Hotfix

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. One wall specific to this skill must be read first: at use time, after its approvals and QA gate, it can MERGE a hotfix branch, TAG a patch release and DEPLOY it — but only after an explicit AskUserQuestion approval that holds unconditionally, in every automation mode including autonomous (see the introduction). It is also explicit-invocation only (disable-model-invocation in its frontmatter). Install "Hotfix" for me. It runs an emergency fix that bypasses the normal sprint process, with a full audit trail — explicit invocation only, for S1 (critical) or S2 (high) bugs; S3 and below are redirected to the normal bug workflow. It confirms the severity with the user, drafts a hotfix record (problem, root cause, fix, testing, approvals, rollback plan) and asks before writing it to production/hotfixes/hotfix-[date]-[short-name].md. It checks the project is a git repository (git rev-parse) and, only on the user's choice, creates a hotfix/[short-name] branch from the release the bug is in — that release's tag or its release/* branch, never the head of main. It investigates the root cause, proposes the minimum fix, and modifies no code before the user approves that proposal; only then does it implement, running targeted tests with commands.test from project.yaml (recorded as NOT RUN, with the reason, when unset or uncovered). It collects parallel sign-offs from the template's lead-programmer, qa-tester and producer agents — all three must APPROVE — then a qa-lead agent sets the QA scope (/smoke-check, a targeted /team-qa, or a full /team-qa), and a NOT ASSESSED QA result is explicitly not a pass. Deployment is the skill's one irreversible act and is gated unconditionally, regardless of automation mode: only on an explicit yes does it merge to main (and the release branch if one exists), tag the patch release and deploy that tag, then verify the backport is actually present on each target, update the original bug file after an ask, and schedule a post-incident review within 48 hours. Its folder is a single SKILL.md. Repository: https://github.com/Donchitos/Claude-Code-Game-Studios (the skill is the whole .claude/skills/hotfix/ 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/hotfix/ 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 20233b7851f526da3ad80ee9acb9e2ec9b99bd15e861252eddef04c0d7aaee6c 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 a single file: SKILL.md. Nothing in the folder is a program; it is emergency-workflow instructions the session follows at use time. Its frontmatter sets disable-model-invocation: true and states it must only run on an explicit /hotfix invocation. - 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, branched or modified. - Integrated-system reality, from the files: this skill runs no template hook — it works from git (its allowed Bash is limited to git rev-parse, git tag --list and git branch --list reads, plus the branch creation the text gates on my choice), project.yaml's commands.test, and the template's other skills and agents (/bug-triage's severity scale, lead-programmer, qa-tester, producer and qa-lead agents, /smoke-check, /team-qa, /bug-report) — pieces that live outside this skill's folder and are absent in a standalone install, so it cannot run as designed outside the full template. - At use time it performs real, partly irreversible operations, each behind an explicit approval: the hotfix record is written after an ask, the branch is created only on my choice, no code changes before I approve the proposed fix, and merging, tagging the patch release and deploying happen only on an unconditional AskUserQuestion yes that applies in every automation mode, including autonomous. The bug file is updated after an ask. Deployment targets, tags and approvals are all named in the file I read; no third-party service, account or credential is named. - Do not hotfix anything, do not run git, any template agent or any other skill, and do not use this 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 hotfix folder into the agent's skills directory, in a folder named exactly "hotfix", keeping its 1 file in their original relative layout (SKILL.md at its root). 4. Verify with no network calls: frontmatter valid (name: hotfix), 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 and may not run standalone — that it belongs to the full Claude Code Game Studios template and may not run standalone (it depends on the template's agents and on /smoke-check, /team-qa and /bug-report), and that using it can, after explicit approvals, merge a hotfix branch, tag a patch release and deploy it — the deployment always requiring its own unconditional 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.