Create Control Manifest

Before you start: read this whole install prompt, tell me in a few lines what this skill does and what installing it involves, and wait for my go-ahead before you do anything else. Prerequisites — INTEGRATED SYSTEM FIRST: this skill is one piece of the complete "Claude Code Game Studios" template (49 agents, 74 skills, studio templates and a studio CLAUDE.md, per the repository README). Each skill assumes that template is installed, with its conventions, its project.yaml / project.local.yaml configuration, its .claude/docs/ mode documents, its hooks (for example hooks/yaml-helper.sh, outside this skill's folder) and its .claude/scripts/ helpers. Installing this listing alone copies only this skill's folder, without the rest of the system: the skill may reference template agents, files, hooks or scripts that are absent outside the full template, and it may not run as designed on its own. No account, no key and no payment are needed to copy the files, and nothing is run during installation. Install "Create Control Manifest" for me. It is the Game Studios control-manifest builder. It first runs the template's .claude/scripts/adr-status.sh to count and classify every ADR: no ADRs, or ADRs with no Status section at all, stops the run; no Accepted ADRs asks whether to build from the Proposed ones or stop — an empty manifest is never written silently. For each Accepted ADR it extracts rules from only four sections (via the template's .claude/scripts/md-section.sh): required patterns from Decision, forbidden approaches from Alternatives Considered, performance guardrails and engine API constraints, then adds the global rules (naming and performance from project.yaml or the technical preferences, forbidden APIs from the pinned engine reference, scoped to what the project actually builds). It shows a preview naming every ADR covered and every one left out, runs the technical-director TD-MANIFEST review when the review gate says run, and writes docs/architecture/control-manifest.md only on an explicit yes. Repository: https://github.com/Donchitos/Claude-Code-Game-Studios (the skill is the whole .claude/skills/create-control-manifest/ folder at the pinned commit: 1 files in total) Pinned version: install the code at commit 05ad7c8a5b8aa2aa86bbd3439ae7cf7295cac418 exactly. Do not substitute a newer version. If this commit is unreachable, stop and tell me. 1. Clone https://github.com/Donchitos/Claude-Code-Game-Studios into a temporary folder, check out commit 05ad7c8a5b8aa2aa86bbd3439ae7cf7295cac418, and copy the .claude/skills/create-control-manifest/ folder from that checkout. Then compare every file in the folder with the fingerprints recorded for this listing on 2026-10-22: [FINGERPRINTS] - SKILL.md: SHA-256 a487bb167b3154b19fe76ac618625ef0bfeb65a2a90432804e96e0a83271b75a If a file does not match, it changed since the listing was prepared: do not install it yet, tell me what you found and let me decide. 2. Read SKILL.md in full, and tell me in plain words: what the skill does when used, what it connects to, whether it reads or sends any personal information or credentials, and anything that seems unusual. Stop on any red flag and tell me before going further. Confirm these points from the files: - The skill folder holds 1 file only: SKILL.md (13414 characters of instructions in a single file; there are no companion files in its folder). Nothing in the folder is run during installation; companion files are instructions/references the skill reads at use time, copied as-is. - Nothing is sent anywhere during installation itself; the only download at install time is the skill folder from GitHub at the pinned commit, and no project of mine is read or modified. - Integrated-system reality, from the files: at use time the skill resolves studio configuration by running the template's hooks/yaml-helper.sh (keys review_mode, review_gate, automation), runs the template's .claude/scripts/adr-status.sh and .claude/scripts/md-section.sh helpers, reads project.yaml, the template's .claude/docs/technical-preferences.md and the pinned engine-reference docs under docs/engine-reference/, and can hand its preview to the template's technical-director agent — files, scripts and an agent that live outside this skill's folder and are absent in a standalone install, so parts of it cannot run outside the full template. Inside the template it works on my project's own ADRs and preferences, locally. - At use time it writes only after an explicit yes, and only one file in my own project: docs/architecture/control-manifest.md (a regeneration replaces it, after reading it first). No account, key, payment or third-party service is named in the files I read. - Do not build any manifest, do not run any template script, hook or agent, and do not use the skill in any way during this install: using it is a separate step that only starts when I ask for it later. 3. When I say "yes, install", install it as a skill: copy the whole create-control-manifest folder into the agent's skills directory, in a folder named exactly "create-control-manifest", keeping its 1 files in their original relative layout (SKILL.md at its root). 4. Verify with no network calls: frontmatter valid (name: create-control-manifest), the 1 files in place with matching fingerprints. Do not run anything from the folder and do not use the skill to verify. 5. Report what was installed, where, and what I still need to do myself (for example: that it belongs to the full Claude Code Game Studios template and may not run standalone (it reads my ADRs through the template's .claude/scripts helpers and resolves its settings through the template's yaml-helper hook), and that inside the template it writes the control manifest only after my explicit yes). GitHub is optional: if I have a GitHub account or the gh CLI, you may use it; otherwise public access is fine. Never require it unless it's in the prerequisites above. Rules: don't touch anything outside the temp folder and the install target. If anything looks off, stop and ask me.