.
+
+**If the fixture exists**, run the Layer C stub detector heuristic against it:
+
+1. **File size:** `wc -c < /Users/sujit/projects/capdotai/cap/capTests/capTests.swift`. A real test file is ≥ 500 bytes. Smaller → stub signal.
+2. **Apple template markers:** grep (case-sensitive) for any of: `Write your test here`, `Swift Testing Documentation`, `developer.apple.com/documentation/testing`. Any match → stub signal.
+3. **Assertion count:** count occurrences of `#expect(` and `#require(` (Swift Testing) plus `XCTAssert` (XCTest). Zero → stub signal.
+
+A file is a STUB if it trips **all three** signals simultaneously (size < 500 AND template markers present AND zero assertions).
+
+Known fixture state: `capTests.swift` is 358 bytes, contains `Write your test here` and `Swift Testing Documentation`, and has zero `#expect` / `#require` / `XCTAssert` calls. The detector MUST classify it as STUB.
+
+- If the detector correctly classifies it as STUB → PASS. Report: `PASS — detector correctly flagged capdotai/capTests.swift as STUB (358 bytes, 2 template markers, 0 assertions)`.
+- If the detector classifies it as NOT-STUB → **FAIL**. Report: `FAIL — V.H.P. regression: detector did NOT flag capdotai/capTests.swift as STUB. The verification fix is broken.` This is the loudest failure in the entire self-check because a silent regression here means user builds will ship untested code.
+
+---
+
+## Check 4: Silent-Skip Detection
+
+**Goal:** no forbidden "skip silently" phrases have been reintroduced into the protocol prose.
+
+Grep every file in `/Users/sujit/projects/oneshot-claude-plugin/protocols/*.md` (case-insensitive) for each of the following forbidden phrases:
+
+- `do not block the build`
+- `skipped check counts as pass`
+- `otherwise skip`
+
+Use Grep with `-i` (case-insensitive) and output-mode content to capture file + line number for any match.
+
+- If zero matches → PASS. Report: `PASS — no silent-skip phrases found in protocols/`.
+- If any match → FAIL. Report: `FAIL — silent-skip phrase "<phrase>" found in protocols/<file>.md:<line>`. Include the full offending line so the maintainer can locate and fix it.
+
+The `otherwise skip` check is specifically for autonomous-mode contexts (i.e., the surrounding prose should be about autonomous / unattended behavior). If a match appears in a non-autonomous context (e.g., user-instruction flow where "otherwise skip" means "if the user declines, skip"), note it in the report but still FAIL — any reintroduction deserves human review.
+
+---
+
+## Output format
+
+For each check, emit one line with the check name, verdict, and one-sentence reason:
+
+```
+Check 1 — Schema Sanity:        PASS — 15 protocols, 10 commands, 47 cross-refs, all resolve
+Check 2 — Manifest Sync:        PASS — 44 agents on disk, no claim in manifest to check against
+Check 3 — V.H.P. Regression:    PASS — detector correctly flagged capdotai/capTests.swift as STUB (358 bytes, 2 markers, 0 assertions)
+Check 4 — Silent-Skip:          PASS — no silent-skip phrases found in protocols/
+```
+
+At the end, emit one of:
+
+- `SELF-CHECK PASS (4/4)` — all four checks passed (or Check 3 SKIPPED, others passed → `SELF-CHECK PASS (3/4, Check 3 SKIPPED)`).
+- `SELF-CHECK FAIL: Check <N> — <one-line reason>` — the first check that failed.
+
+---
+
+## Exit conditions
+
+- **Stop on first FAIL.** The moment any check returns FAIL, emit the per-check results gathered so far, emit the overall `SELF-CHECK FAIL` verdict, and stop. Do not continue to later checks — a failing plugin should not ship, and running the rest wastes time when the maintainer needs to fix the first failure.
+- **Report all results up to and including the failure.** If Check 3 fails, still print Check 1 and Check 2 results.
+- **Check 3 SKIPPED is not a failure.** If the capdotai fixture is missing, Check 3 reports SKIPPED, and the run proceeds to Check 4. The overall verdict is `SELF-CHECK PASS (3/4, Check 3 SKIPPED)` iff Checks 1, 2, and 4 all pass.
+- **Final verdict goes last.** Always end the output with the single `SELF-CHECK PASS` or `SELF-CHECK FAIL` line so the maintainer's eye lands on it immediately.

package/commands/setup.md

@@ -0,0 +1,114 @@
+---
+description: "Install buildanything's external dependencies — tsx, companion plugins, agent-browser CLI, Chrome for Testing, skills, and optional iOS toolchain (XcodeBuildMCP, apple-docs-mcp, Maestro)"
+---
+
+# Setup
+
+You are installing buildanything's external dependencies. The plugin itself is already installed (that's how this command is running), but the companion plugins, CLI tools, and skills it depends on are not — they need to be installed separately. This command does that in one shot.
+
+**iOS project?** If the user's intent is to build an iOS app, also run Steps 7–9 below. Skip them otherwise.
+
+Run every step below. Each step is idempotent: check first, install only if missing, continue on failure. Collect results as you go and report them all at the end.
+
+## Step 1: Install companion plugins from `claude-plugins-official`
+
+For each plugin below, run `claude plugin install <name>@claude-plugins-official`. If the command fails, record the failure and continue — do NOT abort.
+
+| Plugin | Purpose |
+|--------|---------|
+| `feature-dev` | code-architect, code-explorer, code-reviewer |
+| `pr-review-toolkit` | silent-failure-hunter, code-simplifier, type-design-analyzer |
+| `code-review` | final code review passes |
+| `commit-commands` | clean git commits |
+| `playwright` | browser automation for design research and visual QA |
+
+For each one, treat a non-zero exit as "already installed or failed" — record it as `skipped` and keep going. Treat a success as `installed`.
+
+## Step 2: Install `tsx` globally
+
+`tsx` is required by all plugin hooks (pre-tool-use, subagent-start, subagent-stop, session-start cache compiler). Hooks call `npx --no-install tsx` and silently degrade if tsx is missing.
+
+1. Run `which tsx`. If it returns a path, record as `already present` and skip to Step 3.
+2. Otherwise run `npm install -g tsx`. Record `installed` or `failed` based on exit status.
+
+## Step 3: Install the `agent-browser` CLI globally
+
+1. Run `which agent-browser`. If it returns a path, record as `already present` and skip to Step 4.
+2. Otherwise run `npm install -g agent-browser`. Record `installed` or `failed` based on exit status.
+
+## Step 4: Download Chrome for Testing
+
+Run `agent-browser install`. This downloads a pinned Chrome build. If `agent-browser` isn't on PATH (Step 2 failed), record `skipped (agent-browser CLI missing)` and continue. Otherwise record `ready` or `failed`.
+
+Note: this is safe to re-run — `agent-browser install` no-ops if Chrome is already downloaded.
+
+## Step 5: Install the `agent-browser` skill
+
+Run `npx skills add vercel-labs/agent-browser`. Record `installed` or `failed`.
+
+## Step 6: Install the `dogfood` skill
+
+Run `npx skills add vercel-labs/agent-browser --skill dogfood`. Record `installed` or `failed`.
+
+---
+
+## Step 7: Install iOS MCP servers _(iOS only)_
+
+For each MCP server below, run `claude mcp list` first. If the name already appears, record `already configured`. Otherwise run the install command and record `configured` or `failed`.
+
+| MCP | Install command | Purpose |
+|-----|-----------------|---------|
+| `xcodebuildmcp` | `claude mcp add xcodebuildmcp -- npx -y xcodebuildmcp@latest` | Xcode build, simulator, scheme discovery, plist editing |
+| `apple-docs` | `claude mcp add apple-docs -- npx -y apple-docs-mcp@latest` | Live Apple developer documentation and API lookup |
+
+If either fails: record the failure with the exact manual-install command.
+
+## Step 8: Install Maestro _(iOS only)_
+
+Maestro runs E2E flow YAML tests against a booted iOS simulator.
+
+1. Run `which maestro`. If present, record `already installed`.
+2. Otherwise run `brew install maestro`. Record `installed` or `failed`.
+3. If `brew` is missing, record `skipped — install Homebrew first (brew.sh), then: brew install maestro`.
+
+## Step 9: Verify iOS toolchain _(iOS only)_
+
+Run `xcodebuild -version`. Record the version string. If not found, warn: "Xcode 26.3+ required — install from the Mac App Store."
+
+---
+
+## Report
+
+Print a single summary block with three sections:
+
+```
+buildanything setup complete.
+
+Already present:
+  - <item>
+  - <item>
+
+Installed:
+  - <item>
+  - <item>
+
+Failed:
+  - <item> — retry with: <exact command>
+  - <item> — retry with: <exact command>
+```
+
+Omit any section that has no entries. For every item in the `Failed` section, include the exact manual-install command the user can run themselves. If everything succeeded or was already present, print only a one-line success message instead of the full block.
+
+After the summary, print this reminder:
+
+```
+Next: restart Claude Code so newly installed plugins and MCP servers load.
+Then try:
+  /buildanything:build <your idea>       — full product pipeline
+  /buildanything:idea-sweep <your idea>  — parallel research sweep
+```
+
+If iOS steps were run, also print:
+```
+iOS: after restarting, confirm mcp__xcodebuildmcp__ and mcp__apple-docs__ tools appear.
+```

package/commands/ux-review.md

@@ -11,6 +11,15 @@ You are a UX engineer. Your job: find visual and interaction problems in the liv
 
 ---
 
+## Project-type branching
+
+Read `docs/plans/.build-state.md` → `project_type`.
+
+- **If `project_type=web`** (or unset): follow Steps 1-5 below (existing web flow, unchanged).
+- **If `project_type=ios`**: skip Steps 1-5. Run the iOS UX Review twin (§ iOS UX Review at the bottom of this file). iOS has no `/design-system` route — HIG + a synthesized design board are the reference.
+
+---
+
 ## Step 1: Determine Scope
 
 Parse `$ARGUMENTS`:
@@ -79,3 +88,57 @@ Present a summary:
 For deferred issues, explain why (e.g., requires design decision, backend change needed).
 
 Close the browser. Done.
+
+---
+
+## iOS UX Review (project_type=ios)
+
+iOS has no `/design-system` component gallery. The reference surface is **Apple HIG + a synthesized design board** (competitor screenshots + app vibe). Inherit the Senior iOS Engineer persona from `protocols/ios-context.md` for every dispatched agent.
+
+### Step 1: Preflight
+
+**Run iOS preflight:** see `protocols/ios-preflight.md`. Then read app vibe words + category from `docs/plans/.build-state.md` (captured in Phase 3).
+
+### Step 2: Design Board (read-only)
+
+The design board is GENERATED by `/buildanything:build` Phase 3 Step 3.1 — this command only READS it.
+
+- If `docs/plans/ios-design-board.md` does NOT exist: **HALT** and instruct the user to run `/buildanything:build` Phase 3 first. Do not regenerate here.
+- If it exists: use it as-is. Do NOT re-scrape references. **Cache rule:** to refresh the board, the user must delete `docs/plans/ios-design-board.md` and re-run Phase 3.
+
+### Step 3: Capture Current State
+
+Via XcodeBuildMCP:
+1. Boot simulator (default: iPhone 17 Pro, iOS 26.x)
+2. Build + launch app
+3. Walk the primary user flow; capture simulator screenshots for each screen in scope
+4. Save to `docs/plans/ios-ux-review/screens/` with timestamped filenames
+
+For scoped reviews (single screen/issue from `$ARGUMENTS`), capture only that screen.
+
+### Step 4: Dispatch Review Skills (parallel-safe)
+
+Run all four in parallel, each inheriting `protocols/ios-context.md`:
+
+a. **`skills/ios/ios-debugger-agent`** — simulator screenshot sweep + UI state capture + console/log scrape for runtime UI warnings.
+b. **`skills/ios/hig-foundations`** (audit mode) — HIG severity audit across color, typography, SF Symbols, dark mode, layout, motion. Return findings framed as **P0** (blocker / ships broken), **P1** (fix-before-ship), **P2** (polish).
+c. **`skills/ios/swift-accessibility`** (Mode 3: audit pass) — VoiceOver labels, Dynamic Type scaling, contrast ratios, hit-target sizes across all SwiftUI screens in scope.
+d. **`skills/ios/swiftui-design-principles`** — 10-rule visual polish checklist (spacing, hierarchy, alignment, color, type, motion, consistency, affordance, feedback, restraint).
+e. **`skills/ios/writing-for-interfaces`** — microcopy + tone review. Audit button labels, error messages, empty states, alerts, permission prompts, and navigation titles for clarity, brevity, and tone consistency.
+
+### Step 5: Compare Against Design Board
+
+Diff live simulator screenshots against `docs/plans/ios-design-board.md`:
+- Where does the live app match the board's vibe / patterns?
+- Where does it drift (color, spacing, hierarchy, type, navigation model)?
+- Which board patterns are NOT yet implemented but should be?
+
+### Step 6: Output Report
+
+Write `docs/plans/ios-ux-review-report.md`:
+
+| Finding | Severity | Screen | Source | Recommended Fix |
+|---------|----------|--------|--------|-----------------|
+| ... | P0/P1/P2 | ContentView | hig / a11y / principles / board-diff | one-line fix |
+
+Include: summary counts per severity, top 3 fixes to do next, list of screens reviewed, path to design board. Do NOT auto-fix — `/fix` (iOS branch) consumes this report.

package/commands/verify.md

@@ -7,6 +7,13 @@ argument-hint: "Optional scope: 'build', 'tests', 'security', 'lint', 'types', '
 
 You are a verification runner. Fast, deterministic, no opinions — just pass/fail.
 
+## Project-type branching
+
+Read `docs/plans/.build-state.md` → `project_type`.
+
+- **If `project_type=web`** (or unset): run the existing web flow below (Steps 1–3).
+- **If `project_type=ios`**: skip Steps 1–3 and jump to the **iOS Verify** section at the bottom of this file.
+
 ## Step 1: Determine Scope
 
 Check the user's argument:
@@ -41,3 +48,65 @@ Follow `protocols/verify.md` exactly:
 > "Verification failed at [check]. Run `/buildanything:build` with a fix prompt, or I can attempt a targeted fix now."
 
 Do not auto-fix unless the user asks. This command is for reporting, not repairing.
+
+---
+
+## iOS Verify (project_type=ios)
+
+iOS functional-correctness twin. Runs a sequential skill bundle (not parallel — each pass feeds the next) over the Xcode project. No 0-100 scoring — pass/fail gates only.
+
+### Preflight
+
+**Run iOS preflight:** see `protocols/ios-preflight.md`. If any preflight check fails, emit `VERIFY: FAIL at preflight — [reason]` and stop.
+
+### Load context
+
+Every dispatched agent below inherits `protocols/ios-context.md` (Senior iOS Engineer sidecar). Inject it as the first block of each agent prompt.
+
+### Dispatch sequence (sequential)
+
+Run in order. Stop on first hard blocker; soft findings accumulate into the report.
+
+**a. Test triage + snapshot/doubles review — `skills/ios/swift-testing-expert`**
+> Load `protocols/ios-context.md`. Triage existing `@Test` / XCTest suites: parallel-safety, isolation correctness, missing coverage on critical paths, test-plan wiring. Also review snapshot tests and Fowler-style test doubles for correctness, isolation, and coverage gaps. Output: list of test + snapshot/doubles issues with severity.
+
+**b. Security audit — `skills/ios/swift-security-expert` (audit mode)**
+> Load `protocols/ios-context.md`. Audit Keychain usage, CryptoKit calls, ATS exceptions in Info.plist, biometric gating. Report any hardcoded secrets or weak primitives. Severity: P0 / P1 / P2.
+
+**c. App Review compliance — `agents/ios-app-review-guardian`**
+> Load `protocols/ios-context.md`. Check App Review guidelines, privacy manifest (`PrivacyInfo.xcprivacy`), IAP/StoreKit rules, required usage-description strings, tracking/ATT compliance. Report blockers vs. warnings.
+
+**d. Maestro flow authoring — `skills/ios/ios-maestro-flow-author`** _(conditional)_
+> If a critical user journey lacks E2E coverage, author a `.yaml` Maestro flow for it. Skip if coverage is adequate.
+
+**e. Build + test run — XcodeBuildMCP**
+> `BuildProject` all targets → run the active test plan via XcodeBuildMCP → capture failures, warnings, and test output. This is the hard gate.
+
+### Pass/fail gates
+
+All must pass for `VERIFY: PASS`:
+
+| Gate | Pass condition |
+|------|----------------|
+| Build | XcodeBuildMCP `BuildProject` succeeds, zero errors |
+| Tests | All tests in active test plan pass |
+| Security audit | No P0 findings from `swift-security-expert` |
+| App Review | No blockers from `ios-app-review-guardian` (warnings OK) |
+| A11y warnings | No new a11y warnings introduced since last verify |
+
+Any gate failing → `VERIFY: FAIL at [gate] — [reason]`.
+
+### Output
+
+Write `docs/plans/ios-verify-report.md` with:
+
+- One-line pass/fail summary
+- Per-agent section (testing, security, app-review, maestro, build)
+- Findings list grouped by severity (P0/P1/P2)
+- Diff vs. previous report if one exists
+
+Log the final line to `docs/plans/.build-state.md` the same way web mode does.
+
+### Note on Step 6.0 (Pre-Hardening Verification)
+
+Step 6.0 references `protocols/verify.md` which auto-branches on `project_type`. iOS builds flow through the iOS twin section of this file. No separate Step 6.0 action needed for iOS.