Day One PatchSAFE

Turn Claude Code into a full game dev studio — 49 AI agents, 72 workflow skills, and a complete coordination system mirroring real studio hierarchy.

The instruction file, verbatim from the audited commit — this is the text the model reads, and the surface the audit's instruction layer examines. Quoted here so you can judge it without cloning anything.

---
name: day-one-patch
description: "Day-one launch patch — focused fix for known issues found after gold master. Mini-sprint with QA gate and rollback."
argument-hint: "[scope: known-bugs | cert-feedback | all]"
user-invocable: true
disable-model-invocation: true
allowed-tools: Read, Glob, Grep, Write, Edit, Bash, Agent, AskUserQuestion
model: sonnet
---

# Day-One Patch

Every shipped game has a day-one patch. Planning it before launch day prevents
chaos. This skill scopes the patch to only what is safe and necessary, gates it
through a lightweight QA pass, and ensures a rollback plan exists before anything
ships. It is a mini-sprint — not a hotfix, not a full sprint.

**When to run:**
- After the gold master build is locked (cert approved or launch candidate tagged)
- When known bugs exist that are too risky to address in the gold master
- When cert feedback requires minor fixes post-submission
- When a pre-launch playtest surfaces must-fix issues after the release gate passed

**Day-one patch scope rules:**
- Only P1/P2 bugs that are SAFE to fix quickly
- No new features — this is fix-only
- No refactoring — minimum viable change
- Any fix that requires more than 4 hours of dev time belongs in patch 1.1, not day-one

**Output:** `production/releases/day-one-patch-[version].md`

---

## Phase 1: Load Release Context

Read:
- `project.stage` in `project.yaml` (fallback `production/stage.txt`) — confirm project is in Release stage
- The most recent file in `production/gate-checks/` — read the release gate verdict
- `production/qa/bugs/*.md` — load all bugs with Status: Open or Fixed — Pending Verification
- `production/sprints/` most recent — understand what shipped
- `production/security/security-audit-*.md` most recent — check for any open security items

If the resolved stage (project.yaml → stage.txt) is not `Release` or `Polish`:
> "Day-one patch prep is for Release-stage projects. Current stage: [stage]. This skill is not appropriate until you are approaching launch."

**Check the premise, do not assume it.** This whole skill rests on there being a
gold master that already passed a release gate — that premise is what justifies
its lightweight QA pass instead of a full one. So verify it rather than inferring
it from the stage value:

- **No file in `production/gate-checks/`**, or none recording a release-gate
  verdict: report `Release gate: NOT ASSESSED — no gate-check record found`. Do
  not proceed silently. Say plainly that the reduced QA scope below is justified
  by a gate nobody can find, and ask whether to run `/gate-check` first or
  proceed with a full QA pass instead.
- **The most recent record is FAIL, CONCERNS or NOT ASSESSED**: name it and stop.
  A day-one patch on top of a build that never passed its gate is not a day-one
  patch; it is the release gate, arriving late and scoped to the wrong changes.
- `project.stage: Release` on its own does **not** establish this. The stage is a
  claim about where the project is; the gate record is the evidence that it earned
  the position.

---

## Phase 2: Scope the Patch

### Step 2a — Classify open bugs for patch inclusion

For each open bug, evaluate:

| Criterion | Include in day-one? |
|-----------|-------------------|
| S1 or S2 severity | Yes — must include if safe to fix |
| P1 priority | Yes |
| Fix estimated < 4 hours | Yes |
| Fix requires architecture change | No — defer to 1.1 |
| Fix introduces new code paths | No — too risky |
| Fix is data/config only (no code change) | Yes — very low risk |
| Cert feedback requirement | Yes — required for platform approval |
| S3/S4 severity | Only if trivial config fix; otherwise defer |

### Step 2b — Present patch scope to user

Use `AskUserQuestion`:
- Prompt: "Based on open bugs and cert feedback, here is the proposed day-one patch scope. Does this look right?"
- Show: table of included bugs (ID, severity, description, estimated effort)
- Show: table of deferred bugs (ID, severity, reason deferred)
- Options: `[A] Approve this scope` / `[B] Adjust — I want to add or remove items` / `[C] No day-one patch needed`

If [C]: output "No day-one patch required. Proceed to `/launch-checklist`." Stop.

### Step 2c — Check total scope

Sum estimated effort. If total exceeds 1 day of work:
> "⚠️ Patch scope is [N hours] — this exceeds a safe day-one window. Consider deferring lower-priority items to patch 1.1. A bloated day-one patch introduces more risk than it removes."

Use `AskUserQuestion` to confirm proceeding or reduce scope.

---

## Phase 3: Rollback Plan

Before any code is written, define the rollback procedure. This is non-negotiable.

Spawn `release-manager` via `Agent`. Ask them to produce a rollback plan covering:
- How to revert to the gold master build on each target platform
- Platform-specific rollback constraints (some platforms cannot roll back cert builds)
- Who is responsible for triggering the rollback
- What player communication is required if a rollback occurs

Present the rollback plan. Ask: "May I write this rollback plan to `production/releases/rollback-plan-[version].md`?"

Do not proceed to Phase 4 until the rollback plan is written.

---

## Phase 4: Implement Fixes

For each code fix in the approved scope, spawn a focused implementation loop:

1. Spawn `lead-programmer` via `Agent` with:
   - The bug report (exact reproduction steps and root cause if known)
   - The constraint: minimum viable fix only, no cleanup
   - The affected files (from bug report Technical Context section)

   It returns, for each bug, the minimal fix and the files it would change —
   writing nothing.

2. Ask once, for the whole set: "May I apply these fixes? [BUG-ID → files, one
   line each]". No code changes before this approval.

3. On yes, hand each approved fix back to `lead-programmer` (a new `Agent` call
   carrying its plan) to implement it and run targeted tests with `commands.test`
   from `project.yaml`, narrowed to the affected suite where the runner allows —
  

SAFEgrade B · trust 89/100 Nothing in the source contradicts what it says it does. Grade A is reserved for packages that have also passed the behavioural sandbox.

What the source does

Filesystem

none-observed

Network

none-observed

Shell

none-observed

Dependencies

pinned

Secrets in source

none-found

Findings (0)

No findings outside the package's declared scope.

Gates applied: no_behavioural_pass.