chore(agents): update codex/cursor workflows

.codex/agents/browser-check.toml

@@ -2,8 +2,8 @@ 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.
+Verify only the route, user flow, and acceptance criteria the parent agent gives you.
+Use playwright-cli against the already-running local app at http://5chan.localhost:1355 unless the parent agent gives a different URL. Never start, restart, or stop the dev server.
+Check desktop and mobile viewport when the request touches layout, responsiveness, or touch interactions.
+Return concrete PASS/FAIL findings with the route, actions taken, and evidence observed. Do not modify application code or expand the audit beyond the requested flow.
 """

.codex/agents/code-quality.toml

@@ -1,7 +1,8 @@
-model = "gpt-5.3-codex-spark"
+model = "gpt-5.3-codex"
 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.
+Run the repo's required verification commands for the files or feature area the parent agent just changed, then fix only issues surfaced by those checks.
+Use this order: yarn build, yarn lint, yarn type-check. Add yarn doctor when the touched code includes React UI logic, yarn test when tests changed, and yarn knip when package manifests or imports changed.
+Inspect affected files and recent git history before editing, keep fixes minimal, and re-run failing checks until they pass or you hit a real blocker.
+Report the exact commands run, the failures you fixed, and any blockers or residual risk.
 """

.codex/agents/plan-implementer.toml

@@ -1,7 +1,8 @@
-model = "gpt-5.3-codex-spark"
+model = "gpt-5.3-codex"
 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.
+Require enough context to work independently: target files, acceptance criteria, and constraints. Read the target files first, inspect recent git history before editing, avoid expanding scope, and do not revert unrelated changes.
+When you change code, run the smallest verification that proves your slice is sound: at minimum yarn build, plus yarn doctor for React UI logic, yarn test when tests or runtime behavior changed, and any targeted command the parent agent requests.
+Report completed work, exact files touched, verification run, and blockers clearly.
 """

.codex/agents/profiler.toml

@@ -2,8 +2,8 @@ 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.
+Profile only the routes or flows the parent agent assigns.
+Use playwright-cli against the already-running 5chan app without starting, restarting, or stopping the dev server.
+Collect per-route evidence before navigating away, focusing on navigation cost, long tasks, layout shift, LCP, React commit bursts, and react-scan findings when available.
+Return concrete findings with the route, metric, severity, and likely source of the problem. Close browser sessions when done and do not modify application code.
 """

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

@@ -1,7 +1,7 @@
-model = "gpt-5.3-codex-spark"
+model = "gpt-5.3-codex"
 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.
+Implement the smallest change that resolves the validated issue, following repo rules around Zustand, derived state during render, and effect usage. Do not widen the fix beyond the validated diagnostic.
+Re-run yarn doctor after the fix, then report whether the original diagnostic is gone, whether new diagnostics appeared, which files changed, and any remaining risk.
 """

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

@@ -1,7 +1,7 @@
-model = "gpt-5.3-codex-spark"
+model = "gpt-5.3-codex"
 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.
+Review only the recently changed React files or the file set the parent agent names.
+Focus on the repo's critical architecture rules: shared state in Zustand, no data-fetching effects, no derived-state effects, extracting repeated logic into hooks, and clearer state modeling over boolean flag soup.
+Fix only clear violations, keep changes minimal, run yarn doctor when UI logic changed plus at least a build check, and report any violations you left unfixed with reasons.
 """

.codex/agents/test-apk.toml

@@ -1,7 +1,7 @@
-model = "gpt-5.3-codex-spark"
+model = "gpt-5.3-codex"
 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.
+Test only the Android workflow the parent agent asks about on the local emulator, leaving the emulator running when you finish unless the parent agent says otherwise.
+Build and install only when needed, capture focused diagnostics, and prioritize logcat evidence, screenshots, and reproducible failure steps over broad exploratory testing.
+Report results in this order: emulator status, build, install, tests run, logcat evidence, diagnosis, and artifacts. Focus especially on upload automation and WebView behavior.
 """

.codex/agents/translator.toml

@@ -2,6 +2,7 @@ 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.
+Use the project's translation update script instead of editing locale JSON files by hand, always dry-run before writing, and delete any temporary translation map file before finishing.
+Preserve placeholders, technical terms, HTML, and brand names exactly.
+Report the key handled, whether the write succeeded, and any languages or formatting you were uncertain about.
 """

.codex/skills/implement-plan/SKILL.md

@@ -39,7 +39,7 @@ Batch 3 (parallel): [tasks that depend on batch 2]
 
 ### 3. Execute Batches
 
-For each batch, spawn `plan-implementer` subagents using the Task tool with `subagent_type: "plan-implementer"`.
+For each batch, spawn `plan-implementer` subagents using Codex's current delegation tool and select the `plan-implementer` agent by name.
 
 Each subagent prompt must include:
 
@@ -47,7 +47,7 @@ Each subagent prompt must include:
 - **File paths** and context needed to work independently
 - **Constraints** or edge cases from the plan
 
-Use `model: "fast"` for straightforward tasks. Omit model for complex ones.
+If your runtime supports model overrides, use a faster coding model only for straightforward tasks. Omit the override for complex or cross-cutting tasks.
 
 Wait for all subagents in a batch to complete before starting the next batch.
 

.codex/skills/profile-browsing/SKILL.md

@@ -54,16 +54,14 @@ Keep batches balanced. Add thread views (`/:boardIdentifier/thread/:cid`) as nee
 
 ## Step 2: Spawn Profiler Subagents
 
-Read the profiler subagent definition at `.cursor/agents/profiler.md`. Then spawn one `shell` Task per batch **in parallel** (single message, multiple Task calls):
+Read the profiler subagent definition at `.codex/agents/profiler.toml`. Then spawn one `profiler` subagent per batch **in parallel** using Codex's current delegation tool:
 
 ```
-For each batch, create a Task:
-  subagent_type: "shell"
-  prompt: |
-    You are a performance profiler. Follow the workflow in .cursor/agents/profiler.md.
-    Session name: "prof-N"
-    Routes to profile: /route1, /route2, ...
-    [Include the full profiler workflow from the agent file]
+For each batch, create a subagent request that includes:
+  agent: "profiler"
+  Session name: "prof-N"
+  Routes to profile: /route1, /route2, ...
+  Any non-default app URL or extra profiling constraints
 ```
 
 Spawn up to 4 subagents simultaneously. Each opens its own browser session, navigates routes, scrolls, collects both Web Vitals and react-scan data per route, and returns a structured issues list.

.codex/skills/test-apk/SKILL.md

@@ -7,8 +7,8 @@ description: Test and debug Android APK features using a local Android emulator.
 
 ## Overview
 
-Delegates APK testing to a **shell subagent** (`model: fast`) to keep the main context clean.
-The subagent manages the emulator, builds/installs the APK, executes tests, and returns structured diagnostics.
+Delegates APK testing to the dedicated `test-apk` subagent to keep the main context clean.
+That subagent manages the emulator, builds and installs only when needed, executes the requested tests, and returns structured diagnostics.
 
 ## Workflow
 
@@ -25,14 +25,13 @@ Ask the user (or infer from context) what to test. Common scenarios:
 | Manual APK interaction | Build, install, launch, capture logcat |
 | Contract tests (fixtures) | `yarn contract:postimages` |
 
-### Step 2: Delegate to Shell Subagent
+### Step 2: Delegate to the `test-apk` Subagent
 
-Spawn a **shell** subagent with `model: fast`. Use the prompt template below, filling in `{TEST_DESCRIPTION}` with the user's requirements.
+Spawn the `test-apk` subagent with the prompt template below, filling in `{TEST_DESCRIPTION}` with the user's requirements and any exact commands or classes you want run.
 
 ```
-Use the Task tool:
-  subagent_type: "shell"
-  model: "fast"
+Use Codex's current delegation tool:
+  agent: "test-apk"
   prompt: <see Prompt Template below>
 ```
 

.codex/skills/translate/SKILL.md

@@ -28,7 +28,7 @@ For each key, check if the English value already exists in `public/translations/
 
 ### Step 3 — Spawn translator subagents
 
-For **each key**, spawn a `translator` subagent (using the Task tool with `subagent_type: "generalPurpose"` and `model: "fast"`). The prompt for each subagent must include:
+For **each key**, spawn a `translator` subagent using Codex's current delegation tool. The prompt for each subagent must include:
 - The key name
 - The English value
 - An instruction to follow the translator subagent's system prompt
@@ -45,7 +45,7 @@ Follow your system prompt for the full workflow (create dictionary file, dry run
 ```
 
 **Parallelism rules:**
-- Spawn up to 4 subagents concurrently (Task tool limit).
+- Spawn up to 4 subagents concurrently.
 - If there are more than 4 keys, batch them: spawn 4, wait for completion, then spawn the next batch.
 
 ### Step 4 — Report results