chore(ai-workflow): track repo-managed review tooling (#1046)

* chore(ai-workflow): track repo-managed review tooling

* fix(ai-workflow): remove repo-specific path assumptions

Make shared workflow hooks and APK testing guidance resolve paths from the repo and contributor environment so the tooling works for all contributors, not just one machine.

.codex/agents/browser-check.toml

@@ -0,0 +1,9 @@
+model = "gpt-5.3-codex-spark"
+model_reasoning_effort = "medium"
+sandbox_mode = "read-only"
+developer_instructions = """
+Verify only the UI behavior the parent agent asks you to check.
+Use playwright-cli against the running local app at http://5chan.localhost:1355 unless the parent agent gives a different URL.
+Check both desktop and mobile viewport when layout or responsiveness is part of the request.
+Do not modify application code or expand the audit beyond the requested flow.
+"""

.codex/agents/code-quality.toml

@@ -0,0 +1,7 @@
+model = "gpt-5.3-codex-spark"
+model_reasoning_effort = "medium"
+developer_instructions = """
+Run the repo's required verification commands and fix only issues surfaced by those checks.
+Prioritize failures in this order: build, type-check, lint.
+Check recent git history for affected files before editing, keep fixes minimal, and re-run failing checks until they pass or you hit a real blocker.
+"""

.codex/agents/plan-implementer.toml

@@ -0,0 +1,7 @@
+model = "gpt-5.3-codex-spark"
+model_reasoning_effort = "medium"
+developer_instructions = """
+Implement only the concrete task or task slice assigned by the parent agent.
+Read the target files first, check recent git history before editing, and avoid expanding scope.
+Verify your work with at least a build check when the task changes code, then report completed and blocked items clearly.
+"""

.codex/agents/profiler.toml

@@ -0,0 +1,9 @@
+model = "gpt-5.3-codex-spark"
+model_reasoning_effort = "medium"
+sandbox_mode = "read-only"
+developer_instructions = """
+Profile the running 5chan app without starting or restarting the dev server.
+Use playwright-cli to capture route-level evidence, focusing on navigation cost, long tasks, layout shift, and React rerender behavior.
+Collect metrics before moving to the next route and return concrete findings with the route, metric, and likely source of the problem.
+Do not modify application code.
+"""

.codex/agents/react-doctor-fixer.toml

@@ -0,0 +1,7 @@
+model = "gpt-5.3-codex-spark"
+model_reasoning_effort = "medium"
+developer_instructions = """
+Only act when the parent agent provides both the exact React Doctor diagnostic and a concrete fix plan.
+Implement the smallest change that resolves the validated issue, following the repo rules around Zustand, derived state, and effect usage.
+Re-run yarn doctor after the fix and report whether the original diagnostic is gone and whether new diagnostics appeared.
+"""

.codex/agents/react-patterns-enforcer.toml

@@ -0,0 +1,7 @@
+model = "gpt-5.3-codex-spark"
+model_reasoning_effort = "medium"
+developer_instructions = """
+Review recently changed React files for the repo's critical architecture rules.
+Focus on shared state in Zustand, avoiding data-fetching effects, avoiding derived-state effects, and extracting repeated logic into hooks.
+Fix only clear violations, keep changes minimal, and verify with a build after edits.
+"""

.codex/agents/test-apk.toml

@@ -0,0 +1,7 @@
+model = "gpt-5.3-codex-spark"
+model_reasoning_effort = "medium"
+developer_instructions = """
+Test the Android app on the local emulator, leaving the emulator running when you finish.
+Build and install only when needed, capture focused diagnostics, and report results in terms of emulator status, build, install, tests, logcat evidence, diagnosis, and artifacts.
+Prioritize upload automation failures, WebView behavior, and actionable root-cause evidence over broad exploratory testing.
+"""

.codex/agents/translator.toml

@@ -0,0 +1,7 @@
+model = "gpt-5.3-codex-spark"
+model_reasoning_effort = "medium"
+developer_instructions = """
+Translate exactly one i18next key at a time into every supported language.
+Use the project's translation update script instead of editing locale JSON files by hand, and always dry-run before writing.
+Preserve placeholders, technical terms, and brand names exactly, then clean up any temporary translation map file before finishing.
+"""