feat: bridge Codex v0.4.4 (user-owned playtest focus contract)

Port the user-owned playtest focus contract from Codex Game Studios v0.4.4
(upstream commit ddb184c, 2026-07-09) into the OpenCode-native port.

- playtest-report/SKILL.md: Test Focus expanded to hypothesis/setup-build/
  observation prompts/verdict-evidence; gap-statement guidance in Phase 2B;
  follow-up playtest-focus routing in Phase 5
- session-continuity.md: new User-Owned Playtest Focus section; Pause
  Procedure step 3 carries the preserved Playtest focus: brief
- AGENTS.md: playtest-focus sub-bullet in the closeout contract
- audit.sh: new run_playtest_focus validator (audit.sh playtest / all)
  checking AGENTS.md, session-continuity.md, and playtest-report/SKILL.md
- VERSION 0.4.0 -> 0.4.1; CHANGELOG v0.4.1 entry; README badge, version
  line, status bullet, and structure comment updated (also fixes stale
  0.3.0 README badge)

Verification: audit.sh playtest, audit.sh all, and audit.sh release all
pass with 0 errors.

Author: Cipher-85

.opencode/VERSION

@@ -1 +1 @@
-0.4.0
+0.4.1

.opencode/audit.sh

@@ -10,6 +10,7 @@
 #   skills       Validate skill files
 #   closeout     Check closeout-routing contract on completion skills
 #   checkpoint   Check active.md silent-checkpoint contract on skills/agents
+#   playtest     Check playtest-focus contract on root/continuity/skill surfaces
 #   runtime      Check for stale references
 #   config       Validate opencode.json
 #   hooks        Test hook scripts
@@ -26,7 +27,7 @@ command="${1:-all}"
 while [ "$#" -gt 0 ]; do
   case "$1" in
     --root) root="$(cd "$2" && pwd -P)"; shift 2 ;;
-    all|agents|skills|runtime|config|hooks|smoke|release|closeout|checkpoint) command="$1"; shift ;;
+    all|agents|skills|runtime|config|hooks|smoke|release|closeout|checkpoint|playtest) command="$1"; shift ;;
     *) shift ;;
   esac
 done
@@ -218,6 +219,44 @@ PY
   fi
 }
 
+run_playtest_focus() {
+  printf '\n── Playtest Focus Contract ────────────────────────────────\n'
+  local -a surfaces=(
+    "AGENTS.md"
+    ".opencode/docs/session-continuity.md"
+    ".opencode/skills/playtest-report/SKILL.md"
+  )
+  local -a phrases=(
+    "user-owned playtest"
+    "Playtest focus:"
+    "hypothesis"
+    "setup/build"
+    "2-4 observation"
+    "verdict/evidence"
+  )
+  local checked=0
+  local rel
+  for rel in "${surfaces[@]}"; do
+    local f="$root/$rel"
+    checked=$((checked + 1))
+    [ -f "$f" ] || { fail "$rel (missing file)"; continue; }
+    local missing=() p
+    for p in "${phrases[@]}"; do
+      if ! grep -qiF "$p" "$f" 2>/dev/null; then missing+=("$p"); fi
+    done
+    # session-continuity also requires the Session Worklist reference
+    if [ "$rel" = ".opencode/docs/session-continuity.md" ]; then
+      if ! grep -qiF "Session Worklist" "$f" 2>/dev/null; then missing+=("Session Worklist"); fi
+    fi
+    if [ "${#missing[@]}" -eq 0 ]; then
+      pass "$rel (playtest focus contract)"
+    else
+      fail "$rel missing: ${missing[*]}"
+    fi
+  done
+  printf '  %d playtest-focus surfaces checked\n' "$checked"
+}
+
 run_runtime() {
   printf '\n── Runtime References ──────────────────────────────────────\n'
   # Check for stale Claude references
@@ -364,6 +403,7 @@ case "$command" in
     run_skills
     run_closeout
     run_checkpoint
+    run_playtest_focus
     run_runtime
     run_config
     run_hooks
@@ -373,12 +413,13 @@ case "$command" in
   skills)   run_skills ;;
   closeout) run_closeout ;;
   checkpoint) run_checkpoint ;;
+  playtest) run_playtest_focus ;;
   runtime)  run_runtime ;;
   config)   run_config ;;
   hooks)    run_hooks ;;
   smoke)    run_smoke ;;
   release)  run_release ;;
-    *) printf 'Unknown command: %s\nAvailable: all, agents, skills, closeout, checkpoint, runtime, config, hooks, smoke, release\n' "$command" >&2; exit 2 ;;
+    *) printf 'Unknown command: %s\nAvailable: all, agents, skills, closeout, checkpoint, playtest, runtime, config, hooks, smoke, release\n' "$command" >&2; exit 2 ;;
 esac
 
 printf '\n── Result: %d error(s) ──\n' "$errors"

.opencode/docs/session-continuity.md

@@ -26,6 +26,24 @@ The checkpoint exception is narrow. It never authorizes new design, game-feel,
 balance, architecture, source, registry, index, status-file, commit, push,
 branch, build, boot-smoke, mutating `gh`, or additional file changes.
 
+## User-Owned Playtest Focus
+
+When owed verification or the next valid lane is a user-owned playtest, preserve
+a concrete focus brief in both the closeout and any `## Session Worklist` entry.
+Use the label `Playtest focus:` and include:
+
+- **Hypothesis**: what feeling, behavior, or evidence the playtest is probing.
+- **Setup/build**: the build, command, save state, or scenario to use when
+  known.
+- **Observation prompts**: 2-4 observation prompts for specific things the
+  user should watch for.
+- **Verdict/evidence to return**: the user-owned pass/fail/needs-rethink
+  verdict plus the notes, screenshots, logs, or playtest report path needed to
+  make the evidence usable.
+
+The brief narrows the test; it does not make the game-feel, balance, keep,
+revert, or tune decision for the user.
+
 ## Pause Procedure
 
 Before pausing a meaningful work unit, check whether the invoked workflow still
@@ -44,6 +62,8 @@ decision, blocker, or true stop point.
    clear next lane:
    `Next action:` then `1. (Recommended) [action label] - [brief reason /
    command]`. The user can reply with `1`.
+   If that lane is a user-owned playtest, include the preserved `Playtest
+   focus:` brief before the next-action prompt.
 4. Preserve exact next commands only when they are known to be useful.
 5. Keep local-only notes out of tracked docs unless they are project state.
 6. Suggest `/handoff [short-label]` when installed and the next session would

.opencode/skills/playtest-report/SKILL.md

@@ -41,7 +41,14 @@ Generate this template and output it to the user:
 - **Session Type**: [First time / Returning / Targeted test]
 
 ## Test Focus
-[What specific features or flows were being tested]
+- **Hypothesis**: [What feeling, behavior, or evidence this playtest is probing]
+- **Setup/build**: [Build, commit, command, save state, or scenario if known]
+- **Observation prompts**:
+1. [Specific thing to watch for]
+2. [Specific thing to watch for]
+3. [Optional specific thing to watch for]
+4. [Optional specific thing to watch for]
+- **Verdict/evidence to return**: [User-owned pass/fail/needs-rethink verdict plus notes, screenshots, logs, or report path]
 
 ## First Impressions (First 5 minutes)
 - **Understood the goal?** [Yes/No/Partially]
@@ -96,6 +103,12 @@ Generate this template and output it to the user:
 
 Read the raw notes at the provided path. Cross-reference with existing design documents. Fill in the template above with structured findings. Flag any playtest observations that conflict with design intent.
 
+If the notes omit a specific hypothesis or focus, state that gap before
+analysis and ask for or infer only a provisional `Playtest focus:` from the
+notes. Do not route the user to another manual playtest without a concrete
+hypothesis, setup/build if known, 2-4 observation prompts, and the
+verdict/evidence the user should return.
+
 ---
 
 ## Phase 3: Action Routing
@@ -146,3 +159,7 @@ Verdict: **COMPLETE** — playtest report generated.
 - Act on the highest-priority finding category first.
 - After addressing design changes: re-run `/design-review` on the updated GDD.
 - After fixing bugs: re-run `/bug-triage` to update priorities.
+- If another user-owned playtest is the routed next step, include `Playtest
+  focus:` with the specific hypothesis, setup/build if known, 2-4 observation
+  prompts, and the verdict/evidence the user should return. The focus brief
+  narrows the test but leaves game-feel and balance decisions to the user.

AGENTS.md

@@ -41,6 +41,9 @@ verification-first implementation.
   `Next action:` then `1. (Recommended) [action label] - [brief reason /
   command]`. Base that next action on the `## Session Worklist` when
   `production/session-state/active.md` exists. The user can reply with `1`.
+  - When the next action or owed verification is a user-owned playtest, include
+    `Playtest focus:` with the hypothesis, setup/build if known, 2-4 observation
+    prompts, and the verdict/evidence the user should return.
 
 ## Available OpenCode Subagents
 

CHANGELOG.md

@@ -1,5 +1,23 @@
 # Changelog
 
+## v0.4.1 - 2026-07-09
+
+Bridged Codex Game Studios v0.4.4 (user-owned playtest focus contract) into
+the OpenCode-native port.
+
+- Added a user-owned playtest focus contract so closeouts and owed verification
+  include a `Playtest focus:` brief (hypothesis, setup/build, 2-4 observation
+  prompts, verdict/evidence) instead of generic playtest requests, while
+  leaving game-feel and balance verdicts with the user.
+- Updated `/playtest-report` templates and routing so new reports and follow-up
+  playtests carry a concrete hypothesis before sending the user back to play.
+- Updated `AGENTS.md` and `session-continuity.md` to preserve the playtest
+  focus brief in closeouts and `## Session Worklist` entries.
+- Added a `run_playtest_focus` validator to `.opencode/audit.sh` (run via
+  `audit.sh playtest` or as part of `audit.sh all`) that enforces the
+  playtest-focus contract across root instructions, continuity docs, and the
+  playtest-report workflow.
+
 ## v0.4.0 - 2026-07-09
 
 Bridged Codex Game Studios v0.4.2–v0.4.3 (silent active-session checkpoints,

README.md

@@ -13,7 +13,7 @@
   <a href=".opencode/skills"><img src="https://img.shields.io/badge/skills-77-green" alt="77 Skills"></a>
   <a href=".opencode/commands"><img src="https://img.shields.io/badge/commands-77-yellow" alt="77 Commands"></a>
   <a href=".opencode/hooks"><img src="https://img.shields.io/badge/hooks-12-orange" alt="12 Hooks"></a>
-  <a href=".opencode/VERSION"><img src="https://img.shields.io/badge/version-0.3.0-blue" alt="v0.3.0"></a>
+  <a href=".opencode/VERSION"><img src="https://img.shields.io/badge/version-0.4.1-blue" alt="v0.4.1"></a>
   <a href="https://opencode.ai"><img src="https://img.shields.io/badge/built%20for-OpenCode-f5f5f5" alt="Built for OpenCode"></a>
 </p>
 
@@ -69,9 +69,17 @@ first brainstorm to launch.
 
 ## Current Status
 
-Package version: `0.3.0` (see [`.opencode/VERSION`](.opencode/VERSION)).
+Package version: `0.4.1` (see [`.opencode/VERSION`](.opencode/VERSION)).
 
 This release includes:
+- User-owned playtest focus routing: when owed verification or the next action
+  is a manual playtest, closeouts include a `Playtest focus:` brief with the
+  hypothesis, setup/build, observation prompts, and verdict/evidence to return.
+  `/playtest-report` templates and follow-up routing now require concrete
+  hypotheses before sending the user back to play, while preserving the user's
+  ownership of game-feel and balance verdicts. A `run_playtest_focus` validator
+  keeps the contract present in root instructions, session-continuity docs, and
+  the playtest-report workflow.
 - Session Worklist routing cache (`## Session Worklist` + `## Phase Guard` in
   `production/session-state/active.md`); `/resume-from-handoff` compiles it,
   post-work closeouts read it, and `/studio-next` is now a deprecated manual
@@ -364,7 +372,7 @@ opencode.json                        # Permissions, plugin ref, instruction file
   uninstall.sh                       # Coexistence-aware uninstaller
   audit.sh                           # Validation dispatcher
   release.sh                         # Version management + GitHub releases
-  VERSION                            # Package version (0.3.0)
+  VERSION                            # Package version (0.4.1)
 design/                              # GDDs, narrative docs (AGENTS.md + registry/)
 docs/                                # Technical docs, ADRs, engine reference
 production/                          # Sprint plans, milestones, session state