Scope Check

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 "Scope Check" for me. The skill itself is read-only — it reports findings and writes no files, and its allowed-tools contain no Write or Edit at all: it locates the original plan for a feature, sprint or milestone (a GDD under design/, a sprint plan or a milestone file), reads the current state from the codebase, the sprint plan and the local git log (its one shell permission is Bash git log), and produces a comparison — scope additions, removals, a quantified bloat score, risk assessment and cut/defer/keep recommendations — with a PASS, CONCERNS, NOT ASSESSED or FAIL verdict. A percentage is never computed from an empty or unreadable baseline: that case is NOT ASSESSED, not 0%. Unlike most skills of this template it resolves no studio configuration and runs no yaml-helper hook. Its frontmatter pins model: haiku. Repository: https://github.com/Donchitos/Claude-Code-Game-Studios (the skill is the whole .claude/skills/scope-check/ folder at the pinned commit: 1 file 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/scope-check/ 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 70af8cd294881a0c1e62852bc5e47a63f142381f008f4f92adc1b0ed03ab5e11 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: SKILL.md only. Nothing in the folder is a program; it is instructions the agent follows at use time. Its frontmatter grants no Write or Edit tool — the read-only claim is in the tool list itself, not just in its prose. - 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 audited, read or modified. - Integrated-system reality, from the file: at use time the skill reads my project's baseline documents (design/gdd/ GDDs, production/sprints/ sprint plans, production/milestones/), scans the codebase for the feature's files and TODO/FIXME comments, and reads the local git log — project files that live outside this skill's folder and are absent in a standalone install, so it has nothing to compare outside the template's project layout. Unusually for this template, it runs no yaml-helper hook and resolves no configuration. - At use time it writes nothing at all: its only output is the comparison report and verdict shown in conversation. The git history it reads stays local. No third-party service, account or credential is named in the file. - Do not check any scope, do not run git log, 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 scope-check folder into the agent's skills directory, in a folder named exactly "scope-check", keeping its 1 file in their original relative layout (SKILL.md at its root). 4. Verify with no network calls: frontmatter valid (name: scope-check), the 1 file 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's project layout and may not run standalone (it compares the template's design/ and production/ baseline documents against the codebase and local git log), and that it is strictly read-only and writes no file at use time). 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.