create-control-manifest

Generates a layered rules manifest for programmers from accepted architecture decision records.

Updated Aug 2, 2026
One-click install
npx skills add https://github.com/claretagrapelike32/codex-ai-game-studio --skill create-control-manifest-claretagrapelike32
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: create-control-manifest
Source: https://github.com/claretagrapelike32/codex-ai-game-studio/tree/main/plugins/ai-game-studio/skills/create-control-manifest
Command: npx skills add https://github.com/claretagrapelike32/codex-ai-game-studio --skill create-control-manifest-claretagrapelike32

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve? After architecture decisions are recorded in ADRs, programmers still lack a single actionable reference telling them what they must do and must never do per system layer. This Skill extracts every rule from Accepted ADRs, technical preferences, and engine reference docs into one flat control manifest. ## Core Features & Use Cases - Rule Extraction from ADRs: Parses all Accepted ADRs to pull required patterns, forbidden approaches, performance guardrails, and engine API constraints, each traced to its source ADR. - Layer-Based Organization: Classifies rules into Foundation, Core, Feature, and Presentation layers plus cross-cutting naming conventions, performance budgets, and forbidden APIs. - Review Gates: Presents a rule summary for user confirmation and runs a technical-director review gate before writing docs/architecture/control-manifest.md. - Use Case: After your architecture review passes and ADRs are accepted, run this Skill to produce a programmer quick-reference manifest that story files can version-check against to detect stale rules. ## Quick Start Use the create-control-manifest skill to extract all rules from my accepted ADRs and write the control manifest for this project.

Frequently Asked Questions about create-control-manifest

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I turn architecture decision records into actionable coding rules?

Run this Skill after your ADRs reach Accepted status. It extracts every must-do and never-do statement from the ADRs, classifies them by architectural layer, and writes a control manifest at docs/architecture/control-manifest.md with each rule traced to its source ADR.

What is a control manifest in game architecture?

A control manifest is a flat programmer quick-reference listing required patterns, forbidden approaches, and performance guardrails per layer. Unlike ADRs, which explain why decisions were made, the manifest states what programmers must do, and story files embed its version date to detect stale rules.

When should I regenerate the control manifest?

Regenerate it whenever new ADRs are accepted or existing ADRs are revised. The manifest's version date is compared by story-readiness checks against dates embedded in story files, so stale manifests cause stories to be flagged as written against outdated rules.

Does the control manifest include deprecated engine APIs?

Yes. The Skill reads docs/engine-reference/[engine]/deprecated-apis.md for your pinned engine version and converts every deprecated or unverified API into a Forbidden APIs entry in the manifest, so programmers know which calls to avoid.

Can the manifest be written without user review?

No. The Skill always presents a rule summary first and asks for confirmation before writing. In full review mode it also runs a technical-director gate that can approve, raise concerns, or reject the manifest before anything is written.