• Glob

  docs/architecture/adr-*.md

  and read every file
• Filter to only Accepted ADRs (Status: Accepted) — skip Proposed, Deprecated, Superseded
• Note the ADR number and title for every rule sourced

• Read

  .claude/docs/technical-preferences.md

• Extract: naming conventions, performance budgets, approved libraries/addons, forbidden patterns

• Read

  docs/engine-reference/[engine]/VERSION.md

  for engine + version
• Read

  docs/engine-reference/[engine]/deprecated-apis.md

  — these become forbidden API entries
• Read

  docs/engine-reference/[engine]/current-best-practices.md

  if it exists

• Every "must", "should", "required to", "always" statement
• Every specific pattern or approach mandated

• Every alternative that was explicitly rejected — why it was rejected becomes the rule ("never use X because Y")
• Any anti-patterns explicitly called out

• Budget constraints: "max N ms per frame for this system"
• Memory limits: "this system must not exceed N MB"

• Post-cutoff APIs that require verification
• Verified behaviours that differ from default LLM assumptions
• API fields or methods that behave differently in the pinned engine version

• Foundation: Scene management, event architecture, save/load, engine init
• Core: Core gameplay loops, main player systems, physics/collision
• Feature: Secondary systems, secondary mechanics, AI
• Presentation: Rendering, audio, UI, VFX, shaders

• Naming conventions (classes, variables, signals/events, files, constants)
• Performance budgets (target framerate, frame budget, draw call limits, memory ceiling)

• All deprecated APIs → Forbidden API entries

• Engine-recommended patterns → Required entries

• Copy any "Forbidden Patterns" entries directly

• Foundation layer: [N] required, [M] forbidden, [P] guardrails
• Core layer: [N] required, [M] forbidden, [P] guardrails
• Feature layer: ...
• Presentation layer: ...
• Global: [N] naming conventions, [M] forbidden APIs, [P] approved libraries

Use `AskUserQuestion`:
- Prompt: "Does this rule summary look complete?"
- Options:
  - `[A] Yes — looks good, run the director review and write the manifest`
  - `[B] Add rules — I have additional rules to include before writing`
  - `[C] Remove rules — some extracted rules should be dropped`
  - `[D] Stop here — I need to review the ADRs first`

---

• solo

  → skip. Note: "TD-MANIFEST skipped — Solo mode." Proceed to Phase 5.

• lean

  → skip. Note: "TD-MANIFEST skipped — Lean mode." Proceed to Phase 5.

• full

  → spawn as normal.

technical-director

.claude/docs/director-gates.md

• All mandatory ADR patterns are captured and accurately stated
• Forbidden approaches are complete and correctly attributed
• No rules were added that lack a source ADR or preference document
• Performance guardrails are consistent with the ADR constraints

• APPROVE → proceed to Phase 5
• CONCERNS → surface via

  AskUserQuestion

  with options:

  Revise flagged rules

  /

  Accept and proceed

  /

  Discuss further

• REJECT → do not write the manifest; fix the flagged rules and re-present the summary

AskUserQuestion

• Prompt: "May I write the Control Manifest?"
• Options:

  • [A] Yes — write to docs/architecture/control-manifest.md

  • [B] Show me the full draft first, then ask again

  • [C] Not yet — I want to make more changes

undefined

Engine: [name + version] Last Updated: [date] Manifest Version: [date] ADRs Covered: [ADR-NNNN, ADR-MMMM, ...] Status: [Active — regenerate with

/create-control-manifest update

when ADRs change]

Manifest Version

/story-readiness

Last Updated

• [rule] — source: [ADR-NNNN]
• [rule] — source: [ADR-NNNN]

• Never [anti-pattern] — [brief reason] — source: [ADR-NNNN]

• [system]: max [N]ms/frame — source: [ADR-NNNN]

• [library] — approved for [purpose]

• [api name]

  — deprecated since [version] / unverified post-cutoff
• Source:

  docs/engine-reference/[engine]/deprecated-apis.md

• [constraint that applies everywhere, regardless of layer]

---

• If epics/stories don't exist yet: "Run

  /create-epics layer: foundation

  then

  /create-stories [epic-slug]

  — programmers can now use this manifest when writing story implementation notes."
• If this is a regeneration (manifest already existed): "Updated. Recommend notifying the team of changed rules — especially any new Forbidden entries."

1. Load silently — read all inputs before presenting anything
2. Show the summary first — let the user see the scope before writing
3. Ask before writing — always confirm before creating or overwriting the manifest. On write: Verdict: COMPLETE — control manifest written. On decline: Verdict: BLOCKED — user declined write.
4. Source every rule — never add a rule that doesn't trace to an ADR, a technical preference, or an engine reference doc
5. No interpretation — extract rules as stated in ADRs; do not paraphrase in ways that change meaning