!bash "${CLAUDE_SKILL_DIR}/../../hooks/yaml-helper.sh" resolve_config --keys automation,workflow,system_overrides

Review All GDDs

This skill reads every system GDD simultaneously and performs two complementary reviews that cannot be done per-GDD in isolation:

1. Cross-GDD Consistency — contradictions, stale references, and ownership conflicts between documents
2. Game Design Holism — issues that only emerge when you see all systems together: dominant strategies, broken economies, cognitive overload, pillar drift, competing progression loops

This is distinct from /design-review, which reviews one GDD for internal completeness. This skill reviews the relationships between all GDDs.

When to run:

• After all MVP-tier GDDs are individually approved
• After any GDD is significantly revised mid-production
• Before /create-architecture begins (architecture built on inconsistent GDDs inherits those inconsistencies)

Every AskUserQuestion call follows .claude/docs/automation-modes.md (collaborative asks always · guided major-only · autonomous logs and proceeds; automation_always_ask categories always prompt).

Argument modes:

Focus: $ARGUMENTS[0] (blank = full)

• No argument / full: Both consistency and design theory passes
• consistency: Cross-GDD consistency checks only (faster)
• design-theory: Game design holism checks only
• since-last-review: Only GDDs modified since the last review report (git-based)

workflow per GDD (per .claude/docs/workflow-modes.md): each GDD validates against its effective tier — the project value, overridden per system by the system_overrides row for that system when the block lists one. At full, validate all 8 sections across all GDDs. At standard, validate the 5 required sections; optional sections (Player Fantasy, Tuning Knobs, conditional Formulas) are surfaced as advisory only. At minimal, this skill is not applicable (no GDDs).

Phase 1: Load Everything

Phase 1a — L0: Summary Scan (fast, low tokens)

Before reading any full document, use Grep to extract ## Summary sections from all GDD files:

Grep pattern="## Summary" glob="design/gdd/*.md" output_mode="content" -A 5

Fail open on a missing Summary. Establish the denominator: glob design/gdd/*.md and count N. A scan matching fewer than N means those GDDs predate ## Summary — never treat an absent Summary as a system out of scope. A zero-match scan means "no GDD carries a Summary yet", not "nothing to review". This review is holistic and loads its in-scope GDDs regardless (see Phase 1c); the Summary scan only builds the manifest and narrows since-last-review, it never shrinks the review set.

Display a manifest to the user:

Found [N] GDDs. Summaries:
  • combat.md — [summary text]
  • inventory.md — [summary text]
  ...

For since-last-review mode, compute the scope deterministically instead of reasoning through git history:

Bash: bash .claude/scripts/review-scope.sh

It prints PRIOR_REVIEW:, a CHANGED: list, and a DEPS ...: list of each changed GDD's declared dependencies. Use those lists as the scope — the dependency lines are already the "Key deps" expansion, so no second pass is needed. If PRIOR_REVIEW: NONE, a full review is required; fall back to full mode.

Show the user which GDDs are in scope based on summaries before doing any full reads. Only proceed to L1 for the CHANGED set plus the GDDs named on the DEPS lines.

Phase 1b — Registry Pre-Load (fast baseline)

Before full-reading any GDD, check for the entity registry:

Read path="design/registry/entities.yaml"

If the registry exists and has entries, use it as a pre-built conflict baseline: known entities, items, formulas, and constants with their authoritative values and source GDDs. In Phase 2, grep GDDs for registered names first — this is faster than reading all GDDs in full before knowing what to look for.

If the registry is empty or absent: proceed without it. Note in the report: "Entity registry is empty — consistency checks rely on full GDD reads only. Run /consistency-check after this review to populate the registry."

Phase 1c — L1/L2: Section Load

Read whole (small, and every part is used):

1. design/gdd/game-concept.md — game vision, core loop, MVP definition
2. design/gdd/game-pillars.md if it exists — design pillars and anti-pillars
3. design/gdd/systems-index.md — authoritative system list, layers, dependencies, status

Then, for every in-scope system GDD, load the sections this review actually consumes — not the whole file:

Grep pattern="^## (Dependencies|Detailed Rules|Detailed Design|Formulas|Tuning Knobs|Acceptance Criteria|Player Fantasy)" glob="design/gdd/*.md" output_mode="content" -A 40

That list is not a guess — it is exactly the union the Parallel Execution contract below already enumerates: Phase 2 needs Dependencies, Detailed Design/Rules, Formulas, Tuning Knobs and Acceptance Criteria; Phase 3 needs Player Fantasy and progression/reward structure. Overview is narrative restated by the Summary this skill already scanned in Phase 1a, and Edge Cases feeds no checklist item here (/design-review owns per-GDD completeness). Loading them put content in three context windows — this one and both sub-agents' — that no checklist item ever read.

Accept either ## Detailed Rules or ## Detailed Design; the design standard and the GDD template disagree on the name and they denote the same section.

Escalate to a full read of one GDD when a scanned section cross-references material outside itself, or when a GDD matched zero sections — that GDD predates the template, and a zero-match there means "unstructured", not "empty". Never let a zero-match silently drop a system: the scan narrows the read, it never shrinks the review set.

Report: "Loaded [N] system GDDs covering [M] systems. Pillars: [list]. Anti-pillars: [list]."

If fewer than 2 system GDDs exist, stop:

"Cross-GDD review requires at least 2 system GDDs. Write more GDDs first, then re-run /review-all-gdds."

Parallel Execution

Phase 2 (Consistency) and Phase 3 (Design Theory) are independent — they read the same GDD inputs but produce separate reports. Spawn both as parallel Agent agents simultaneously rather than waiting for Phase 2 to complete before starting Phase 3. Collect both results before writing the combined report.

Spawn both as game-designer sub-agents (subagent_type: game-designer) — GDD consistency and design-theory review is its domain.

When spawning the Phase 2 and Phase 3 agents, always pass:

• The loaded GDD content each phase needs — not file paths. Paste the sections; the sub-agent has its own context and cannot re-read Phase 1's results, so a path forces a full re-read (and contradicts the "do not re-read" rule below). Pass only the phase's slice: Phase 2 (consistency) needs each GDD's Dependencies, Detailed Design/Rules, Formulas, Tuning Knobs and Acceptance Criteria; Phase 3 (design theory) needs Player Fantasy, progression/reward structure and the game pillars.
• The full TR registry contents if loaded in Phase 1b (paste the registry text, not just a file path)
• The specific checklist items assigned to that agent's phase (Phase 2 gets 2a–2f; Phase 3 gets 3a–3g)
• The engine name and version — engine.name and engine.version from project.yaml, resolving each field independently (if its key is absent or empty, use .claude/docs/technical-preferences.md) — plus docs/engine-reference/[engine]/VERSION.md

Do not rely on the subagent to re-read these files — it has its own context window and cannot access Phase 1 results unless they are explicitly passed in the Agent prompt.

Phase 2: Cross-GDD Consistency

Work through every pair and group of GDDs to find contradictions and gaps.

2a: Dependency Bidirectionality

For every GDD's Dependencies section, check that every listed dependency is reciprocal:

• If GDD-A lists "depends on GDD-B", check that GDD-B lists GDD-A as a dependent
• If GDD-A lists "depended on by GDD-C", check that GDD-C lists GDD-A as a dependency
• Flag any one-directional dependency as a consistency issue

⚠️  Dependency Asymmetry
[system-a].md lists: Depends On → [system-b].md
[system-b].md does NOT list [system-a].md as a dependent
→ One of these documents has a stale dependency section

2b: Rule Contradictions

For each game rule, mechanic, or constraint defined in any GDD, check whether any other GDD defines a contradicting rule for the same situation:

Categories to scan:

• Floor/ceiling rules: Does any GDD define a minimum value for an output? Does any other say a different system can bypass that floor? These contradict.
• Resource ownership: If two GDDs both define how a shared resource accumulates or depletes, do they agree?
• State transitions: If GDD-A describes what happens when a character dies, does GDD-B's description of the same event agree?
• Timing: If GDD-A says "X happens on the same frame", does GDD-B assume it happens asynchronously?
• Stacking rules: If GDD-A says status effects stack, does GDD-B assume they don't?

🔴 Rule Contradiction
[system-a].md: "Minimum [output] after reduction is [floor_value]"
[system-b].md: "[mechanic] bypasses [system-a]'s rules and can reduce [output] to 0"
→ These rules directly contradict. Which GDD is authoritative?

2c: Stale References

Start from the ## Cross-References table where a GDD has one. That table is the document's own declaration of what it depends on — templates/game-design-document.md tells authors it is machine-checked here, and /design-system requires it whenever Dependencies names another GDD. For each row, confirm the Target GDD exists and the Specific Element Referenced is still present in it under that name, with the declared Nature still accurate.

A table that is absent, or still holding the template's bracketed examples, is itself reportable: say the GDD declares no cross-references and that the prose scan below was the only check applied. Do not treat an absent table as "no dependencies" — it far more often means the section was never authored.

Then scan the prose regardless, table or no table: a declared table catches what the author remembered, and the scan below catches what they did not.

For every cross-document reference (GDD-A mentions a mechanic, value, or system name from GDD-B), verify the referenced element still exists in GDD-B with the same name and behaviour:

• If GDD-A says "combo multiplier from the combat system feeds into score", check that the combat GDD actually defines a combo multiplier that outputs to score
• If GDD-A references "the progression curve defined in [system].md", check that [system].md actually has that curve, not a different progression model
• If GDD-A was written before GDD-B and assumed a mechanic that GDD-B later designed differently, flag GDD-A as containing a stale reference

⚠️  Stale Reference
inventory.md (written first): "Item weight uses the encumbrance formula
  from movement.md"
movement.md (written later): Defines no encumbrance formula — uses a flat
  carry limit instead
→ inventory.md references a formula that doesn't exist

2d: Data and Tuning Knob Ownership Conflicts

Two GDDs should not both claim to own the same data or tuning knob. Scan all Tuning Knobs sections across all GDDs and flag duplicates:

⚠️  Ownership Conflict
[system-a].md Tuning Knobs: "[multiplier_name] — controls [output] scaling"
[system-b].md Tuning Knobs: "[multiplier_name] — scales [output] with [factor]"
→ Two GDDs define multipliers on the same output. Which owns the final value?
  This will produce either a double-application bug or a design conflict.

2e: Formula Compatibility

For GDDs whose formulas are connected (output of one feeds input of another), check that the output range of the upstream formula is within the expected input range of the downstream formula:

• If [system-a].md outputs values between [min]–[max], and [system-b].md is designed to receive values between [min2]–[max2], is the mismatch intentional?
• If an economy GDD expects resource acquisition in range X, and the progression GDD generates it at range Y, the economy will be trivial or inaccessible — is that intended?

Flag incompatibilities as CONCERNS (design judgment needed, not necessarily wrong):

⚠️  Formula Range Mismatch
[system-a].md: Max [output] = [value_a] (at max [condition])
[system-b].md: Base [input] = [value_b], max [input] = [value_c]
→ Late-[stage] [scenario] can resolve in a single [event].
  Is this intentional? If not, either [system-a]'s ceiling or [system-b]'s ceiling needs adjustment.

2f: Acceptance Criteria Cross-Check

Scan Acceptance Criteria sections across all GDDs for contradictions:

• GDD-A criteria: "Player cannot die from a single hit"
• GDD-B criteria: "Boss attack deals 150% of player max health" These acceptance criteria cannot both pass simultaneously.

Phase 3: Game Design Holism

Review all GDDs together through the lens of game design theory and player psychology. These are issues that individual GDD reviews cannot catch because they require seeing all systems at once.

3a: Progression Loop Competition

A game should have one dominant progression loop that players feel is "the point" of the game, with supporting loops that feed into it. When multiple systems compete equally as the primary progression driver, players don't know what the game is about.

Scan all GDDs for systems that:

• Award the player's primary resource (XP, levels, prestige, unlocks)
• Define themselves as the "core" or "main" loop
• Have comparable depth and time investment to other systems doing the same

⚠️  Competing Progression Loops
combat.md: Awards XP, unlocks abilities, is described as "the core loop"
crafting.md: Awards XP, unlocks recipes, is described as "the primary activity"
exploration.md: Awards XP, unlocks map areas, described as "the main driver"
→ Three systems all claim to be the primary progression loop and all award
  the same primary currency. Players will optimise one and ignore the others.
  Consider: one primary loop with the others as support systems.

3b: Player Attention Budget

Count how many systems require active player attention simultaneously during a typical session. Each actively-managed system costs attention:

• Active = player must make decisions about this system regularly during play
• Passive = system runs automatically, player sees results but doesn't manage it

More than 3-4 simultaneously active systems creates cognitive overload for most players. Present the count and flag if it exceeds 4 concurrent active systems:

⚠️  Cognitive Load Risk
Simultaneously active systems during [core loop moment]:
  1. [system-a].md — [decision type] (active)
  2. [system-b].md — [resource management] (active)
  3. [system-c].md — [tracking] (active)
  4. [system-d].md — [item/action use] (active)
  5. [system-e].md — [cooldown/timer management] (active)
  6. [system-f].md — [coordination decisions] (active)
→ 6 simultaneously active systems during the core loop.
  Research suggests 3-4 is the comfortable limit for most players.
  Consider: which of these can be made passive or simplified?

3c: Dominant Strategy Detection

A dominant strategy makes other strategies irrelevant — players discover it, use it exclusively, and find the rest of the game boring. Look for:

• Resource monopolies: One strategy generates a resource significantly faster than all others
• Risk-free power: A strategy that is both high-reward and low-risk (if high-risk strategies exist, they need proportionally higher reward)
• No trade-offs: An option that is superior in all dimensions to all others
• Obvious optimal path: If any progression choice is "clearly correct", the others aren't real choices

⚠️  Potential Dominant Strategy
combat.md: Ranged attacks deal 80% of melee damage with no risk
combat.md: Melee attacks deal 100% damage but require close range
→ Unless melee has a significant compensating advantage (AOE, stagger,
  resource regeneration), ranged is dominant — higher safety, only 20% less
  damage. Consider what melee offers that ranged cannot.

3d: Economic Loop Analysis

Identify all resources across all GDDs (gold, XP, crafting materials, stamina, health, mana, etc.). For each resource, map its sources (how players gain it) and sinks (how players spend it).

Flag dangerous economic conditions:

🔴 Economic Imbalance: Unbounded Positive Feedback
gold economy:
  Sources: monster drops (scales with player power), merchant selling (unlimited)
  Sinks: equipment purchase (one-time), ability upgrades (finite count)
→ After equipment and abilities are purchased, gold has no sink.
  Infinite surplus. Gold becomes meaningless mid-game.
  Add ongoing gold sinks (upkeep, consumables, cosmetics, gambling).

3e: Difficulty Curve Consistency

When multiple systems scale with player progression, they must scale in compatible directions and at compatible rates. Mismatched scaling curves create unintended difficulty spikes or trivialisations.

For each system that scales over time, extract:

• What scales (enemy health, player damage, resource cost, area size)
• How it scales (linear, exponential, stepped)
• When it scales (level, time, area)

Compare all scaling curves. Flag mismatches:

⚠️  Difficulty Curve Mismatch
combat.md: Enemy health scales exponentially with area (×2 per area)
progression.md: Player damage scales linearly with level (+10% per level)
→ By area 5, enemies have 32× base health; player deals ~1.5× base damage.
  The gap widens indefinitely. Late areas will become inaccessibly difficult
  unless the curves are reconciled.

3f: Pillar Alignment

Every system should clearly serve at least one design pillar. A system that serves no pillar is "scope creep by design" — it's in the game but not in service of what the game is trying to be.

For each GDD system, check its Player Fantasy section against the design pillars. Flag any system whose stated fantasy doesn't map to any pillar:

⚠️  Pillar Drift
fishing-system.md: Player Fantasy — "peaceful, meditative activity"
Pillars: "Brutal Combat", "Tense Survival", "Emergent Stories"
→ The fishing system serves none of the three pillars. Either add a pillar
  that covers it, redesign it to serve an existing pillar, or cut it.

Also check anti-pillars — flag any system that does what an anti-pillar explicitly says the game will NOT do:

🔴 Anti-Pillar Violation
Anti-Pillar: "We will NOT have linear story progression — player defines their path"
main-quest.md: Defines a 12-chapter linear story with mandatory sequence
→ This system directly violates the defined anti-pillar.

3g: Player Fantasy Coherence

The player fantasies across all systems should be compatible — they should reinforce a consistent identity for what the player IS in this game. Conflicting player fantasies create identity confusion.

⚠️  Player Fantasy Conflict
combat.md: "You are a ruthless, precise warrior — every kill is earned"
dialogue.md: "You are a charismatic diplomat — violence is always avoidable"
exploration.md: "You are a reckless adventurer — diving in without a plan"
→ Three systems present incompatible identities. Players will feel the game
  doesn't know what it wants them to be. Consider: do these fantasies serve
  the same core identity from different angles, or do they genuinely conflict?

Phase 4: Cross-System Scenario Walkthrough

Walk through the game from the player's perspective to find problems that only appear at the interaction boundary between multiple systems — things static analysis of individual GDDs cannot surface.

4a: Identify Key Multi-System Moments

Scan all GDDs and identify the 3–5 most important player-facing moments where multiple systems activate simultaneously. Look specifically for:

• Combat + Economy overlap: killing enemies that drop resources, spending resources during combat, death/respawn interacting with economy state
• Progression + Difficulty overlap: level-up triggering mid-fight, ability unlocks changing combat viability, difficulty scaling at progression milestones
• Narrative + Gameplay overlap: dialogue choices locking/unlocking mechanics, story beats interrupting resource loops, quest completion triggering system state changes
• 3+ system chains: any player action that triggers System A, which feeds into System B, which triggers System C (these are highest-risk interaction paths)

List each identified scenario with a one-line description before proceeding.

4b: Walk Through Each Scenario

For each scenario, step through the sequence explicitly:

1. Trigger — what player action or game event starts this?
2. Activation order — which systems activate, in what sequence?
3. Data flow — what does each system output, and is that output a valid input for the next system in the chain?
4. Player experience — what does the player see, hear, or feel at each step?
5. Failure modes — are there any of the following?
   • Race conditions: two systems trying to modify the same state simultaneously
   • Feedback loops: System A amplifies System B which re-amplifies System A with no cap or dampener
   • Broken state transitions: a system assumes a state that a previous system may have changed (e.g., "player is alive" assumption after a combat step that could have caused death)
   • Contradictory messaging: player receives conflicting feedback from two systems reacting to the same event (e.g., "success" sound + "failure" UI)
   • Compounding difficulty spikes: two systems both scaling up at the same progression point, multiplying the intended difficulty increase
   • Reward conflicts: two systems both reacting to the same trigger with rewards that together exceed the intended value (double-dipping)
   • Undefined behavior: the GDDs don't specify what happens in this combined state (neither system's rules cover it)

Example walkthrough:
Scenario: Player kills elite enemy at level-up threshold during active quest

Trigger: Player lands killing blow on elite enemy
→ combat.md: awards kill XP (100 pts)
→ progression.md: XP total crosses level threshold → triggers level-up
  Output: new level, stat increases, ability unlock popup
→ quest.md: kill-count criterion met → triggers quest completion event
  Output: quest reward XP (500 pts), completion fanfare
→ progression.md (again): quest XP added → triggers SECOND level-up in same frame
  ⚠️  Data flow issue: quest.md awards XP without checking if a level-up
  is already in progress. progression.md has no guard against concurrent
  level-up events. Undefined behavior: does the player level up once or twice?
  Does the ability popup fire twice? Does the second level use the updated or
  pre-update stat baseline?

4c: Flag Scenario Issues

For each problem found during the walkthrough, categorize severity:

• BLOCKER: undefined behavior, broken state transition, or contradictory player messaging — the experience is broken or incoherent in this scenario
• WARNING: compounding spikes, feedback loops without caps, reward conflicts — the experience works but produces unintended outcomes
• INFO: minor ordering ambiguity or messaging overlap — worth noting but unlikely to cause player-visible problems

Add all findings to the output report under "Cross-System Scenario Issues". Each finding must cite: the scenario name, the specific systems involved, the step where the issue occurs, and the nature of the failure mode.

Phase 5: Output the Review Report

## Cross-GDD Review Report
Date: [date]
GDDs Reviewed: [N]
Systems Covered: [list]

---

### Consistency Issues

#### Blocking (must resolve before architecture begins)
🔴 [Issue title]
[What GDDs are involved, what the contradiction is, what needs to change]

#### Warnings (should resolve, but won't block)
⚠️  [Issue title]
[What GDDs are involved, what the concern is]

---

### Game Design Issues

#### Blocking
🔴 [Issue title]
[What the problem is, which GDDs are involved, design recommendation]

#### Warnings
⚠️  [Issue title]
[What the concern is, which GDDs are affected, recommendation]

---

### Cross-System Scenario Issues

Scenarios walked: [N]
[List scenario names]

#### Blockers
🔴 [Scenario name] — [Systems involved]
[Step where failure occurs, nature of the failure mode, what must be resolved]

#### Warnings
⚠️  [Scenario name] — [Systems involved]
[What the unintended outcome is, recommendation]

#### Info
ℹ️  [Scenario name] — [Systems involved]
[Minor ordering ambiguity or note]

---

### GDDs Flagged for Revision

| GDD | Reason | Type | Priority |
|-----|--------|------|----------|
| [system-a].md | Rule contradiction with [system-b].md | Consistency | Blocking |
| [system-c].md | Stale reference to nonexistent mechanic | Consistency | Blocking |
| [system-d].md | No pillar alignment | Design Theory | Warning |

---

### Verdict: [PASS / NOT ASSESSED / CONCERNS / FAIL]

PASS: No blocking issues. Warnings present but don't prevent architecture.
NOT ASSESSED: One or more review phases could not run — named below.
CONCERNS: Warnings present that should be resolved but are not blocking.
FAIL: One or more blocking issues must be resolved before architecture begins.

### If NOT ASSESSED — what could not be reviewed, and why:
[Name each phase that did not run and the input it needed]

### If FAIL — required actions before re-running:
[Specific list of what must change in which GDD]

NOT ASSESSED — a cross-review is only as wide as what it could read. Rank: above PASS, below CONCERNS and FAIL. This skill's whole value is comparing systems against each other, so it is unusually easy for it to look thorough while covering a fraction of the surface. Emit it when any of:

• Fewer than two GDDs were readable. Contradiction-hunting across one document is not a cross-review; a clean result there means only that nothing was compared. This is the single most important trigger in this skill.
• A whole review phase did not run — consistency, design theory, economy, pillar drift. A parallel phase that returned nothing has to be distinguished from one that returned no findings; if a spawned agent produced no report, that phase is NOT ASSESSED, not clean — an agent can return a fluent sentence, write nothing, and consume a phase.
• The design pillars are undefined, so pillar-drift has no reference to drift from — the same shape as an accessibility gate with no committed tier.
• A GDD is present but empty (headings only, or all placeholders). Present is not the same as reviewable, and a stub contradicts nothing.

Report the covered set explicitly either way: GDDs reviewed: [N] of [M] present. A cross-review that silently skipped half the systems is indistinguishable from one that found them consistent.

Phase 6: Write Report and Flag GDDs

Use AskUserQuestion for write permission:

• Prompt: "May I write this review to design/gdd/gdd-cross-review-[date].md?"
• Options: [A] Yes — write the report / [B] No — skip

[date] here means ISO 8601 — YYYY-MM-DD, e.g. gdd-cross-review-2026-08-19.md. This is not a style preference. .claude/scripts/review-scope.sh picks the prior review with sort | tail -1, so lexical order IS chronological order only for ISO dates. Written as aug-19-2026 or 19-08-2026, the wrong file is chosen as the baseline, the changed-set is computed from it, and GDDs modified since the real last review silently escape the next one. That is the same quiet-escape failure the three fixes documented at the top of that script exist to prevent.

If any GDDs are flagged for revision, use a second AskUserQuestion:

• Prompt: "Should I update the systems index to mark these GDDs as needing revision? ([list of flagged GDDs])"
• Options: [A] Yes — update systems index / [B] No — leave as-is
• If yes: update each flagged GDD's Status field in systems-index.md to "Needs Revision". (Do NOT append parentheticals to the status value — other skills match "Needs Revision" as an exact string and parentheticals break that match.)

Session State Update

After writing the report (and updating systems index if approved), silently append to production/session-state/active.md:

## Session Extract — /review-all-gdds [date]
- Verdict: [PASS / NOT ASSESSED / CONCERNS / FAIL]
- GDDs reviewed: [N of M present]
- Phases not run: [names, or "None"]
- Flagged for revision: [comma-separated list, or "None"]
- Blocking issues: [N — brief one-line descriptions, or "None"]
- Recommended next: [the Phase 7 handoff action, condensed to one line]
- Report: design/gdd/gdd-cross-review-[date].md   ← only if user approved the write
- Report: (not written — user declined at [date])  ← only if user declined the write

Use the appropriate line based on the user's response to the write-permission widget in Phase 6.

If active.md does not exist, create it with this block as the initial content. Confirm in conversation: "Session state updated."

Phase 7: Handoff

After all file writes are complete, use AskUserQuestion for a closing widget.

Before building options, check project state:

• Are there any Warning-level items that are simple edits (flagged with "30-second edit", "brief addition", or similar)? → offer inline quick-fix option
• Are any GDDs in the "Flagged for Revision" table? → offer /design-review option for each
• Read systems-index.md for the next system with Status: Not Started → offer /design-system option
• Is the verdict PASS or CONCERNS? → offer /gate-check or /create-architecture

Build the option list dynamically — only include options that apply:

Option pool:

• [_] Apply quick fix: [W-XX description] in [gdd-name].md — [effort estimate] (one option per simple-edit warning; only for Warning-level, not Blocking)
• [_] Run /design-review [flagged-gdd-path] — address flagged warnings (one per flagged GDD, if any)
• [_] Run /design-system [next-system] — next in design order (always include, name the actual system)
• [_] Run /create-architecture — begin architecture (verdict is PASS/CONCERNS) (include if verdict is not FAIL)
• [_] Run /gate-check — validate Systems Design phase gate (include if verdict is PASS)
• [_] Stop here

Assign letters A, B, C… only to included options. Mark the most pipeline-advancing option as (recommended).

In collaborative and guided modes, never end the skill with plain text — always close with this widget. In autonomous mode, print the verdict and recommended next step, then record via log_decision (no widget).

Error Recovery Protocol

First, verify the artifact. If the return contract named a path, check the path exists before treating the phase as done — a named artifact that is not on disk is a failed phase, however fluent the response reads. An agent can burn a full phase and return a plausible preamble having written nothing, which is neither BLOCKED nor an error nor "fails to complete", so the trigger below never fires. Resume it naming the unmet contract; the context is usually still there.

If any spawned agent returns BLOCKED, errors, or fails to complete: surface it immediately, don't proceed past a dependency it blocks, and always produce a partial report (retry scope here = fewer GDDs / single-system). Full procedure: .claude/docs/error-recovery-protocol.md.

Collaborative Protocol

In collaborative mode (the default). For guided and autonomous modes, see .claude/docs/automation-modes.md. In autonomous mode the PASS/CONCERNS/FAIL verdict is still printed and logged — only the closing handoff widget is skipped.

1. Read silently — load all GDDs before presenting anything
2. Show everything — present the full consistency and design theory analysis before asking for any action
3. Distinguish blocking from advisory — not every issue needs to block architecture; be clear about which do
4. Don't make design decisions — flag contradictions and options, but never unilaterally decide which GDD is "right"
5. Ask before writing — confirm before writing the report or updating the systems index
6. Be specific — every issue must cite the exact GDD, section, and text involved; no vague warnings