time-attack · time-attack · Jul 14, 2026 · Jul 14, 2026 · Jul 14, 2026 · Jul 14, 2026
diff --git a/autoplan/SKILL.md b/autoplan/SKILL.md
@@ -1168,7 +1168,7 @@ Override: every AskUserQuestion → auto-decide using the 6 principles.
   What alternatives were dismissed too quickly? What competitive or market risks are
   unaddressed? What scope decisions will look foolish in 6 months? Be adversarial.
   No compliments. Just the strategic blind spots.
-  File: <plan_path>" -C "$_REPO_ROOT" -s read-only --enable web_search_cached < /dev/null
+  File: <plan_path>" -C "$_REPO_ROOT" -s read-only < /dev/null
   _CODEX_EXIT=$?
   if [ "$_CODEX_EXIT" = "124" ]; then
     _gstack_codex_log_event "codex_timeout" "600"
@@ -1291,7 +1291,7 @@ Override: every AskUserQuestion → auto-decide using the 6 principles.
   accessibility requirements (keyboard nav, contrast, touch targets) specified or
   aspirational? Does the plan describe specific UI decisions or generic patterns?
   What design decisions will haunt the implementer if left ambiguous?
-  Be opinionated. No hedging." -C "$_REPO_ROOT" -s read-only --enable web_search_cached < /dev/null
+  Be opinionated. No hedging." -C "$_REPO_ROOT" -s read-only < /dev/null
   _CODEX_EXIT=$?
   if [ "$_CODEX_EXIT" = "124" ]; then
     _gstack_codex_log_event "codex_timeout" "600"
@@ -1367,7 +1367,7 @@ Override: every AskUserQuestion → auto-decide using the 6 principles.
   CEO: <insert CEO consensus table summary — key concerns, DISAGREEs>
   Design: <insert Design consensus table summary, or 'skipped, no UI scope'>
 
-  File: <plan_path>" -C "$_REPO_ROOT" -s read-only --enable web_search_cached < /dev/null
+  File: <plan_path>" -C "$_REPO_ROOT" -s read-only < /dev/null
   _CODEX_EXIT=$?
   if [ "$_CODEX_EXIT" = "124" ]; then
     _gstack_codex_log_event "codex_timeout" "600"
@@ -1493,7 +1493,7 @@ Log: "Phase 3.5 skipped — no developer-facing scope detected."
   3. API/CLI design: are names guessable? Are defaults sensible? Is it consistent?
   4. Docs: can a dev find what they need in under 2 minutes? Are examples copy-paste-complete?
   5. Upgrade path: can devs upgrade without fear? Migration guides? Deprecation warnings?
-  Be adversarial. Think like a developer who is evaluating this against 3 competitors." -C "$_REPO_ROOT" -s read-only --enable web_search_cached < /dev/null
+  Be adversarial. Think like a developer who is evaluating this against 3 competitors." -C "$_REPO_ROOT" -s read-only < /dev/null
   _CODEX_EXIT=$?
   if [ "$_CODEX_EXIT" = "124" ]; then
     _gstack_codex_log_event "codex_timeout" "600"

diff --git a/autoplan/SKILL.md.tmpl b/autoplan/SKILL.md.tmpl
@@ -304,7 +304,7 @@ Override: every AskUserQuestion → auto-decide using the 6 principles.
   What alternatives were dismissed too quickly? What competitive or market risks are
   unaddressed? What scope decisions will look foolish in 6 months? Be adversarial.
   No compliments. Just the strategic blind spots.
-  File: <plan_path>" -C "$_REPO_ROOT" -s read-only --enable web_search_cached < /dev/null
+  File: <plan_path>" -C "$_REPO_ROOT" -s read-only < /dev/null
   _CODEX_EXIT=$?
   if [ "$_CODEX_EXIT" = "124" ]; then
     _gstack_codex_log_event "codex_timeout" "600"
@@ -427,7 +427,7 @@ Override: every AskUserQuestion → auto-decide using the 6 principles.
   accessibility requirements (keyboard nav, contrast, touch targets) specified or
   aspirational? Does the plan describe specific UI decisions or generic patterns?
   What design decisions will haunt the implementer if left ambiguous?
-  Be opinionated. No hedging." -C "$_REPO_ROOT" -s read-only --enable web_search_cached < /dev/null
+  Be opinionated. No hedging." -C "$_REPO_ROOT" -s read-only < /dev/null
   _CODEX_EXIT=$?
   if [ "$_CODEX_EXIT" = "124" ]; then
     _gstack_codex_log_event "codex_timeout" "600"
@@ -503,7 +503,7 @@ Override: every AskUserQuestion → auto-decide using the 6 principles.
   CEO: <insert CEO consensus table summary — key concerns, DISAGREEs>
   Design: <insert Design consensus table summary, or 'skipped, no UI scope'>
 
-  File: <plan_path>" -C "$_REPO_ROOT" -s read-only --enable web_search_cached < /dev/null
+  File: <plan_path>" -C "$_REPO_ROOT" -s read-only < /dev/null
   _CODEX_EXIT=$?
   if [ "$_CODEX_EXIT" = "124" ]; then
     _gstack_codex_log_event "codex_timeout" "600"
@@ -629,7 +629,7 @@ Log: "Phase 3.5 skipped — no developer-facing scope detected."
   3. API/CLI design: are names guessable? Are defaults sensible? Is it consistent?
   4. Docs: can a dev find what they need in under 2 minutes? Are examples copy-paste-complete?
   5. Upgrade path: can devs upgrade without fear? Migration guides? Deprecation warnings?
-  Be adversarial. Think like a developer who is evaluating this against 3 competitors." -C "$_REPO_ROOT" -s read-only --enable web_search_cached < /dev/null
+  Be adversarial. Think like a developer who is evaluating this against 3 competitors." -C "$_REPO_ROOT" -s read-only < /dev/null
   _CODEX_EXIT=$?
   if [ "$_CODEX_EXIT" = "124" ]; then
     _gstack_codex_log_event "codex_timeout" "600"

diff --git a/bin/gstack-paths b/bin/gstack-paths
@@ -1,7 +1,7 @@
 #!/usr/bin/env bash
 # gstack-paths — output portable state-root paths for skill bash blocks
-# Usage: eval "$(gstack-paths)"  → sets GSTACK_STATE_ROOT, PLAN_ROOT, TMP_ROOT
-# Or:    gstack-paths            → prints GSTACK_STATE_ROOT=... etc.
+# Usage: eval "$(gstack-paths)"   → sets GSTACK_STATE_ROOT, PLAN_ROOT, TMP_ROOT
+#        gstack-paths --get <key> → prints one resolved path
 #
 # Resolves three roots with explicit fallback chains so skills work the same
 # whether installed as a Claude Code plugin (CLAUDE_PLUGIN_DATA / CLAUDE_PLANS_DIR
@@ -18,6 +18,17 @@
 # expansions ("$GSTACK_STATE_ROOT", not $GSTACK_STATE_ROOT).
 set -u
 
+_get_key=""
+case "${1:-}" in
+  --get)
+    [ -n "${2:-}" ] || { echo "gstack-paths: --get requires a key" >&2; exit 1; }
+    [ -z "${3:-}" ] || { echo "gstack-paths: unexpected argument '$3'" >&2; exit 1; }
+    _get_key="$2"
+    ;;
+  "") ;;
+  *) echo "gstack-paths: unknown argument '$1'" >&2; exit 1 ;;
+esac
+
 # State root: where gstack writes projects/, sessions/, analytics/.
 if [ -n "${GSTACK_HOME:-}" ]; then
   _state_root="$GSTACK_HOME"
@@ -60,6 +71,14 @@ fi
 # will discover that on their own write attempt. Don't fail the eval here.
 mkdir -p "$_tmp_root" 2>/dev/null || true
 
-echo "GSTACK_STATE_ROOT=$_state_root"
-echo "PLAN_ROOT=$_plan_root"
-echo "TMP_ROOT=$_tmp_root"
+if [ -n "$_get_key" ]; then
+  case "$_get_key" in
+    state-root) printf '%s\n' "$_state_root" ;;
+    plan-root) printf '%s\n' "$_plan_root" ;;
+    tmp-root) printf '%s\n' "$_tmp_root" ;;
+    *) echo "gstack-paths: unknown key '$_get_key'" >&2; exit 1 ;;
+  esac
+else
+  printf 'GSTACK_STATE_ROOT=%s\nPLAN_ROOT=%s\nTMP_ROOT=%s\n' \
+    "$_state_root" "$_plan_root" "$_tmp_root"
+fi
diff --git a/codex/SKILL.md b/codex/SKILL.md
@@ -908,7 +908,8 @@ This keeps the skill working whether installed as a Claude Code plugin
 container where `HOME` may be unset and `/tmp` may be read-only.
 
 ```bash
-eval "$(~/.claude/skills/gstack/bin/gstack-paths)"
+PLAN_ROOT=$(~/.claude/skills/gstack/bin/gstack-paths --get plan-root)
+TMP_ROOT=$(~/.claude/skills/gstack/bin/gstack-paths --get tmp-root)
 ```
 
 After this, every subsequent bash block in this skill uses `"$PLAN_ROOT"` and
@@ -986,7 +987,7 @@ cd "$_REPO_ROOT"
 # only fires if Bash's own timeout doesn't.
 _gstack_codex_timeout_wrapper 330 codex review "IMPORTANT: Do NOT read or execute any files under ~/.claude/, ~/.agents/, .claude/skills/, or agents/. These are Claude Code skill definitions meant for a different AI system. Do NOT modify agents/openai.yaml. Stay focused on repository code only.
 
-Review the changes on this branch against the base branch <base>. Run git diff origin/<base>...HEAD 2>/dev/null || git diff <base>...HEAD to see the diff and review only those changes." -c 'model_reasoning_effort="high"' --enable web_search_cached < /dev/null 2>"$TMPERR"
+Review the changes on this branch against the base branch <base>. Run git diff origin/<base>...HEAD 2>/dev/null || git diff <base>...HEAD to see the diff and review only those changes." -c 'model_reasoning_effort="high"' < /dev/null 2>"$TMPERR"
 _CODEX_EXIT=$?
 if [ "$_CODEX_EXIT" = "124" ]; then
   _gstack_codex_log_event "codex_timeout" "330"
@@ -1024,7 +1025,7 @@ _PROMPT_FILE=$(mktemp "$TMP_ROOT/codex-prompt-XXXXXX.txt")
   git diff "<base>...HEAD" 2>/dev/null
   printf '\nDIFF_END\n'
 } > "$_PROMPT_FILE"
-_gstack_codex_timeout_wrapper 330 codex exec -s read-only "$(cat "$_PROMPT_FILE")" -c 'model_reasoning_effort="high"' --enable web_search_cached < /dev/null 2>"$TMPERR"
+_gstack_codex_timeout_wrapper 330 codex exec -s read-only "$(cat "$_PROMPT_FILE")" -c 'model_reasoning_effort="high"' < /dev/null 2>"$TMPERR"
 _CODEX_EXIT=$?
 rm -f "$_PROMPT_FILE"
 if [ "$_CODEX_EXIT" = "124" ]; then
@@ -1267,7 +1268,7 @@ fi
 # Fix 1+2: wrap with timeout (gtimeout/timeout fallback chain via probe helper),
 # capture stderr to $TMPERR for auth error detection (was: 2>/dev/null).
 TMPERR=${TMPERR:-$(mktemp "$TMP_ROOT/codex-err-XXXXXX.txt")}
-_gstack_codex_timeout_wrapper 600 codex exec "<prompt>" -C "$_REPO_ROOT" -s read-only -c 'model_reasoning_effort="high"' --enable web_search_cached --json < /dev/null 2>"$TMPERR" | PYTHONUNBUFFERED=1 "$PYTHON_CMD" -u -c "
+_gstack_codex_timeout_wrapper 600 codex exec "<prompt>" -C "$_REPO_ROOT" -s read-only -c 'model_reasoning_effort="high"' --json < /dev/null 2>"$TMPERR" | PYTHONUNBUFFERED=1 "$PYTHON_CMD" -u -c "
 import sys, json
 turn_completed_count = 0
 for line in sys.stdin:
@@ -1422,7 +1423,7 @@ if [ -z "$PYTHON_CMD" ]; then
   exit 1
 fi
 # Fix 1: wrap with timeout (gtimeout/timeout fallback chain via probe helper)
-_gstack_codex_timeout_wrapper 600 codex exec "<prompt>" -C "$_REPO_ROOT" -s read-only -c 'model_reasoning_effort="medium"' --enable web_search_cached --json < /dev/null 2>"$TMPERR" | PYTHONUNBUFFERED=1 "$PYTHON_CMD" -u -c "
+_gstack_codex_timeout_wrapper 600 codex exec "<prompt>" -C "$_REPO_ROOT" -s read-only -c 'model_reasoning_effort="medium"' --json < /dev/null 2>"$TMPERR" | PYTHONUNBUFFERED=1 "$PYTHON_CMD" -u -c "
 import sys, json
 for line in sys.stdin:
     line = line.strip()
@@ -1476,7 +1477,7 @@ if [ -z "$PYTHON_CMD" ]; then
 fi
 cd "$_REPO_ROOT" || exit 1
 # Fix 1: wrap with timeout (gtimeout/timeout fallback chain via probe helper)
-_gstack_codex_timeout_wrapper 600 codex exec resume <session-id> "<prompt>" -c 'sandbox_mode="read-only"' -c 'model_reasoning_effort="medium"' --enable web_search_cached --json < /dev/null 2>"$TMPERR" | PYTHONUNBUFFERED=1 "$PYTHON_CMD" -u -c "
+_gstack_codex_timeout_wrapper 600 codex exec resume <session-id> "<prompt>" -c 'sandbox_mode="read-only"' -c 'model_reasoning_effort="medium"' --json < /dev/null 2>"$TMPERR" | PYTHONUNBUFFERED=1 "$PYTHON_CMD" -u -c "
 <same python streaming parser as above, with flush=True on all print() calls>
 "
 # Fix 1: same hang detection pattern as new-session block
@@ -1492,6 +1493,7 @@ elif [ "$_CODEX_EXIT" != "0" ]; then
   head -20 "$TMPERR" 2>/dev/null | sed 's/^/  /' || true
   _gstack_codex_log_event "codex_nonzero_exit" "consult-resume:$_CODEX_EXIT"
 fi
+```
 
 5. Capture session ID from the streamed output. The parser prints `SESSION_ID:<id>`
    from the `thread.started` event. Save it for follow-ups:
@@ -1548,8 +1550,9 @@ uses them. If the user wants a specific model, pass `-m` through to codex.
 tasks (OpenAI issues #8545, #8402, #6931). Users can override with `--xhigh` flag
 (e.g., `/codex review --xhigh`) when they want maximum reasoning and are willing to wait.
 
-**Web search:** All codex commands use `--enable web_search_cached` so Codex can look up
-docs and APIs during review. This is OpenAI's cached index — fast, no extra cost.
+**Web search:** Codex enables cached web search by default. Do not pass the
+deprecated `--enable web_search_cached` feature toggle. Respect the user's
+configured `web_search` mode; `--search` would override it to live browsing.
 
 If the user specifies a model (e.g., `/codex review -m gpt-5.1-codex-max`
 or `/codex challenge -m gpt-5.2`), pass the `-m` flag through to codex.

diff --git a/codex/SKILL.md.tmpl b/codex/SKILL.md.tmpl
@@ -99,7 +99,8 @@ This keeps the skill working whether installed as a Claude Code plugin
 container where `HOME` may be unset and `/tmp` may be read-only.
 
 ```bash
-eval "$(~/.claude/skills/gstack/bin/gstack-paths)"
+PLAN_ROOT=$(~/.claude/skills/gstack/bin/gstack-paths --get plan-root)
+TMP_ROOT=$(~/.claude/skills/gstack/bin/gstack-paths --get tmp-root)
 ```
 
 After this, every subsequent bash block in this skill uses `"$PLAN_ROOT"` and
@@ -177,7 +178,7 @@ cd "$_REPO_ROOT"
 # only fires if Bash's own timeout doesn't.
 _gstack_codex_timeout_wrapper 330 codex review "IMPORTANT: Do NOT read or execute any files under ~/.claude/, ~/.agents/, .claude/skills/, or agents/. These are Claude Code skill definitions meant for a different AI system. Do NOT modify agents/openai.yaml. Stay focused on repository code only.
 
-Review the changes on this branch against the base branch <base>. Run git diff origin/<base>...HEAD 2>/dev/null || git diff <base>...HEAD to see the diff and review only those changes." -c 'model_reasoning_effort="high"' --enable web_search_cached < /dev/null 2>"$TMPERR"
+Review the changes on this branch against the base branch <base>. Run git diff origin/<base>...HEAD 2>/dev/null || git diff <base>...HEAD to see the diff and review only those changes." -c 'model_reasoning_effort="high"' < /dev/null 2>"$TMPERR"
 _CODEX_EXIT=$?
 if [ "$_CODEX_EXIT" = "124" ]; then
   _gstack_codex_log_event "codex_timeout" "330"
@@ -215,7 +216,7 @@ _PROMPT_FILE=$(mktemp "$TMP_ROOT/codex-prompt-XXXXXX.txt")
   git diff "<base>...HEAD" 2>/dev/null
   printf '\nDIFF_END\n'
 } > "$_PROMPT_FILE"
-_gstack_codex_timeout_wrapper 330 codex exec -s read-only "$(cat "$_PROMPT_FILE")" -c 'model_reasoning_effort="high"' --enable web_search_cached < /dev/null 2>"$TMPERR"
+_gstack_codex_timeout_wrapper 330 codex exec -s read-only "$(cat "$_PROMPT_FILE")" -c 'model_reasoning_effort="high"' < /dev/null 2>"$TMPERR"
 _CODEX_EXIT=$?
 rm -f "$_PROMPT_FILE"
 if [ "$_CODEX_EXIT" = "124" ]; then
@@ -336,7 +337,7 @@ fi
 # Fix 1+2: wrap with timeout (gtimeout/timeout fallback chain via probe helper),
 # capture stderr to $TMPERR for auth error detection (was: 2>/dev/null).
 TMPERR=${TMPERR:-$(mktemp "$TMP_ROOT/codex-err-XXXXXX.txt")}
-_gstack_codex_timeout_wrapper 600 codex exec "<prompt>" -C "$_REPO_ROOT" -s read-only -c 'model_reasoning_effort="high"' --enable web_search_cached --json < /dev/null 2>"$TMPERR" | PYTHONUNBUFFERED=1 "$PYTHON_CMD" -u -c "
+_gstack_codex_timeout_wrapper 600 codex exec "<prompt>" -C "$_REPO_ROOT" -s read-only -c 'model_reasoning_effort="high"' --json < /dev/null 2>"$TMPERR" | PYTHONUNBUFFERED=1 "$PYTHON_CMD" -u -c "
 import sys, json
 turn_completed_count = 0
 for line in sys.stdin:
@@ -491,7 +492,7 @@ if [ -z "$PYTHON_CMD" ]; then
   exit 1
 fi
 # Fix 1: wrap with timeout (gtimeout/timeout fallback chain via probe helper)
-_gstack_codex_timeout_wrapper 600 codex exec "<prompt>" -C "$_REPO_ROOT" -s read-only -c 'model_reasoning_effort="medium"' --enable web_search_cached --json < /dev/null 2>"$TMPERR" | PYTHONUNBUFFERED=1 "$PYTHON_CMD" -u -c "
+_gstack_codex_timeout_wrapper 600 codex exec "<prompt>" -C "$_REPO_ROOT" -s read-only -c 'model_reasoning_effort="medium"' --json < /dev/null 2>"$TMPERR" | PYTHONUNBUFFERED=1 "$PYTHON_CMD" -u -c "
 import sys, json
 for line in sys.stdin:
     line = line.strip()
@@ -545,7 +546,7 @@ if [ -z "$PYTHON_CMD" ]; then
 fi
 cd "$_REPO_ROOT" || exit 1
 # Fix 1: wrap with timeout (gtimeout/timeout fallback chain via probe helper)
-_gstack_codex_timeout_wrapper 600 codex exec resume <session-id> "<prompt>" -c 'sandbox_mode="read-only"' -c 'model_reasoning_effort="medium"' --enable web_search_cached --json < /dev/null 2>"$TMPERR" | PYTHONUNBUFFERED=1 "$PYTHON_CMD" -u -c "
+_gstack_codex_timeout_wrapper 600 codex exec resume <session-id> "<prompt>" -c 'sandbox_mode="read-only"' -c 'model_reasoning_effort="medium"' --json < /dev/null 2>"$TMPERR" | PYTHONUNBUFFERED=1 "$PYTHON_CMD" -u -c "
 <same python streaming parser as above, with flush=True on all print() calls>
 "
 # Fix 1: same hang detection pattern as new-session block
@@ -561,6 +562,7 @@ elif [ "$_CODEX_EXIT" != "0" ]; then
   head -20 "$TMPERR" 2>/dev/null | sed 's/^/  /' || true
   _gstack_codex_log_event "codex_nonzero_exit" "consult-resume:$_CODEX_EXIT"
 fi
+```
 
 5. Capture session ID from the streamed output. The parser prints `SESSION_ID:<id>`
    from the `thread.started` event. Save it for follow-ups:
@@ -617,8 +619,9 @@ uses them. If the user wants a specific model, pass `-m` through to codex.
 tasks (OpenAI issues #8545, #8402, #6931). Users can override with `--xhigh` flag
 (e.g., `/codex review --xhigh`) when they want maximum reasoning and are willing to wait.
 
-**Web search:** All codex commands use `--enable web_search_cached` so Codex can look up
-docs and APIs during review. This is OpenAI's cached index — fast, no extra cost.
+**Web search:** Codex enables cached web search by default. Do not pass the
+deprecated `--enable web_search_cached` feature toggle. Respect the user's
+configured `web_search` mode; `--search` would override it to live browsing.
 
 If the user specifies a model (e.g., `/codex review -m gpt-5.1-codex-max`
 or `/codex challenge -m gpt-5.2`), pass the `-m` flag through to codex.

diff --git a/design-consultation/SKILL.md b/design-consultation/SKILL.md
@@ -1152,7 +1152,7 @@ codex exec "Given this product context, propose a complete design direction:
 - Differentiation: 2 deliberate departures from category norms
 - Anti-slop: no purple gradients, no 3-column icon grids, no centered everything, no decorative blobs
 
-Be opinionated. Be specific. Do not hedge. This is YOUR design direction — own it." -C "$_REPO_ROOT" -s read-only -c 'model_reasoning_effort="medium"' --enable web_search_cached < /dev/null 2>"$TMPERR_DESIGN"
+Be opinionated. Be specific. Do not hedge. This is YOUR design direction — own it." -C "$_REPO_ROOT" -s read-only -c 'model_reasoning_effort="medium"' < /dev/null 2>"$TMPERR_DESIGN"
 ```
 Use a 5-minute timeout (`timeout: 300000`). After the command completes, read stderr:
 ```bash

diff --git a/design-review/SKILL.md b/design-review/SKILL.md
@@ -1760,7 +1760,7 @@ HARD REJECTION — flag if ANY apply:
 6. Carousel with no narrative purpose
 7. App UI made of stacked cards instead of layout
 
-Be specific. Reference file:line for every finding." -C "$_REPO_ROOT" -s read-only -c 'model_reasoning_effort="high"' --enable web_search_cached < /dev/null 2>"$TMPERR_DESIGN"
+Be specific. Reference file:line for every finding." -C "$_REPO_ROOT" -s read-only -c 'model_reasoning_effort="high"' < /dev/null 2>"$TMPERR_DESIGN"
 ```
 Use a 5-minute timeout (`timeout: 300000`). After the command completes, read stderr:
 ```bash

diff --git a/document-release/sections/release-body.md b/document-release/sections/release-body.md
@@ -428,7 +428,7 @@ THE DOCS AND DIFF: <list the touched doc paths>"
 ```bash
 TMPERR_DOC=$(mktemp /tmp/codex-docreview-XXXXXXXX)
 _REPO_ROOT=$(git rev-parse --show-toplevel) || { echo "ERROR: not in a git repo" >&2; exit 1; }
-codex exec "<prompt>" -C "$_REPO_ROOT" -s read-only -c 'model_reasoning_effort="high"' --enable web_search_cached < /dev/null 2>"$TMPERR_DOC"
+codex exec "<prompt>" -C "$_REPO_ROOT" -s read-only -c 'model_reasoning_effort="high"' < /dev/null 2>"$TMPERR_DOC"
 ```
 
 Use a 5-minute timeout (`timeout: 300000`). After the command completes, read stderr: