[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M77Z9FWR6DW2EYEXQWN6ASWW":3,"skill-same:01M77Z9FWR6DW2EYEXQWN6ASWW":58},{"skillNo":4,"name":5,"nameZh":6,"description":7,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":16,"categories":17,"keywords":18,"publishedAt":19,"linkOnly":20,"markdownContent":21,"markdownBody":22,"frontMatter":23,"refName":35,"commitSha":36,"skillDirectory":37,"forksCount":38,"repositoryHtmlUrl":39,"repositoryHomepageUrl":40,"ownerHtmlUrl":41,"ownerBlogUrl":6,"ownerDescription":42,"updatedAt":43,"install":44,"resources":57},"01M77Z9FWR6DW2EYEXQWN6ASWW","benchmark-models",null,"Cross-model benchmark for gstack skills. (gstack)","Lord1Egypt\u002Fawesome-skill-forge","Lord1Egypt","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F99746359?v=4","01M7592YDNT0XK9WJ0T2MQVPDN","Mohamed Mounir Ali AL Keshita","01M75GRFNHC8VZNWEB8DKDE433",3,"MIT","https:\u002F\u002Fgithub.com\u002FLord1Egypt\u002Fawesome-skill-forge\u002Fblob\u002Fmaster\u002Fcommunity\u002Fgstack\u002Fg\u002Fgarrytan_gstack_benchmark-models\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: benchmark-models\npreamble-tier: 1\nversion: 1.0.0\ndescription: Cross-model benchmark for gstack skills. (gstack)\ntriggers:\n  - cross model benchmark\n  - compare claude gpt gemini\n  - benchmark skill across models\n  - which model should I use\nallowed-tools:\n  - Bash\n  - Read\n  - AskUserQuestion\n---\n\u003C!-- AUTO-GENERATED from SKILL.md.tmpl — do not edit directly -->\n\u003C!-- Regenerate: bun run gen:skill-docs -->\n\n\n## When to invoke this skill\n\nRuns the same prompt through Claude,\nGPT (via Codex CLI), and Gemini side-by-side — compares latency, tokens, cost,\nand optionally quality via LLM judge. Answers \"which model is actually best\nfor this skill?\" with data instead of vibes. Separate from \u002Fbenchmark, which\nmeasures web page performance. Use when: \"benchmark models\", \"compare models\",\n\"which model is best for X\", \"cross-model comparison\", \"model shootout\".\n\nVoice triggers (speech-to-text aliases): \"compare models\", \"model shootout\", \"which model is best\".\n\n## Preamble (run first)\n\n```bash\n_UPD=$(~\u002F.claude\u002Fskills\u002Fgstack\u002Fbin\u002Fgstack-update-check 2>\u002Fdev\u002Fnull || .claude\u002Fskills\u002Fgstack\u002Fbin\u002Fgstack-update-check 2>\u002Fdev\u002Fnull || true)\n[ -n \"$_UPD\" ] && echo \"$_UPD\" || true\nmkdir -p ~\u002F.gstack\u002Fsessions\ntouch ~\u002F.gstack\u002Fsessions\u002F\"$PPID\"\n_SESSIONS=$(find ~\u002F.gstack\u002Fsessions -mmin -120 -type f 2>\u002Fdev\u002Fnull | wc -l | tr -d ' ')\nfind ~\u002F.gstack\u002Fsessions -mmin +120 -type f -exec rm {} + 2>\u002Fdev\u002Fnull || true\n_PROACTIVE=$(~\u002F.claude\u002Fskills\u002Fgstack\u002Fbin\u002Fgstack-config get proactive 2>\u002Fdev\u002Fnull || echo \"true\")\n_PROACTIVE_PROMPTED=$([ -f ~\u002F.gstack\u002F.proactive-prompted ] && echo \"yes\" || echo \"no\")\n_BRANCH=$(git branch --show-current 2>\u002Fdev\u002Fnull || echo \"unknown\")\necho \"BRANCH: $_BRANCH\"\n_SKILL_PREFIX=$(~\u002F.claude\u002Fskills\u002Fgstack\u002Fbin\u002Fgstack-config get skill_prefix 2>\u002Fdev\u002Fnull || echo \"false\")\necho \"PROACTIVE: $_PROACTIVE\"\necho \"PROACTIVE_PROMPTED: $_PROACTIVE_PROMPTED\"\necho \"SKILL_PREFIX: $_SKILL_PREFIX\"\nsource \u003C(~\u002F.claude\u002Fskills\u002Fgstack\u002Fbin\u002Fgstack-repo-mode 2>\u002Fdev\u002Fnull) || true\nREPO_MODE=${REPO_MODE:-unknown}\necho \"REPO_MODE: $REPO_MODE\"\n_SESSION_KIND=$(~\u002F.claude\u002Fskills\u002Fgstack\u002Fbin\u002Fgstack-session-kind 2>\u002Fdev\u002Fnull || echo \"interactive\")\ncase \"$_SESSION_KIND\" in spawned|headless|interactive) ;; *) _SESSION_KIND=\"interactive\" ;; esac\necho \"SESSION_KIND: $_SESSION_KIND\"\n_LAKE_SEEN=$([ -f ~\u002F.gstack\u002F.completeness-intro-seen ] && echo \"yes\" || echo \"no\")\necho \"LAKE_INTRO: $_LAKE_SEEN\"\n_TEL=$(~\u002F.claude\u002Fskills\u002Fgstack\u002Fbin\u002Fgstack-config get telemetry 2>\u002Fdev\u002Fnull || true)\n_TEL_PROMPTED=$([ -f ~\u002F.gstack\u002F.telemetry-prompted ] && echo \"yes\" || echo \"no\")\n_TEL_START=$(date +%s)\n_SESSION_ID=\"$$-$(date +%s)\"\necho \"TELEMETRY: ${_TEL:-off}\"\necho \"TEL_PROMPTED: $_TEL_PROMPTED\"\n_EXPLAIN_LEVEL=$(~\u002F.claude\u002Fskills\u002Fgstack\u002Fbin\u002Fgstack-config get explain_level 2>\u002Fdev\u002Fnull || echo \"default\")\nif [ \"$_EXPLAIN_LEVEL\" != \"default\" ] && [ \"$_EXPLAIN_LEVEL\" != \"terse\" ]; then _EXPLAIN_LEVEL=\"default\"; fi\necho \"EXPLAIN_LEVEL: $_EXPLAIN_LEVEL\"\n_QUESTION_TUNING=$(~\u002F.claude\u002Fskills\u002Fgstack\u002Fbin\u002Fgstack-config get question_tuning 2>\u002Fdev\u002Fnull || echo \"false\")\necho \"QUESTION_TUNING: $_QUESTION_TUNING\"\nmkdir -p ~\u002F.gstack\u002Fanalytics\nif [ \"$_TEL\" != \"off\" ]; then\necho '{\"skill\":\"benchmark-models\",\"ts\":\"'$(date -u +%Y-%m-%dT%H:%M:%SZ)'\",\"repo\":\"'$(_repo=$(basename \"$(git rev-parse --show-toplevel 2>\u002Fdev\u002Fnull)\" 2>\u002Fdev\u002Fnull | tr -cd 'a-zA-Z0-9._-'); echo \"${_repo:-unknown}\")'\"}'  >> ~\u002F.gstack\u002Fanalytics\u002Fskill-usage.jsonl 2>\u002Fdev\u002Fnull || true\nfi\nfor _PF in $(find ~\u002F.gstack\u002Fanalytics -maxdepth 1 -name '.pending-*' 2>\u002Fdev\u002Fnull); do\n  if [ -f \"$_PF\" ]; then\n    if [ \"$_TEL\" != \"off\" ] && [ -x \"~\u002F.claude\u002Fskills\u002Fgstack\u002Fbin\u002Fgstack-telemetry-log\" ]; then\n      ~\u002F.claude\u002Fskills\u002Fgstack\u002Fbin\u002Fgstack-telemetry-log --event-type skill_run --skill _pending_finalize --outcome unknown --session-id \"$_SESSION_ID\" 2>\u002Fdev\u002Fnull || true\n    fi\n    rm -f \"$_PF\" 2>\u002Fdev\u002Fnull || true\n  fi\n  break\ndone\neval \"$(~\u002F.claude\u002Fskills\u002Fgstack\u002Fbin\u002Fgstack-slug 2>\u002Fdev\u002Fnull)\" 2>\u002Fdev\u002Fnull || true\n_LEARN_FILE=\"${GSTACK_HOME:-$HOME\u002F.gstack}\u002Fprojects\u002F${SLUG:-unknown}\u002Flearnings.jsonl\"\nif [ -f \"$_LEARN_FILE\" ]; then\n  _LEARN_COUNT=$(wc -l \u003C \"$_LEARN_FILE\" 2>\u002Fdev\u002Fnull | tr -d ' ')\n  echo \"LEARNINGS: $_LEARN_COUNT entries loaded\"\n  if [ \"$_LEARN_COUNT\" -gt 5 ] 2>\u002Fdev\u002Fnull; then\n    ~\u002F.claude\u002Fskills\u002Fgstack\u002Fbin\u002Fgstack-learnings-search --limit 3 2>\u002Fdev\u002Fnull || true\n  fi\nelse\n  echo \"LEARNINGS: 0\"\nfi\n~\u002F.claude\u002Fskills\u002Fgstack\u002Fbin\u002Fgstack-timeline-log '{\"skill\":\"benchmark-models\",\"event\":\"started\",\"branch\":\"'\"$_BRANCH\"'\",\"session\":\"'\"$_SESSION_ID\"'\"}' 2>\u002Fdev\u002Fnull &\n_HAS_ROUTING=\"no\"\nif [ -f CLAUDE.md ] && grep -q \"## Skill routing\" CLAUDE.md 2>\u002Fdev\u002Fnull; then\n  _HAS_ROUTING=\"yes\"\nfi\n_ROUTING_DECLINED=$(~\u002F.claude\u002Fskills\u002Fgstack\u002Fbin\u002Fgstack-config get routing_declined 2>\u002Fdev\u002Fnull || echo \"false\")\necho \"HAS_ROUTING: $_HAS_ROUTING\"\necho \"ROUTING_DECLINED: $_ROUTING_DECLINED\"\n_VENDORED=\"no\"\nif [ -d \".claude\u002Fskills\u002Fgstack\" ] && [ ! -L \".claude\u002Fskills\u002Fgstack\" ]; then\n  if [ -f \".claude\u002Fskills\u002Fgstack\u002FVERSION\" ] || [ -d \".claude\u002Fskills\u002Fgstack\u002F.git\" ]; then\n    _VENDORED=\"yes\"\n  fi\nfi\necho \"VENDORED_GSTACK: $_VENDORED\"\necho \"MODEL_OVERLAY: claude\"\n_CHECKPOINT_MODE=$(~\u002F.claude\u002Fskills\u002Fgstack\u002Fbin\u002Fgstack-config get checkpoint_mode 2>\u002Fdev\u002Fnull || echo \"explicit\")\n_CHECKPOINT_PUSH=$(~\u002F.claude\u002Fskills\u002Fgstack\u002Fbin\u002Fgstack-config get checkpoint_push 2>\u002Fdev\u002Fnull || echo \"false\")\necho \"CHECKPOINT_MODE: $_CHECKPOINT_MODE\"\necho \"CHECKPOINT_PUSH: $_CHECKPOINT_PUSH\"\n# Plan-mode hint for skills like \u002Fspec that branch behavior on plan-mode state.\n# Claude Code exposes plan mode via system reminders; we detect best-effort\n# from CLAUDE_PLAN_FILE (set by the harness when plan mode is active) and\n# fall back to \"inactive\". Codex hosts and Claude execution mode both end up\n# inactive, which is the safe default (defaults to file+execute pipeline).\nif [ -n \"${CLAUDE_PLAN_FILE:-}${GSTACK_PLAN_MODE_FORCE:-}\" ]; then\n  export GSTACK_PLAN_MODE=\"active\"\nelif [ \"${GSTACK_PLAN_MODE:-}\" = \"active\" ]; then\n  export GSTACK_PLAN_MODE=\"active\"\nelse\n  export GSTACK_PLAN_MODE=\"inactive\"\nfi\necho \"GSTACK_PLAN_MODE: $GSTACK_PLAN_MODE\"\n[ -n \"$OPENCLAW_SESSION\" ] && echo \"SPAWNED_SESSION: true\" || true\n```\n\n## Plan Mode Safe Operations\n\nIn plan mode, allowed because they inform the plan: `$B`, `$D`, `codex exec`\u002F`codex review`, writes to `~\u002F.gstack\u002F`, writes to the plan file, and `open` for generated artifacts.\n\n## Skill Invocation During Plan Mode\n\nIf the user invokes a skill in plan mode, the skill takes precedence over generic plan mode behavior. **Treat the skill file as executable instructions, not reference.** Follow it step by step starting from Step 0; the first AskUserQuestion is the workflow entering plan mode, not a violation of it. AskUserQuestion (any variant — `mcp__*__AskUserQuestion` or native; see \"AskUserQuestion Format → Tool resolution\") satisfies plan mode's end-of-turn requirement. If AskUserQuestion is unavailable or a call fails, follow the AskUserQuestion Format failure fallback: `headless` → BLOCKED; `interactive` → the prose fallback (also satisfies end-of-turn). At a STOP point, stop immediately. Do not continue the workflow or call ExitPlanMode there. Commands marked \"PLAN MODE EXCEPTION — ALWAYS RUN\" execute. Call ExitPlanMode only after the skill workflow completes, or if the user tells you to cancel the skill or leave plan mode.\n\nIf `PROACTIVE` is `\"false\"`, do not auto-invoke or proactively suggest skills. If a skill seems useful, ask: \"I think \u002Fskillname might help here — want me to run it?\"\n\nIf `SKILL_PREFIX` is `\"true\"`, suggest\u002Finvoke `\u002Fgstack-*` names. Disk paths stay `~\u002F.claude\u002Fskills\u002Fgstack\u002F[skill-name]\u002FSKILL.md`.\n\nIf output shows `UPGRADE_AVAILABLE \u003Cold> \u003Cnew>`: read `~\u002F.claude\u002Fskills\u002Fgstack\u002Fgstack-upgrade\u002FSKILL.md` and follow the \"Inline upgrade flow\" (auto-upgrade if configured, otherwise AskUserQuestion with 4 options, write snooze state if declined).\n\nIf output shows `JUST_UPGRADED \u003Cfrom> \u003Cto>`: print \"Running gstack v{to} (just updated!)\". If `SPAWNED_SESSION` is true, skip feature discovery.\n\nFeature discovery, max one prompt per session:\n- Missing `~\u002F.claude\u002Fskills\u002Fgstack\u002F.feature-prompted-continuous-checkpoint`: AskUserQuestion for Continuous checkpoint auto-commits. If accepted, run `~\u002F.claude\u002Fskills\u002Fgstack\u002Fbin\u002Fgstack-config set checkpoint_mode continuous`. Always touch marker.\n- Missing `~\u002F.claude\u002Fskills\u002Fgstack\u002F.feature-prompted-model-overlay`: inform \"Model overlays are active. MODEL_OVERLAY shows the patch.\" Always touch marker.\n\nAfter upgrade prompts, continue workflow.\n\nIf `WRITING_STYLE_PENDING` is `yes`: ask once about writing style:\n\n> v1 prompts are simpler: first-use jargon glosses, outcome-framed questions, shorter prose. Keep default or restore terse?\n\nOptions:\n- A) Keep the new default (recommended — good writing helps everyone)\n- B) Restore V0 prose — set `explain_level: terse`\n\nIf A: leave `explain_level` unset (defaults to `default`).\nIf B: run `~\u002F.claude\u002Fskills\u002Fgstack\u002Fbin\u002Fgstack-config set explain_level terse`.\n\nAlways run (regardless of choice):\n```bash\nrm -f ~\u002F.gstack\u002F.writing-style-prompt-pending\ntouch ~\u002F.gstack\u002F.writing-style-prompted\n```\n\nSkip if `WRITING_STYLE_PENDING` is `no`.\n\nIf `LAKE_INTRO` is `no`: say \"gstack follows the **Boil the Ocean** principle — do the complete thing when AI makes marginal cost near-zero. Read more: https:\u002F\u002Fgarryslist.org\u002Fposts\u002Fboil-the-ocean\" Offer to open:\n\n```bash\nopen https:\u002F\u002Fgarryslist.org\u002Fposts\u002Fboil-the-ocean\ntouch ~\u002F.gstack\u002F.completeness-intro-seen\n```\n\nOnly run `open` if yes. Always run `touch`.\n\nIf `TEL_PROMPTED` is `no` AND `LAKE_INTRO` is `yes`: ask telemetry once via AskUserQuestion:\n\n> Help gstack get better. Share usage data only: skill, duration, crashes, stable device ID. No code or file paths. Your repo name is recorded locally only and stripped before any upload.\n\nOptions:\n- A) Help gstack get better! (recommended)\n- B) No thanks\n\nIf A: run `~\u002F.claude\u002Fskills\u002Fgstack\u002Fbin\u002Fgstack-config set telemetry community`\n\nIf B: ask follow-up:\n\n> Anonymous mode sends only aggregate usage, no unique ID.\n\nOptions:\n- A) Sure, anonymous is fine\n- B) No thanks, fully off\n\nIf B→A: run `~\u002F.claude\u002Fskills\u002Fgstack\u002Fbin\u002Fgstack-config set telemetry anonymous`\nIf B→B: run `~\u002F.claude\u002Fskills\u002Fgstack\u002Fbin\u002Fgstack-config set telemetry off`\n\nAlways run:\n```bash\ntouch ~\u002F.gstack\u002F.telemetry-prompted\n```\n\nSkip if `TEL_PROMPTED` is `yes`.\n\nIf `PROACTIVE_PROMPTED` is `no` AND `TEL_PROMPTED` is `yes`: ask once:\n\n> Let gstack proactively suggest skills, like \u002Fqa for \"does this work?\" or \u002Finvestigate for bugs?\n\nOptions:\n- A) Keep it on (recommended)\n- B) Turn it off — I'll type \u002Fcommands myself\n\nIf A: run `~\u002F.claude\u002Fskills\u002Fgstack\u002Fbin\u002Fgstack-config set proactive true`\nIf B: run `~\u002F.claude\u002Fskills\u002Fgstack\u002Fbin\u002Fgstack-config set proactive false`\n\nAlways run:\n```bash\ntouch ~\u002F.gstack\u002F.proactive-prompted\n```\n\nSkip if `PROACTIVE_PROMPTED` is `yes`.\n\nIf `HAS_ROUTING` is `no` AND `ROUTING_DECLINED` is `false` AND `PROACTIVE_PROMPTED` is `yes`:\nCheck if a CLAUDE.md file exists in the project root. If it does not exist, create it.\n\nUse AskUserQuestion:\n\n> gstack works best when your project's CLAUDE.md includes skill routing rules.\n\nOptions:\n- A) Add routing rules to CLAUDE.md (recommended)\n- B) No thanks, I'll invoke skills manually\n\nIf A: Append this section to the end of CLAUDE.md:\n\n```markdown\n\n## Skill routing\n\nWhen the user's request matches an available skill, invoke it via the Skill tool. When in doubt, invoke the skill.\n\nKey routing rules:\n- Product ideas\u002Fbrainstorming → invoke \u002Foffice-hours\n- Strategy\u002Fscope → invoke \u002Fplan-ceo-review\n- Architecture → invoke \u002Fplan-eng-review\n- Design system\u002Fplan review → invoke \u002Fdesign-consultation or \u002Fplan-design-review\n- Full review pipeline → invoke \u002Fautoplan\n- Bugs\u002Ferrors → invoke \u002Finvestigate\n- QA\u002Ftesting site behavior → invoke \u002Fqa or \u002Fqa-only\n- Code review\u002Fdiff check → invoke \u002Freview\n- Visual polish → invoke \u002Fdesign-review\n- Ship\u002Fdeploy\u002FPR → invoke \u002Fship or \u002Fland-and-deploy\n- Save progress → invoke \u002Fcontext-save\n- Resume context → invoke \u002Fcontext-restore\n- Author a backlog-ready spec\u002Fissue → invoke \u002Fspec\n```\n\nThen commit the change: `git add CLAUDE.md && git commit -m \"chore: add gstack skill routing rules to CLAUDE.md\"`\n\nIf B: run `~\u002F.claude\u002Fskills\u002Fgstack\u002Fbin\u002Fgstack-config set routing_declined true` and say they can re-enable with `gstack-config set routing_declined false`.\n\nThis only happens once per project. Skip if `HAS_ROUTING` is `yes` or `ROUTING_DECLINED` is `true`.\n\nIf `VENDORED_GSTACK` is `yes`, warn once via AskUserQuestion unless `~\u002F.gstack\u002F.vendoring-warned-$SLUG` exists:\n\n> This project has gstack vendored in `.claude\u002Fskills\u002Fgstack\u002F`. Vendoring is deprecated.\n> Migrate to team mode?\n\nOptions:\n- A) Yes, migrate to team mode now\n- B) No, I'll handle it myself\n\nIf A:\n1. Run `git rm -r .claude\u002Fskills\u002Fgstack\u002F`\n2. Run `echo '.claude\u002Fskills\u002Fgstack\u002F' >> .gitignore`\n3. Run `~\u002F.claude\u002Fskills\u002Fgstack\u002Fbin\u002Fgstack-team-init required` (or `optional`)\n4. Run `git add .claude\u002F .gitignore CLAUDE.md && git commit -m \"chore: migrate gstack from vendored to team mode\"`\n5. Tell the user: \"Done. Each developer now runs: `cd ~\u002F.claude\u002Fskills\u002Fgstack && .\u002Fsetup --team`\"\n\nIf B: say \"OK, you're on your own to keep the vendored copy up to date.\"\n\nAlways run (regardless of choice):\n```bash\neval \"$(~\u002F.claude\u002Fskills\u002Fgstack\u002Fbin\u002Fgstack-slug 2>\u002Fdev\u002Fnull)\" 2>\u002Fdev\u002Fnull || true\ntouch ~\u002F.gstack\u002F.vendoring-warned-${SLUG:-unknown}\n```\n\nIf marker exists, skip.\n\nIf `SPAWNED_SESSION` is `\"true\"`, you are running inside a session spawned by an\nAI orchestrator (e.g., OpenClaw). In spawned sessions:\n- Do NOT use AskUserQuestion for interactive prompts. Auto-choose the recommended option.\n- Do NOT run upgrade checks, telemetry prompts, routing injection, or lake intro.\n- Focus on completing the task and reporting results via prose output.\n- End with a completion report: what shipped, decisions made, anything uncertain.\n\n## Artifacts Sync (skill start)\n\n```bash\n_GSTACK_HOME=\"${GSTACK_HOME:-$HOME\u002F.gstack}\"\n# Prefer the v1.27.0.0 artifacts file; fall back to brain file for users\n# upgrading mid-stream before the migration script runs.\nif [ -f \"$HOME\u002F.gstack-artifacts-remote.txt\" ]; then\n  _BRAIN_REMOTE_FILE=\"$HOME\u002F.gstack-artifacts-remote.txt\"\nelse\n  _BRAIN_REMOTE_FILE=\"$HOME\u002F.gstack-brain-remote.txt\"\nfi\n_BRAIN_SYNC_BIN=\"~\u002F.claude\u002Fskills\u002Fgstack\u002Fbin\u002Fgstack-brain-sync\"\n_BRAIN_CONFIG_BIN=\"~\u002F.claude\u002Fskills\u002Fgstack\u002Fbin\u002Fgstack-config\"\n\n# \u002Fsync-gbrain context-load: teach the agent to use gbrain when it's available.\n# Per-worktree pin: post-spike redesign uses kubectl-style `.gbrain-source` in the\n# git toplevel to scope queries. Look for the pin in the worktree (not a global\n# state file) so that opening worktree B without a pin doesn't claim \"indexed\"\n# just because worktree A was synced. Empty string when gbrain is not\n# configured (zero context cost for non-gbrain users).\n_GBRAIN_CONFIG=\"$HOME\u002F.gbrain\u002Fconfig.json\"\nif [ -f \"$_GBRAIN_CONFIG\" ] && command -v gbrain >\u002Fdev\u002Fnull 2>&1; then\n  _GBRAIN_VERSION_OK=$(gbrain --version 2>\u002Fdev\u002Fnull | grep -c '^gbrain ' || echo 0)\n  if [ \"$_GBRAIN_VERSION_OK\" -gt 0 ] 2>\u002Fdev\u002Fnull; then\n    _GBRAIN_PIN_PATH=\"\"\n    _REPO_TOP=$(git rev-parse --show-toplevel 2>\u002Fdev\u002Fnull || echo \"\")\n    if [ -n \"$_REPO_TOP\" ] && [ -f \"$_REPO_TOP\u002F.gbrain-source\" ]; then\n      _GBRAIN_PIN_PATH=\"$_REPO_TOP\u002F.gbrain-source\"\n    fi\n    if [ -n \"$_GBRAIN_PIN_PATH\" ]; then\n      echo \"GBrain configured. Prefer \\`gbrain search\\`\u002F\\`gbrain query\\` over Grep for\"\n      echo \"semantic questions; use \\`gbrain code-def\\`\u002F\\`code-refs\\`\u002F\\`code-callers\\` for\"\n      echo \"symbol-aware code lookup. See \\\"## GBrain Search Guidance\\\" in CLAUDE.md.\"\n      echo \"Run \u002Fsync-gbrain to refresh.\"\n    else\n      echo \"GBrain configured but this worktree isn't pinned yet. Run \\`\u002Fsync-gbrain --full\\`\"\n      echo \"before relying on \\`gbrain search\\` for code questions in this worktree.\"\n      echo \"Falls back to Grep until pinned.\"\n    fi\n  fi\nfi\n\n_BRAIN_SYNC_MODE=$(\"$_BRAIN_CONFIG_BIN\" get artifacts_sync_mode 2>\u002Fdev\u002Fnull || echo off)\n\n# Detect remote-MCP mode (Path 4 of \u002Fsetup-gbrain). Local artifacts sync is\n# a no-op in remote mode; the brain server pulls from GitHub\u002FGitLab on its\n# own cadence. Read claude.json directly to keep this preamble fast (no\n# subprocess to claude CLI on every skill start).\n_GBRAIN_MCP_MODE=\"none\"\nif command -v jq >\u002Fdev\u002Fnull 2>&1 && [ -f \"$HOME\u002F.claude.json\" ]; then\n  _GBRAIN_MCP_TYPE=$(jq -r '.mcpServers.gbrain.type \u002F\u002F .mcpServers.gbrain.transport \u002F\u002F empty' \"$HOME\u002F.claude.json\" 2>\u002Fdev\u002Fnull)\n  case \"$_GBRAIN_MCP_TYPE\" in\n    url|http|sse) _GBRAIN_MCP_MODE=\"remote-http\" ;;\n    stdio) _GBRAIN_MCP_MODE=\"local-stdio\" ;;\n  esac\nfi\n\nif [ -f \"$_BRAIN_REMOTE_FILE\" ] && [ ! -d \"$_GSTACK_HOME\u002F.git\" ] && [ \"$_BRAIN_SYNC_MODE\" = \"off\" ]; then\n  _BRAIN_NEW_URL=$(head -1 \"$_BRAIN_REMOTE_FILE\" 2>\u002Fdev\u002Fnull | tr -d '[:space:]')\n  if [ -n \"$_BRAIN_NEW_URL\" ]; then\n    echo \"ARTIFACTS_SYNC: artifacts repo detected: $_BRAIN_NEW_URL\"\n    echo \"ARTIFACTS_SYNC: run 'gstack-brain-restore' to pull your cross-machine artifacts (or 'gstack-config set artifacts_sync_mode off' to dismiss forever)\"\n  fi\nfi\n\nif [ -d \"$_GSTACK_HOME\u002F.git\" ] && [ \"$_BRAIN_SYNC_MODE\" != \"off\" ]; then\n  _BRAIN_LAST_PULL_FILE=\"$_GSTACK_HOME\u002F.brain-last-pull\"\n  _BRAIN_NOW=$(date +%s)\n  _BRAIN_DO_PULL=1\n  if [ -f \"$_BRAIN_LAST_PULL_FILE\" ]; then\n    _BRAIN_LAST=$(cat \"$_BRAIN_LAST_PULL_FILE\" 2>\u002Fdev\u002Fnull || echo 0)\n    _BRAIN_AGE=$(( _BRAIN_NOW - _BRAIN_LAST ))\n    [ \"$_BRAIN_AGE\" -lt 86400 ] && _BRAIN_DO_PULL=0\n  fi\n  if [ \"$_BRAIN_DO_PULL\" = \"1\" ]; then\n    ( cd \"$_GSTACK_HOME\" && git fetch origin >\u002Fdev\u002Fnull 2>&1 && git merge --ff-only \"origin\u002F$(git rev-parse --abbrev-ref HEAD)\" >\u002Fdev\u002Fnull 2>&1 ) || true\n    echo \"$_BRAIN_NOW\" > \"$_BRAIN_LAST_PULL_FILE\"\n  fi\n  \"$_BRAIN_SYNC_BIN\" --once 2>\u002Fdev\u002Fnull || true\nfi\n\nif [ \"$_GBRAIN_MCP_MODE\" = \"remote-http\" ]; then\n  # Remote-MCP mode: local artifacts sync is a no-op (brain admin's server\n  # pulls from GitHub\u002FGitLab). Show the user this is by design, not broken.\n  _GBRAIN_HOST=$(jq -r '.mcpServers.gbrain.url \u002F\u002F empty' \"$HOME\u002F.claude.json\" 2>\u002Fdev\u002Fnull | sed -E 's|^https?:\u002F\u002F([^\u002F:]+).*|\\1|')\n  echo \"ARTIFACTS_SYNC: remote-mode (managed by brain server ${_GBRAIN_HOST:-remote})\"\nelif [ -d \"$_GSTACK_HOME\u002F.git\" ] && [ \"$_BRAIN_SYNC_MODE\" != \"off\" ]; then\n  _BRAIN_QUEUE_DEPTH=0\n  [ -f \"$_GSTACK_HOME\u002F.brain-queue.jsonl\" ] && _BRAIN_QUEUE_DEPTH=$(wc -l \u003C \"$_GSTACK_HOME\u002F.brain-queue.jsonl\" | tr -d ' ')\n  _BRAIN_LAST_PUSH=\"never\"\n  [ -f \"$_GSTACK_HOME\u002F.brain-last-push\" ] && _BRAIN_LAST_PUSH=$(cat \"$_GSTACK_HOME\u002F.brain-last-push\" 2>\u002Fdev\u002Fnull || echo never)\n  echo \"ARTIFACTS_SYNC: mode=$_BRAIN_SYNC_MODE | last_push=$_BRAIN_LAST_PUSH | queue=$_BRAIN_QUEUE_DEPTH\"\nelse\n  echo \"ARTIFACTS_SYNC: off\"\nfi\n```\n\n\n\nPrivacy stop-gate: if output shows `ARTIFACTS_SYNC: off`, `artifacts_sync_mode_prompted` is `false`, and gbrain is on PATH or `gbrain doctor --fast --json` works, ask once:\n\n> gstack can publish your artifacts (CEO plans, designs, reports) to a private GitHub repo that GBrain indexes across machines. How much should sync?\n\nOptions:\n- A) Everything allowlisted (recommended)\n- B) Only artifacts\n- C) Decline, keep everything local\n\nAfter answer:\n\n```bash\n# Chosen mode: full | artifacts-only | off\n\"$_BRAIN_CONFIG_BIN\" set artifacts_sync_mode \u003Cchoice>\n\"$_BRAIN_CONFIG_BIN\" set artifacts_sync_mode_prompted true\n```\n\nIf A\u002FB and `~\u002F.gstack\u002F.git` is missing, ask whether to run `gstack-artifacts-init`. Do not block the skill.\n\nAt skill END before telemetry:\n\n```bash\n\"~\u002F.claude\u002Fskills\u002Fgstack\u002Fbin\u002Fgstack-brain-sync\" --discover-new 2>\u002Fdev\u002Fnull || true\n\"~\u002F.claude\u002Fskills\u002Fgstack\u002Fbin\u002Fgstack-brain-sync\" --once 2>\u002Fdev\u002Fnull || true\n```\n\n\n## Model-Specific Behavioral Patch (claude)\n\nThe following nudges are tuned for the claude model family. They are\n**subordinate** to skill workflow, STOP points, AskUserQuestion gates, plan-mode\nsafety, and \u002Fship review gates. If a nudge below conflicts with skill instructions,\nthe skill wins. Treat these as preferences, not rules.\n\n**Todo-list discipline.** When working through a multi-step plan, mark each task\ncomplete individually as you finish it. Do not batch-complete at the end. If a task\nturns out to be unnecessary, mark it skipped with a one-line reason.\n\n**Think before heavy actions.** For complex operations (refactors, migrations,\nnon-trivial new features), briefly state your approach before executing. This lets\nthe user course-correct cheaply instead of mid-flight.\n\n**Dedicated tools over Bash.** Prefer Read, Edit, Write, Glob, Grep over shell\nequivalents (cat, sed, find, grep). The dedicated tools are cheaper and clearer.\n\n## Voice\n\nDirect, concrete, builder-to-builder. Name the file, function, command, and user-visible impact. No filler.\n\nNo em dashes. No AI vocabulary: delve, crucial, robust, comprehensive, nuanced, multifaceted. Never corporate or academic. Short paragraphs. End with what to do.\n\nThe user has context you do not. Cross-model agreement is a recommendation, not a decision. The user decides.\n\n## Completion Status Protocol\n\nWhen completing a skill workflow, report status using one of:\n- **DONE** — completed with evidence.\n- **DONE_WITH_CONCERNS** — completed, but list concerns.\n- **BLOCKED** — cannot proceed; state blocker and what was tried.\n- **NEEDS_CONTEXT** — missing info; state exactly what is needed.\n\nEscalate after 3 failed attempts, uncertain security-sensitive changes, or scope you cannot verify. Format: `STATUS`, `REASON`, `ATTEMPTED`, `RECOMMENDATION`.\n\n## Operational Self-Improvement\n\nBefore completing, if you discovered a durable project quirk or command fix that would save 5+ minutes next time, log it:\n\n```bash\n~\u002F.claude\u002Fskills\u002Fgstack\u002Fbin\u002Fgstack-learnings-log '{\"skill\":\"SKILL_NAME\",\"type\":\"operational\",\"key\":\"SHORT_KEY\",\"insight\":\"DESCRIPTION\",\"confidence\":N,\"source\":\"observed\"}'\n```\n\nDo not log obvious facts or one-time transient errors.\n\n## Telemetry (run last)\n\nAfter workflow completion, log telemetry. Use skill `name:` from frontmatter. OUTCOME is success\u002Ferror\u002Fabort\u002Funknown.\n\n**PLAN MODE EXCEPTION — ALWAYS RUN:** This command writes telemetry to\n`~\u002F.gstack\u002Fanalytics\u002F`, matching preamble analytics writes.\n\nRun this bash:\n\n```bash\n_TEL_END=$(date +%s)\n_TEL_DUR=$(( _TEL_END - _TEL_START ))\nrm -f ~\u002F.gstack\u002Fanalytics\u002F.pending-\"$_SESSION_ID\" 2>\u002Fdev\u002Fnull || true\n# Session timeline: record skill completion (local-only, never sent anywhere)\n~\u002F.claude\u002Fskills\u002Fgstack\u002Fbin\u002Fgstack-timeline-log '{\"skill\":\"SKILL_NAME\",\"event\":\"completed\",\"branch\":\"'$(git branch --show-current 2>\u002Fdev\u002Fnull || echo unknown)'\",\"outcome\":\"OUTCOME\",\"duration_s\":\"'\"$_TEL_DUR\"'\",\"session\":\"'\"$_SESSION_ID\"'\"}' 2>\u002Fdev\u002Fnull || true\n# Local analytics (gated on telemetry setting)\nif [ \"$_TEL\" != \"off\" ]; then\necho '{\"skill\":\"SKILL_NAME\",\"duration_s\":\"'\"$_TEL_DUR\"'\",\"outcome\":\"OUTCOME\",\"browse\":\"USED_BROWSE\",\"session\":\"'\"$_SESSION_ID\"'\",\"ts\":\"'$(date -u +%Y-%m-%dT%H:%M:%SZ)'\"}' >> ~\u002F.gstack\u002Fanalytics\u002Fskill-usage.jsonl 2>\u002Fdev\u002Fnull || true\nfi\n# Remote telemetry (opt-in, requires binary)\nif [ \"$_TEL\" != \"off\" ] && [ -x ~\u002F.claude\u002Fskills\u002Fgstack\u002Fbin\u002Fgstack-telemetry-log ]; then\n  ~\u002F.claude\u002Fskills\u002Fgstack\u002Fbin\u002Fgstack-telemetry-log \\\n    --skill \"SKILL_NAME\" --duration \"$_TEL_DUR\" --outcome \"OUTCOME\" \\\n    --used-browse \"USED_BROWSE\" --session-id \"$_SESSION_ID\" 2>\u002Fdev\u002Fnull &\nfi\n```\n\nReplace `SKILL_NAME`, `OUTCOME`, and `USED_BROWSE` before running.\n\n## Plan Status Footer\n\nSkills that run plan reviews (`\u002Fplan-*-review`, `\u002Fcodex review`) include the EXIT PLAN MODE GATE blocking checklist at the end of the skill, which verifies the plan file ends with `## GSTACK REVIEW REPORT` before ExitPlanMode is called. Skills that don't run plan reviews (operational skills like `\u002Fship`, `\u002Fqa`, `\u002Freview`) typically don't operate in plan mode and have no review report to verify; this footer is a no-op for them. Writing the plan file is the one edit allowed in plan mode.\n\n# \u002Fbenchmark-models — Cross-Model Skill Benchmark\n\nYou are running the `\u002Fbenchmark-models` workflow. Wraps the `gstack-model-benchmark` binary with an interactive flow that picks a prompt, confirms providers, previews auth, and runs the benchmark.\n\nDifferent from `\u002Fbenchmark` — that skill measures web page performance (Core Web Vitals, load times). This skill measures AI model performance on gstack skills or arbitrary prompts.\n\n---\n\n## Step 0: Locate the binary\n\n```bash\nBIN=\"$HOME\u002F.claude\u002Fskills\u002Fgstack\u002Fbin\u002Fgstack-model-benchmark\"\n[ -x \"$BIN\" ] || BIN=\".claude\u002Fskills\u002Fgstack\u002Fbin\u002Fgstack-model-benchmark\"\n[ -x \"$BIN\" ] || { echo \"ERROR: gstack-model-benchmark not found. Run .\u002Fsetup in the gstack install dir.\" >&2; exit 1; }\necho \"BIN: $BIN\"\n```\n\nIf not found, stop and tell the user to reinstall gstack.\n\n---\n\n## Step 1: Choose a prompt\n\nUse AskUserQuestion with the preamble format:\n- **Re-ground:** current project + branch.\n- **Simplify:** \"A cross-model benchmark runs the same prompt through 2-3 AI models and shows you how they compare on speed, cost, and output quality. What prompt should we use?\"\n- **RECOMMENDATION:** A because benchmarking against a real skill exposes tool-use differences, not just raw generation.\n- **Options:**\n  - A) Benchmark one of my gstack skills (we'll pick which skill next). Completeness: 10\u002F10.\n  - B) Use an inline prompt — type it on the next turn. Completeness: 8\u002F10.\n  - C) Point at a prompt file on disk — specify path on the next turn. Completeness: 8\u002F10.\n\nIf A: list top-level gstack skills that have SKILL.md files (from `find . -maxdepth 2 -name SKILL.md -not -path '.\u002F.*'`), ask the user to pick one via a second AskUserQuestion. Use the picked SKILL.md path as the prompt file.\n\nIf B: ask the user for the inline prompt. Use it verbatim via `--prompt \"\u003Ctext>\"`.\n\nIf C: ask for the path. Verify it exists. Use as positional argument.\n\n---\n\n## Step 2: Choose providers\n\n```bash\n\"$BIN\" --prompt \"unused, dry-run\" --models claude,gpt,gemini --dry-run\n```\n\nShow the dry-run output. The \"Adapter availability\" section tells the user which providers will actually run (OK) vs skip (NOT READY — remediation hint included).\n\nIf ALL three show NOT READY: stop with a clear message — benchmark can't run without at least one authed provider. Suggest `claude login`, `codex login`, or `gemini login` \u002F `export GOOGLE_API_KEY`.\n\nIf at least one is OK: AskUserQuestion:\n- **Simplify:** \"Which models should we include? The dry-run above showed which are authed. Unauthed ones will be skipped cleanly — they won't abort the batch.\"\n- **RECOMMENDATION:** A (all authed providers) because running as many as possible gives the richest comparison.\n- **Options:**\n  - A) All authed providers. Completeness: 10\u002F10.\n  - B) Only Claude. Completeness: 6\u002F10 (no cross-model signal — use \u002Fship's review for solo claude benchmarks instead).\n  - C) Pick two — specify on next turn. Completeness: 8\u002F10.\n\n---\n\n## Step 3: Decide on judge\n\n```bash\n[ -n \"$ANTHROPIC_API_KEY\" ] || grep -q 'ANTHROPIC' \"$HOME\u002F.claude\u002F.credentials.json\" 2>\u002Fdev\u002Fnull && echo \"JUDGE_AVAILABLE\" || echo \"JUDGE_UNAVAILABLE\"\n```\n\nIf judge is available, AskUserQuestion:\n- **Simplify:** \"The quality judge scores each model's output on a 0-10 scale using Anthropic's Claude as a tiebreaker. Adds ~$0.05\u002Frun. Recommended if you care about output quality, not just latency and cost.\"\n- **RECOMMENDATION:** A — the whole point is comparing quality, not just speed.\n- **Options:**\n  - A) Enable judge (adds ~$0.05). Completeness: 10\u002F10.\n  - B) Skip judge — speed\u002Fcost\u002Ftokens only. Completeness: 7\u002F10.\n\nIf judge is NOT available, skip this question and omit the `--judge` flag.\n\n---\n\n## Step 4: Run the benchmark\n\nConstruct the command from Step 1, 2, 3 decisions:\n\n```bash\n\"$BIN\" \u003Cprompt-spec> --models \u003Cpicked-models> [--judge] --output table\n```\n\nWhere `\u003Cprompt-spec>` is either `--prompt \"\u003Ctext>\"` (Step 1B), a file path (Step 1A or 1C), and `\u003Cpicked-models>` is the comma-separated list from Step 2.\n\nStream the output as it arrives. This is slow — each provider runs the prompt fully. Expect 30s-5min depending on prompt complexity and whether `--judge` is on.\n\n---\n\n## Step 5: Interpret results\n\nAfter the table prints, summarize for the user:\n- **Fastest** — provider with lowest latency.\n- **Cheapest** — provider with lowest cost.\n- **Highest quality** (if `--judge` ran) — provider with highest score.\n- **Best overall** — use judgment. If judge ran: quality-weighted. Otherwise: note the tradeoff the user needs to make.\n\nIf any provider hit an error (auth\u002Ftimeout\u002Frate_limit), call it out with the remediation path.\n\n---\n\n## Step 6: Offer to save results\n\nAskUserQuestion:\n- **Simplify:** \"Save this benchmark as JSON so you can compare future runs against it?\"\n- **RECOMMENDATION:** A — skill performance drifts as providers update their models; a saved baseline catches quality regressions.\n- **Options:**\n  - A) Save to `~\u002F.gstack\u002Fbenchmarks\u002F\u003Cdate>-\u003Cskill-or-prompt-slug>.json`. Completeness: 10\u002F10.\n  - B) Just print, don't save. Completeness: 5\u002F10 (loses trend data).\n\nIf A: re-run with `--output json` and tee to the dated file. Print the path so the user can diff future runs against it.\n\n---\n\n## Important Rules\n\n- **Never run a real benchmark without Step 2's dry-run first.** Users need to see auth status before spending API calls.\n- **Never hardcode model names.** Always pass providers from user's Step 2 choice — the binary handles the rest.\n- **Never auto-include `--judge`.** It adds real cost; user must opt in.\n- **If zero providers are authed, STOP.** Don't attempt the benchmark — it produces no useful output.\n- **Cost is visible.** Every run shows per-provider cost in the table. Users should see it before the next run.\n","\u003C!-- AUTO-GENERATED from SKILL.md.tmpl — do not edit directly -->\n\u003C!-- Regenerate: bun run gen:skill-docs -->\n\n\n## When to invoke this skill\n\nRuns the same prompt through Claude,\nGPT (via Codex CLI), and Gemini side-by-side — compares latency, tokens, cost,\nand optionally quality via LLM judge. Answers \"which model is actually best\nfor this skill?\" with data instead of vibes. Separate from \u002Fbenchmark, which\nmeasures web page performance. Use when: \"benchmark models\", \"compare models\",\n\"which model is best for X\", \"cross-model comparison\", \"model shootout\".\n\nVoice triggers (speech-to-text aliases): \"compare models\", \"model shootout\", \"which model is best\".\n\n## Preamble (run first)\n\n```bash\n_UPD=$(~\u002F.claude\u002Fskills\u002Fgstack\u002Fbin\u002Fgstack-update-check 2>\u002Fdev\u002Fnull || .claude\u002Fskills\u002Fgstack\u002Fbin\u002Fgstack-update-check 2>\u002Fdev\u002Fnull || true)\n[ -n \"$_UPD\" ] && echo \"$_UPD\" || true\nmkdir -p ~\u002F.gstack\u002Fsessions\ntouch ~\u002F.gstack\u002Fsessions\u002F\"$PPID\"\n_SESSIONS=$(find ~\u002F.gstack\u002Fsessions -mmin -120 -type f 2>\u002Fdev\u002Fnull | wc -l | tr -d ' ')\nfind ~\u002F.gstack\u002Fsessions -mmin +120 -type f -exec rm {} + 2>\u002Fdev\u002Fnull || true\n_PROACTIVE=$(~\u002F.claude\u002Fskills\u002Fgstack\u002Fbin\u002Fgstack-config get proactive 2>\u002Fdev\u002Fnull || echo \"true\")\n_PROACTIVE_PROMPTED=$([ -f ~\u002F.gstack\u002F.proactive-prompted ] && echo \"yes\" || echo \"no\")\n_BRANCH=$(git branch --show-current 2>\u002Fdev\u002Fnull || echo \"unknown\")\necho \"BRANCH: $_BRANCH\"\n_SKILL_PREFIX=$(~\u002F.claude\u002Fskills\u002Fgstack\u002Fbin\u002Fgstack-config get skill_prefix 2>\u002Fdev\u002Fnull || echo \"false\")\necho \"PROACTIVE: $_PROACTIVE\"\necho \"PROACTIVE_PROMPTED: $_PROACTIVE_PROMPTED\"\necho \"SKILL_PREFIX: $_SKILL_PREFIX\"\nsource \u003C(~\u002F.claude\u002Fskills\u002Fgstack\u002Fbin\u002Fgstack-repo-mode 2>\u002Fdev\u002Fnull) || true\nREPO_MODE=${REPO_MODE:-unknown}\necho \"REPO_MODE: $REPO_MODE\"\n_SESSION_KIND=$(~\u002F.claude\u002Fskills\u002Fgstack\u002Fbin\u002Fgstack-session-kind 2>\u002Fdev\u002Fnull || echo \"interactive\")\ncase \"$_SESSION_KIND\" in spawned|headless|interactive) ;; *) _SESSION_KIND=\"interactive\" ;; esac\necho \"SESSION_KIND: $_SESSION_KIND\"\n_LAKE_SEEN=$([ -f ~\u002F.gstack\u002F.completeness-intro-seen ] && echo \"yes\" || echo \"no\")\necho \"LAKE_INTRO: $_LAKE_SEEN\"\n_TEL=$(~\u002F.claude\u002Fskills\u002Fgstack\u002Fbin\u002Fgstack-config get telemetry 2>\u002Fdev\u002Fnull || true)\n_TEL_PROMPTED=$([ -f ~\u002F.gstack\u002F.telemetry-prompted ] && echo \"yes\" || echo \"no\")\n_TEL_START=$(date +%s)\n_SESSION_ID=\"$$-$(date +%s)\"\necho \"TELEMETRY: ${_TEL:-off}\"\necho \"TEL_PROMPTED: $_TEL_PROMPTED\"\n_EXPLAIN_LEVEL=$(~\u002F.claude\u002Fskills\u002Fgstack\u002Fbin\u002Fgstack-config get explain_level 2>\u002Fdev\u002Fnull || echo \"default\")\nif [ \"$_EXPLAIN_LEVEL\" != \"default\" ] && [ \"$_EXPLAIN_LEVEL\" != \"terse\" ]; then _EXPLAIN_LEVEL=\"default\"; fi\necho \"EXPLAIN_LEVEL: $_EXPLAIN_LEVEL\"\n_QUESTION_TUNING=$(~\u002F.claude\u002Fskills\u002Fgstack\u002Fbin\u002Fgstack-config get question_tuning 2>\u002Fdev\u002Fnull || echo \"false\")\necho \"QUESTION_TUNING: $_QUESTION_TUNING\"\nmkdir -p ~\u002F.gstack\u002Fanalytics\nif [ \"$_TEL\" != \"off\" ]; then\necho '{\"skill\":\"benchmark-models\",\"ts\":\"'$(date -u +%Y-%m-%dT%H:%M:%SZ)'\",\"repo\":\"'$(_repo=$(basename \"$(git rev-parse --show-toplevel 2>\u002Fdev\u002Fnull)\" 2>\u002Fdev\u002Fnull | tr -cd 'a-zA-Z0-9._-'); echo \"${_repo:-unknown}\")'\"}'  >> ~\u002F.gstack\u002Fanalytics\u002Fskill-usage.jsonl 2>\u002Fdev\u002Fnull || true\nfi\nfor _PF in $(find ~\u002F.gstack\u002Fanalytics -maxdepth 1 -name '.pending-*' 2>\u002Fdev\u002Fnull); do\n  if [ -f \"$_PF\" ]; then\n    if [ \"$_TEL\" != \"off\" ] && [ -x \"~\u002F.claude\u002Fskills\u002Fgstack\u002Fbin\u002Fgstack-telemetry-log\" ]; then\n      ~\u002F.claude\u002Fskills\u002Fgstack\u002Fbin\u002Fgstack-telemetry-log --event-type skill_run --skill _pending_finalize --outcome unknown --session-id \"$_SESSION_ID\" 2>\u002Fdev\u002Fnull || true\n    fi\n    rm -f \"$_PF\" 2>\u002Fdev\u002Fnull || true\n  fi\n  break\ndone\neval \"$(~\u002F.claude\u002Fskills\u002Fgstack\u002Fbin\u002Fgstack-slug 2>\u002Fdev\u002Fnull)\" 2>\u002Fdev\u002Fnull || true\n_LEARN_FILE=\"${GSTACK_HOME:-$HOME\u002F.gstack}\u002Fprojects\u002F${SLUG:-unknown}\u002Flearnings.jsonl\"\nif [ -f \"$_LEARN_FILE\" ]; then\n  _LEARN_COUNT=$(wc -l \u003C \"$_LEARN_FILE\" 2>\u002Fdev\u002Fnull | tr -d ' ')\n  echo \"LEARNINGS: $_LEARN_COUNT entries loaded\"\n  if [ \"$_LEARN_COUNT\" -gt 5 ] 2>\u002Fdev\u002Fnull; then\n    ~\u002F.claude\u002Fskills\u002Fgstack\u002Fbin\u002Fgstack-learnings-search --limit 3 2>\u002Fdev\u002Fnull || true\n  fi\nelse\n  echo \"LEARNINGS: 0\"\nfi\n~\u002F.claude\u002Fskills\u002Fgstack\u002Fbin\u002Fgstack-timeline-log '{\"skill\":\"benchmark-models\",\"event\":\"started\",\"branch\":\"'\"$_BRANCH\"'\",\"session\":\"'\"$_SESSION_ID\"'\"}' 2>\u002Fdev\u002Fnull &\n_HAS_ROUTING=\"no\"\nif [ -f CLAUDE.md ] && grep -q \"## Skill routing\" CLAUDE.md 2>\u002Fdev\u002Fnull; then\n  _HAS_ROUTING=\"yes\"\nfi\n_ROUTING_DECLINED=$(~\u002F.claude\u002Fskills\u002Fgstack\u002Fbin\u002Fgstack-config get routing_declined 2>\u002Fdev\u002Fnull || echo \"false\")\necho \"HAS_ROUTING: $_HAS_ROUTING\"\necho \"ROUTING_DECLINED: $_ROUTING_DECLINED\"\n_VENDORED=\"no\"\nif [ -d \".claude\u002Fskills\u002Fgstack\" ] && [ ! -L \".claude\u002Fskills\u002Fgstack\" ]; then\n  if [ -f \".claude\u002Fskills\u002Fgstack\u002FVERSION\" ] || [ -d \".claude\u002Fskills\u002Fgstack\u002F.git\" ]; then\n    _VENDORED=\"yes\"\n  fi\nfi\necho \"VENDORED_GSTACK: $_VENDORED\"\necho \"MODEL_OVERLAY: claude\"\n_CHECKPOINT_MODE=$(~\u002F.claude\u002Fskills\u002Fgstack\u002Fbin\u002Fgstack-config get checkpoint_mode 2>\u002Fdev\u002Fnull || echo \"explicit\")\n_CHECKPOINT_PUSH=$(~\u002F.claude\u002Fskills\u002Fgstack\u002Fbin\u002Fgstack-config get checkpoint_push 2>\u002Fdev\u002Fnull || echo \"false\")\necho \"CHECKPOINT_MODE: $_CHECKPOINT_MODE\"\necho \"CHECKPOINT_PUSH: $_CHECKPOINT_PUSH\"\n# Plan-mode hint for skills like \u002Fspec that branch behavior on plan-mode state.\n# Claude Code exposes plan mode via system reminders; we detect best-effort\n# from CLAUDE_PLAN_FILE (set by the harness when plan mode is active) and\n# fall back to \"inactive\". Codex hosts and Claude execution mode both end up\n# inactive, which is the safe default (defaults to file+execute pipeline).\nif [ -n \"${CLAUDE_PLAN_FILE:-}${GSTACK_PLAN_MODE_FORCE:-}\" ]; then\n  export GSTACK_PLAN_MODE=\"active\"\nelif [ \"${GSTACK_PLAN_MODE:-}\" = \"active\" ]; then\n  export GSTACK_PLAN_MODE=\"active\"\nelse\n  export GSTACK_PLAN_MODE=\"inactive\"\nfi\necho \"GSTACK_PLAN_MODE: $GSTACK_PLAN_MODE\"\n[ -n \"$OPENCLAW_SESSION\" ] && echo \"SPAWNED_SESSION: true\" || true\n```\n\n## Plan Mode Safe Operations\n\nIn plan mode, allowed because they inform the plan: `$B`, `$D`, `codex exec`\u002F`codex review`, writes to `~\u002F.gstack\u002F`, writes to the plan file, and `open` for generated artifacts.\n\n## Skill Invocation During Plan Mode\n\nIf the user invokes a skill in plan mode, the skill takes precedence over generic plan mode behavior. **Treat the skill file as executable instructions, not reference.** Follow it step by step starting from Step 0; the first AskUserQuestion is the workflow entering plan mode, not a violation of it. AskUserQuestion (any variant — `mcp__*__AskUserQuestion` or native; see \"AskUserQuestion Format → Tool resolution\") satisfies plan mode's end-of-turn requirement. If AskUserQuestion is unavailable or a call fails, follow the AskUserQuestion Format failure fallback: `headless` → BLOCKED; `interactive` → the prose fallback (also satisfies end-of-turn). At a STOP point, stop immediately. Do not continue the workflow or call ExitPlanMode there. Commands marked \"PLAN MODE EXCEPTION — ALWAYS RUN\" execute. Call ExitPlanMode only after the skill workflow completes, or if the user tells you to cancel the skill or leave plan mode.\n\nIf `PROACTIVE` is `\"false\"`, do not auto-invoke or proactively suggest skills. If a skill seems useful, ask: \"I think \u002Fskillname might help here — want me to run it?\"\n\nIf `SKILL_PREFIX` is `\"true\"`, suggest\u002Finvoke `\u002Fgstack-*` names. Disk paths stay `~\u002F.claude\u002Fskills\u002Fgstack\u002F[skill-name]\u002FSKILL.md`.\n\nIf output shows `UPGRADE_AVAILABLE \u003Cold> \u003Cnew>`: read `~\u002F.claude\u002Fskills\u002Fgstack\u002Fgstack-upgrade\u002FSKILL.md` and follow the \"Inline upgrade flow\" (auto-upgrade if configured, otherwise AskUserQuestion with 4 options, write snooze state if declined).\n\nIf output shows `JUST_UPGRADED \u003Cfrom> \u003Cto>`: print \"Running gstack v{to} (just updated!)\". If `SPAWNED_SESSION` is true, skip feature discovery.\n\nFeature discovery, max one prompt per session:\n- Missing `~\u002F.claude\u002Fskills\u002Fgstack\u002F.feature-prompted-continuous-checkpoint`: AskUserQuestion for Continuous checkpoint auto-commits. If accepted, run `~\u002F.claude\u002Fskills\u002Fgstack\u002Fbin\u002Fgstack-config set checkpoint_mode continuous`. Always touch marker.\n- Missing `~\u002F.claude\u002Fskills\u002Fgstack\u002F.feature-prompted-model-overlay`: inform \"Model overlays are active. MODEL_OVERLAY shows the patch.\" Always touch marker.\n\nAfter upgrade prompts, continue workflow.\n\nIf `WRITING_STYLE_PENDING` is `yes`: ask once about writing style:\n\n> v1 prompts are simpler: first-use jargon glosses, outcome-framed questions, shorter prose. Keep default or restore terse?\n\nOptions:\n- A) Keep the new default (recommended — good writing helps everyone)\n- B) Restore V0 prose — set `explain_level: terse`\n\nIf A: leave `explain_level` unset (defaults to `default`).\nIf B: run `~\u002F.claude\u002Fskills\u002Fgstack\u002Fbin\u002Fgstack-config set explain_level terse`.\n\nAlways run (regardless of choice):\n```bash\nrm -f ~\u002F.gstack\u002F.writing-style-prompt-pending\ntouch ~\u002F.gstack\u002F.writing-style-prompted\n```\n\nSkip if `WRITING_STYLE_PENDING` is `no`.\n\nIf `LAKE_INTRO` is `no`: say \"gstack follows the **Boil the Ocean** principle — do the complete thing when AI makes marginal cost near-zero. Read more: https:\u002F\u002Fgarryslist.org\u002Fposts\u002Fboil-the-ocean\" Offer to open:\n\n```bash\nopen https:\u002F\u002Fgarryslist.org\u002Fposts\u002Fboil-the-ocean\ntouch ~\u002F.gstack\u002F.completeness-intro-seen\n```\n\nOnly run `open` if yes. Always run `touch`.\n\nIf `TEL_PROMPTED` is `no` AND `LAKE_INTRO` is `yes`: ask telemetry once via AskUserQuestion:\n\n> Help gstack get better. Share usage data only: skill, duration, crashes, stable device ID. No code or file paths. Your repo name is recorded locally only and stripped before any upload.\n\nOptions:\n- A) Help gstack get better! (recommended)\n- B) No thanks\n\nIf A: run `~\u002F.claude\u002Fskills\u002Fgstack\u002Fbin\u002Fgstack-config set telemetry community`\n\nIf B: ask follow-up:\n\n> Anonymous mode sends only aggregate usage, no unique ID.\n\nOptions:\n- A) Sure, anonymous is fine\n- B) No thanks, fully off\n\nIf B→A: run `~\u002F.claude\u002Fskills\u002Fgstack\u002Fbin\u002Fgstack-config set telemetry anonymous`\nIf B→B: run `~\u002F.claude\u002Fskills\u002Fgstack\u002Fbin\u002Fgstack-config set telemetry off`\n\nAlways run:\n```bash\ntouch ~\u002F.gstack\u002F.telemetry-prompted\n```\n\nSkip if `TEL_PROMPTED` is `yes`.\n\nIf `PROACTIVE_PROMPTED` is `no` AND `TEL_PROMPTED` is `yes`: ask once:\n\n> Let gstack proactively suggest skills, like \u002Fqa for \"does this work?\" or \u002Finvestigate for bugs?\n\nOptions:\n- A) Keep it on (recommended)\n- B) Turn it off — I'll type \u002Fcommands myself\n\nIf A: run `~\u002F.claude\u002Fskills\u002Fgstack\u002Fbin\u002Fgstack-config set proactive true`\nIf B: run `~\u002F.claude\u002Fskills\u002Fgstack\u002Fbin\u002Fgstack-config set proactive false`\n\nAlways run:\n```bash\ntouch ~\u002F.gstack\u002F.proactive-prompted\n```\n\nSkip if `PROACTIVE_PROMPTED` is `yes`.\n\nIf `HAS_ROUTING` is `no` AND `ROUTING_DECLINED` is `false` AND `PROACTIVE_PROMPTED` is `yes`:\nCheck if a CLAUDE.md file exists in the project root. If it does not exist, create it.\n\nUse AskUserQuestion:\n\n> gstack works best when your project's CLAUDE.md includes skill routing rules.\n\nOptions:\n- A) Add routing rules to CLAUDE.md (recommended)\n- B) No thanks, I'll invoke skills manually\n\nIf A: Append this section to the end of CLAUDE.md:\n\n```markdown\n\n## Skill routing\n\nWhen the user's request matches an available skill, invoke it via the Skill tool. When in doubt, invoke the skill.\n\nKey routing rules:\n- Product ideas\u002Fbrainstorming → invoke \u002Foffice-hours\n- Strategy\u002Fscope → invoke \u002Fplan-ceo-review\n- Architecture → invoke \u002Fplan-eng-review\n- Design system\u002Fplan review → invoke \u002Fdesign-consultation or \u002Fplan-design-review\n- Full review pipeline → invoke \u002Fautoplan\n- Bugs\u002Ferrors → invoke \u002Finvestigate\n- QA\u002Ftesting site behavior → invoke \u002Fqa or \u002Fqa-only\n- Code review\u002Fdiff check → invoke \u002Freview\n- Visual polish → invoke \u002Fdesign-review\n- Ship\u002Fdeploy\u002FPR → invoke \u002Fship or \u002Fland-and-deploy\n- Save progress → invoke \u002Fcontext-save\n- Resume context → invoke \u002Fcontext-restore\n- Author a backlog-ready spec\u002Fissue → invoke \u002Fspec\n```\n\nThen commit the change: `git add CLAUDE.md && git commit -m \"chore: add gstack skill routing rules to CLAUDE.md\"`\n\nIf B: run `~\u002F.claude\u002Fskills\u002Fgstack\u002Fbin\u002Fgstack-config set routing_declined true` and say they can re-enable with `gstack-config set routing_declined false`.\n\nThis only happens once per project. Skip if `HAS_ROUTING` is `yes` or `ROUTING_DECLINED` is `true`.\n\nIf `VENDORED_GSTACK` is `yes`, warn once via AskUserQuestion unless `~\u002F.gstack\u002F.vendoring-warned-$SLUG` exists:\n\n> This project has gstack vendored in `.claude\u002Fskills\u002Fgstack\u002F`. Vendoring is deprecated.\n> Migrate to team mode?\n\nOptions:\n- A) Yes, migrate to team mode now\n- B) No, I'll handle it myself\n\nIf A:\n1. Run `git rm -r .claude\u002Fskills\u002Fgstack\u002F`\n2. Run `echo '.claude\u002Fskills\u002Fgstack\u002F' >> .gitignore`\n3. Run `~\u002F.claude\u002Fskills\u002Fgstack\u002Fbin\u002Fgstack-team-init required` (or `optional`)\n4. Run `git add .claude\u002F .gitignore CLAUDE.md && git commit -m \"chore: migrate gstack from vendored to team mode\"`\n5. Tell the user: \"Done. Each developer now runs: `cd ~\u002F.claude\u002Fskills\u002Fgstack && .\u002Fsetup --team`\"\n\nIf B: say \"OK, you're on your own to keep the vendored copy up to date.\"\n\nAlways run (regardless of choice):\n```bash\neval \"$(~\u002F.claude\u002Fskills\u002Fgstack\u002Fbin\u002Fgstack-slug 2>\u002Fdev\u002Fnull)\" 2>\u002Fdev\u002Fnull || true\ntouch ~\u002F.gstack\u002F.vendoring-warned-${SLUG:-unknown}\n```\n\nIf marker exists, skip.\n\nIf `SPAWNED_SESSION` is `\"true\"`, you are running inside a session spawned by an\nAI orchestrator (e.g., OpenClaw). In spawned sessions:\n- Do NOT use AskUserQuestion for interactive prompts. Auto-choose the recommended option.\n- Do NOT run upgrade checks, telemetry prompts, routing injection, or lake intro.\n- Focus on completing the task and reporting results via prose output.\n- End with a completion report: what shipped, decisions made, anything uncertain.\n\n## Artifacts Sync (skill start)\n\n```bash\n_GSTACK_HOME=\"${GSTACK_HOME:-$HOME\u002F.gstack}\"\n# Prefer the v1.27.0.0 artifacts file; fall back to brain file for users\n# upgrading mid-stream before the migration script runs.\nif [ -f \"$HOME\u002F.gstack-artifacts-remote.txt\" ]; then\n  _BRAIN_REMOTE_FILE=\"$HOME\u002F.gstack-artifacts-remote.txt\"\nelse\n  _BRAIN_REMOTE_FILE=\"$HOME\u002F.gstack-brain-remote.txt\"\nfi\n_BRAIN_SYNC_BIN=\"~\u002F.claude\u002Fskills\u002Fgstack\u002Fbin\u002Fgstack-brain-sync\"\n_BRAIN_CONFIG_BIN=\"~\u002F.claude\u002Fskills\u002Fgstack\u002Fbin\u002Fgstack-config\"\n\n# \u002Fsync-gbrain context-load: teach the agent to use gbrain when it's available.\n# Per-worktree pin: post-spike redesign uses kubectl-style `.gbrain-source` in the\n# git toplevel to scope queries. Look for the pin in the worktree (not a global\n# state file) so that opening worktree B without a pin doesn't claim \"indexed\"\n# just because worktree A was synced. Empty string when gbrain is not\n# configured (zero context cost for non-gbrain users).\n_GBRAIN_CONFIG=\"$HOME\u002F.gbrain\u002Fconfig.json\"\nif [ -f \"$_GBRAIN_CONFIG\" ] && command -v gbrain >\u002Fdev\u002Fnull 2>&1; then\n  _GBRAIN_VERSION_OK=$(gbrain --version 2>\u002Fdev\u002Fnull | grep -c '^gbrain ' || echo 0)\n  if [ \"$_GBRAIN_VERSION_OK\" -gt 0 ] 2>\u002Fdev\u002Fnull; then\n    _GBRAIN_PIN_PATH=\"\"\n    _REPO_TOP=$(git rev-parse --show-toplevel 2>\u002Fdev\u002Fnull || echo \"\")\n    if [ -n \"$_REPO_TOP\" ] && [ -f \"$_REPO_TOP\u002F.gbrain-source\" ]; then\n      _GBRAIN_PIN_PATH=\"$_REPO_TOP\u002F.gbrain-source\"\n    fi\n    if [ -n \"$_GBRAIN_PIN_PATH\" ]; then\n      echo \"GBrain configured. Prefer \\`gbrain search\\`\u002F\\`gbrain query\\` over Grep for\"\n      echo \"semantic questions; use \\`gbrain code-def\\`\u002F\\`code-refs\\`\u002F\\`code-callers\\` for\"\n      echo \"symbol-aware code lookup. See \\\"## GBrain Search Guidance\\\" in CLAUDE.md.\"\n      echo \"Run \u002Fsync-gbrain to refresh.\"\n    else\n      echo \"GBrain configured but this worktree isn't pinned yet. Run \\`\u002Fsync-gbrain --full\\`\"\n      echo \"before relying on \\`gbrain search\\` for code questions in this worktree.\"\n      echo \"Falls back to Grep until pinned.\"\n    fi\n  fi\nfi\n\n_BRAIN_SYNC_MODE=$(\"$_BRAIN_CONFIG_BIN\" get artifacts_sync_mode 2>\u002Fdev\u002Fnull || echo off)\n\n# Detect remote-MCP mode (Path 4 of \u002Fsetup-gbrain). Local artifacts sync is\n# a no-op in remote mode; the brain server pulls from GitHub\u002FGitLab on its\n# own cadence. Read claude.json directly to keep this preamble fast (no\n# subprocess to claude CLI on every skill start).\n_GBRAIN_MCP_MODE=\"none\"\nif command -v jq >\u002Fdev\u002Fnull 2>&1 && [ -f \"$HOME\u002F.claude.json\" ]; then\n  _GBRAIN_MCP_TYPE=$(jq -r '.mcpServers.gbrain.type \u002F\u002F .mcpServers.gbrain.transport \u002F\u002F empty' \"$HOME\u002F.claude.json\" 2>\u002Fdev\u002Fnull)\n  case \"$_GBRAIN_MCP_TYPE\" in\n    url|http|sse) _GBRAIN_MCP_MODE=\"remote-http\" ;;\n    stdio) _GBRAIN_MCP_MODE=\"local-stdio\" ;;\n  esac\nfi\n\nif [ -f \"$_BRAIN_REMOTE_FILE\" ] && [ ! -d \"$_GSTACK_HOME\u002F.git\" ] && [ \"$_BRAIN_SYNC_MODE\" = \"off\" ]; then\n  _BRAIN_NEW_URL=$(head -1 \"$_BRAIN_REMOTE_FILE\" 2>\u002Fdev\u002Fnull | tr -d '[:space:]')\n  if [ -n \"$_BRAIN_NEW_URL\" ]; then\n    echo \"ARTIFACTS_SYNC: artifacts repo detected: $_BRAIN_NEW_URL\"\n    echo \"ARTIFACTS_SYNC: run 'gstack-brain-restore' to pull your cross-machine artifacts (or 'gstack-config set artifacts_sync_mode off' to dismiss forever)\"\n  fi\nfi\n\nif [ -d \"$_GSTACK_HOME\u002F.git\" ] && [ \"$_BRAIN_SYNC_MODE\" != \"off\" ]; then\n  _BRAIN_LAST_PULL_FILE=\"$_GSTACK_HOME\u002F.brain-last-pull\"\n  _BRAIN_NOW=$(date +%s)\n  _BRAIN_DO_PULL=1\n  if [ -f \"$_BRAIN_LAST_PULL_FILE\" ]; then\n    _BRAIN_LAST=$(cat \"$_BRAIN_LAST_PULL_FILE\" 2>\u002Fdev\u002Fnull || echo 0)\n    _BRAIN_AGE=$(( _BRAIN_NOW - _BRAIN_LAST ))\n    [ \"$_BRAIN_AGE\" -lt 86400 ] && _BRAIN_DO_PULL=0\n  fi\n  if [ \"$_BRAIN_DO_PULL\" = \"1\" ]; then\n    ( cd \"$_GSTACK_HOME\" && git fetch origin >\u002Fdev\u002Fnull 2>&1 && git merge --ff-only \"origin\u002F$(git rev-parse --abbrev-ref HEAD)\" >\u002Fdev\u002Fnull 2>&1 ) || true\n    echo \"$_BRAIN_NOW\" > \"$_BRAIN_LAST_PULL_FILE\"\n  fi\n  \"$_BRAIN_SYNC_BIN\" --once 2>\u002Fdev\u002Fnull || true\nfi\n\nif [ \"$_GBRAIN_MCP_MODE\" = \"remote-http\" ]; then\n  # Remote-MCP mode: local artifacts sync is a no-op (brain admin's server\n  # pulls from GitHub\u002FGitLab). Show the user this is by design, not broken.\n  _GBRAIN_HOST=$(jq -r '.mcpServers.gbrain.url \u002F\u002F empty' \"$HOME\u002F.claude.json\" 2>\u002Fdev\u002Fnull | sed -E 's|^https?:\u002F\u002F([^\u002F:]+).*|\\1|')\n  echo \"ARTIFACTS_SYNC: remote-mode (managed by brain server ${_GBRAIN_HOST:-remote})\"\nelif [ -d \"$_GSTACK_HOME\u002F.git\" ] && [ \"$_BRAIN_SYNC_MODE\" != \"off\" ]; then\n  _BRAIN_QUEUE_DEPTH=0\n  [ -f \"$_GSTACK_HOME\u002F.brain-queue.jsonl\" ] && _BRAIN_QUEUE_DEPTH=$(wc -l \u003C \"$_GSTACK_HOME\u002F.brain-queue.jsonl\" | tr -d ' ')\n  _BRAIN_LAST_PUSH=\"never\"\n  [ -f \"$_GSTACK_HOME\u002F.brain-last-push\" ] && _BRAIN_LAST_PUSH=$(cat \"$_GSTACK_HOME\u002F.brain-last-push\" 2>\u002Fdev\u002Fnull || echo never)\n  echo \"ARTIFACTS_SYNC: mode=$_BRAIN_SYNC_MODE | last_push=$_BRAIN_LAST_PUSH | queue=$_BRAIN_QUEUE_DEPTH\"\nelse\n  echo \"ARTIFACTS_SYNC: off\"\nfi\n```\n\n\n\nPrivacy stop-gate: if output shows `ARTIFACTS_SYNC: off`, `artifacts_sync_mode_prompted` is `false`, and gbrain is on PATH or `gbrain doctor --fast --json` works, ask once:\n\n> gstack can publish your artifacts (CEO plans, designs, reports) to a private GitHub repo that GBrain indexes across machines. How much should sync?\n\nOptions:\n- A) Everything allowlisted (recommended)\n- B) Only artifacts\n- C) Decline, keep everything local\n\nAfter answer:\n\n```bash\n# Chosen mode: full | artifacts-only | off\n\"$_BRAIN_CONFIG_BIN\" set artifacts_sync_mode \u003Cchoice>\n\"$_BRAIN_CONFIG_BIN\" set artifacts_sync_mode_prompted true\n```\n\nIf A\u002FB and `~\u002F.gstack\u002F.git` is missing, ask whether to run `gstack-artifacts-init`. Do not block the skill.\n\nAt skill END before telemetry:\n\n```bash\n\"~\u002F.claude\u002Fskills\u002Fgstack\u002Fbin\u002Fgstack-brain-sync\" --discover-new 2>\u002Fdev\u002Fnull || true\n\"~\u002F.claude\u002Fskills\u002Fgstack\u002Fbin\u002Fgstack-brain-sync\" --once 2>\u002Fdev\u002Fnull || true\n```\n\n\n## Model-Specific Behavioral Patch (claude)\n\nThe following nudges are tuned for the claude model family. They are\n**subordinate** to skill workflow, STOP points, AskUserQuestion gates, plan-mode\nsafety, and \u002Fship review gates. If a nudge below conflicts with skill instructions,\nthe skill wins. Treat these as preferences, not rules.\n\n**Todo-list discipline.** When working through a multi-step plan, mark each task\ncomplete individually as you finish it. Do not batch-complete at the end. If a task\nturns out to be unnecessary, mark it skipped with a one-line reason.\n\n**Think before heavy actions.** For complex operations (refactors, migrations,\nnon-trivial new features), briefly state your approach before executing. This lets\nthe user course-correct cheaply instead of mid-flight.\n\n**Dedicated tools over Bash.** Prefer Read, Edit, Write, Glob, Grep over shell\nequivalents (cat, sed, find, grep). The dedicated tools are cheaper and clearer.\n\n## Voice\n\nDirect, concrete, builder-to-builder. Name the file, function, command, and user-visible impact. No filler.\n\nNo em dashes. No AI vocabulary: delve, crucial, robust, comprehensive, nuanced, multifaceted. Never corporate or academic. Short paragraphs. End with what to do.\n\nThe user has context you do not. Cross-model agreement is a recommendation, not a decision. The user decides.\n\n## Completion Status Protocol\n\nWhen completing a skill workflow, report status using one of:\n- **DONE** — completed with evidence.\n- **DONE_WITH_CONCERNS** — completed, but list concerns.\n- **BLOCKED** — cannot proceed; state blocker and what was tried.\n- **NEEDS_CONTEXT** — missing info; state exactly what is needed.\n\nEscalate after 3 failed attempts, uncertain security-sensitive changes, or scope you cannot verify. Format: `STATUS`, `REASON`, `ATTEMPTED`, `RECOMMENDATION`.\n\n## Operational Self-Improvement\n\nBefore completing, if you discovered a durable project quirk or command fix that would save 5+ minutes next time, log it:\n\n```bash\n~\u002F.claude\u002Fskills\u002Fgstack\u002Fbin\u002Fgstack-learnings-log '{\"skill\":\"SKILL_NAME\",\"type\":\"operational\",\"key\":\"SHORT_KEY\",\"insight\":\"DESCRIPTION\",\"confidence\":N,\"source\":\"observed\"}'\n```\n\nDo not log obvious facts or one-time transient errors.\n\n## Telemetry (run last)\n\nAfter workflow completion, log telemetry. Use skill `name:` from frontmatter. OUTCOME is success\u002Ferror\u002Fabort\u002Funknown.\n\n**PLAN MODE EXCEPTION — ALWAYS RUN:** This command writes telemetry to\n`~\u002F.gstack\u002Fanalytics\u002F`, matching preamble analytics writes.\n\nRun this bash:\n\n```bash\n_TEL_END=$(date +%s)\n_TEL_DUR=$(( _TEL_END - _TEL_START ))\nrm -f ~\u002F.gstack\u002Fanalytics\u002F.pending-\"$_SESSION_ID\" 2>\u002Fdev\u002Fnull || true\n# Session timeline: record skill completion (local-only, never sent anywhere)\n~\u002F.claude\u002Fskills\u002Fgstack\u002Fbin\u002Fgstack-timeline-log '{\"skill\":\"SKILL_NAME\",\"event\":\"completed\",\"branch\":\"'$(git branch --show-current 2>\u002Fdev\u002Fnull || echo unknown)'\",\"outcome\":\"OUTCOME\",\"duration_s\":\"'\"$_TEL_DUR\"'\",\"session\":\"'\"$_SESSION_ID\"'\"}' 2>\u002Fdev\u002Fnull || true\n# Local analytics (gated on telemetry setting)\nif [ \"$_TEL\" != \"off\" ]; then\necho '{\"skill\":\"SKILL_NAME\",\"duration_s\":\"'\"$_TEL_DUR\"'\",\"outcome\":\"OUTCOME\",\"browse\":\"USED_BROWSE\",\"session\":\"'\"$_SESSION_ID\"'\",\"ts\":\"'$(date -u +%Y-%m-%dT%H:%M:%SZ)'\"}' >> ~\u002F.gstack\u002Fanalytics\u002Fskill-usage.jsonl 2>\u002Fdev\u002Fnull || true\nfi\n# Remote telemetry (opt-in, requires binary)\nif [ \"$_TEL\" != \"off\" ] && [ -x ~\u002F.claude\u002Fskills\u002Fgstack\u002Fbin\u002Fgstack-telemetry-log ]; then\n  ~\u002F.claude\u002Fskills\u002Fgstack\u002Fbin\u002Fgstack-telemetry-log \\\n    --skill \"SKILL_NAME\" --duration \"$_TEL_DUR\" --outcome \"OUTCOME\" \\\n    --used-browse \"USED_BROWSE\" --session-id \"$_SESSION_ID\" 2>\u002Fdev\u002Fnull &\nfi\n```\n\nReplace `SKILL_NAME`, `OUTCOME`, and `USED_BROWSE` before running.\n\n## Plan Status Footer\n\nSkills that run plan reviews (`\u002Fplan-*-review`, `\u002Fcodex review`) include the EXIT PLAN MODE GATE blocking checklist at the end of the skill, which verifies the plan file ends with `## GSTACK REVIEW REPORT` before ExitPlanMode is called. Skills that don't run plan reviews (operational skills like `\u002Fship`, `\u002Fqa`, `\u002Freview`) typically don't operate in plan mode and have no review report to verify; this footer is a no-op for them. Writing the plan file is the one edit allowed in plan mode.\n\n# \u002Fbenchmark-models — Cross-Model Skill Benchmark\n\nYou are running the `\u002Fbenchmark-models` workflow. Wraps the `gstack-model-benchmark` binary with an interactive flow that picks a prompt, confirms providers, previews auth, and runs the benchmark.\n\nDifferent from `\u002Fbenchmark` — that skill measures web page performance (Core Web Vitals, load times). This skill measures AI model performance on gstack skills or arbitrary prompts.\n\n---\n\n## Step 0: Locate the binary\n\n```bash\nBIN=\"$HOME\u002F.claude\u002Fskills\u002Fgstack\u002Fbin\u002Fgstack-model-benchmark\"\n[ -x \"$BIN\" ] || BIN=\".claude\u002Fskills\u002Fgstack\u002Fbin\u002Fgstack-model-benchmark\"\n[ -x \"$BIN\" ] || { echo \"ERROR: gstack-model-benchmark not found. Run .\u002Fsetup in the gstack install dir.\" >&2; exit 1; }\necho \"BIN: $BIN\"\n```\n\nIf not found, stop and tell the user to reinstall gstack.\n\n---\n\n## Step 1: Choose a prompt\n\nUse AskUserQuestion with the preamble format:\n- **Re-ground:** current project + branch.\n- **Simplify:** \"A cross-model benchmark runs the same prompt through 2-3 AI models and shows you how they compare on speed, cost, and output quality. What prompt should we use?\"\n- **RECOMMENDATION:** A because benchmarking against a real skill exposes tool-use differences, not just raw generation.\n- **Options:**\n  - A) Benchmark one of my gstack skills (we'll pick which skill next). Completeness: 10\u002F10.\n  - B) Use an inline prompt — type it on the next turn. Completeness: 8\u002F10.\n  - C) Point at a prompt file on disk — specify path on the next turn. Completeness: 8\u002F10.\n\nIf A: list top-level gstack skills that have SKILL.md files (from `find . -maxdepth 2 -name SKILL.md -not -path '.\u002F.*'`), ask the user to pick one via a second AskUserQuestion. Use the picked SKILL.md path as the prompt file.\n\nIf B: ask the user for the inline prompt. Use it verbatim via `--prompt \"\u003Ctext>\"`.\n\nIf C: ask for the path. Verify it exists. Use as positional argument.\n\n---\n\n## Step 2: Choose providers\n\n```bash\n\"$BIN\" --prompt \"unused, dry-run\" --models claude,gpt,gemini --dry-run\n```\n\nShow the dry-run output. The \"Adapter availability\" section tells the user which providers will actually run (OK) vs skip (NOT READY — remediation hint included).\n\nIf ALL three show NOT READY: stop with a clear message — benchmark can't run without at least one authed provider. Suggest `claude login`, `codex login`, or `gemini login` \u002F `export GOOGLE_API_KEY`.\n\nIf at least one is OK: AskUserQuestion:\n- **Simplify:** \"Which models should we include? The dry-run above showed which are authed. Unauthed ones will be skipped cleanly — they won't abort the batch.\"\n- **RECOMMENDATION:** A (all authed providers) because running as many as possible gives the richest comparison.\n- **Options:**\n  - A) All authed providers. Completeness: 10\u002F10.\n  - B) Only Claude. Completeness: 6\u002F10 (no cross-model signal — use \u002Fship's review for solo claude benchmarks instead).\n  - C) Pick two — specify on next turn. Completeness: 8\u002F10.\n\n---\n\n## Step 3: Decide on judge\n\n```bash\n[ -n \"$ANTHROPIC_API_KEY\" ] || grep -q 'ANTHROPIC' \"$HOME\u002F.claude\u002F.credentials.json\" 2>\u002Fdev\u002Fnull && echo \"JUDGE_AVAILABLE\" || echo \"JUDGE_UNAVAILABLE\"\n```\n\nIf judge is available, AskUserQuestion:\n- **Simplify:** \"The quality judge scores each model's output on a 0-10 scale using Anthropic's Claude as a tiebreaker. Adds ~$0.05\u002Frun. Recommended if you care about output quality, not just latency and cost.\"\n- **RECOMMENDATION:** A — the whole point is comparing quality, not just speed.\n- **Options:**\n  - A) Enable judge (adds ~$0.05). Completeness: 10\u002F10.\n  - B) Skip judge — speed\u002Fcost\u002Ftokens only. Completeness: 7\u002F10.\n\nIf judge is NOT available, skip this question and omit the `--judge` flag.\n\n---\n\n## Step 4: Run the benchmark\n\nConstruct the command from Step 1, 2, 3 decisions:\n\n```bash\n\"$BIN\" \u003Cprompt-spec> --models \u003Cpicked-models> [--judge] --output table\n```\n\nWhere `\u003Cprompt-spec>` is either `--prompt \"\u003Ctext>\"` (Step 1B), a file path (Step 1A or 1C), and `\u003Cpicked-models>` is the comma-separated list from Step 2.\n\nStream the output as it arrives. This is slow — each provider runs the prompt fully. Expect 30s-5min depending on prompt complexity and whether `--judge` is on.\n\n---\n\n## Step 5: Interpret results\n\nAfter the table prints, summarize for the user:\n- **Fastest** — provider with lowest latency.\n- **Cheapest** — provider with lowest cost.\n- **Highest quality** (if `--judge` ran) — provider with highest score.\n- **Best overall** — use judgment. If judge ran: quality-weighted. Otherwise: note the tradeoff the user needs to make.\n\nIf any provider hit an error (auth\u002Ftimeout\u002Frate_limit), call it out with the remediation path.\n\n---\n\n## Step 6: Offer to save results\n\nAskUserQuestion:\n- **Simplify:** \"Save this benchmark as JSON so you can compare future runs against it?\"\n- **RECOMMENDATION:** A — skill performance drifts as providers update their models; a saved baseline catches quality regressions.\n- **Options:**\n  - A) Save to `~\u002F.gstack\u002Fbenchmarks\u002F\u003Cdate>-\u003Cskill-or-prompt-slug>.json`. Completeness: 10\u002F10.\n  - B) Just print, don't save. Completeness: 5\u002F10 (loses trend data).\n\nIf A: re-run with `--output json` and tee to the dated file. Print the path so the user can diff future runs against it.\n\n---\n\n## Important Rules\n\n- **Never run a real benchmark without Step 2's dry-run first.** Users need to see auth status before spending API calls.\n- **Never hardcode model names.** Always pass providers from user's Step 2 choice — the binary handles the rest.\n- **Never auto-include `--judge`.** It adds real cost; user must opt in.\n- **If zero providers are authed, STOP.** Don't attempt the benchmark — it produces no useful output.\n- **Cost is visible.** Every run shows per-provider cost in the table. Users should see it before the next run.\n",{"name":5,"version":24,"triggers":25,"description":7,"allowed-tools":30,"preamble-tier":34},"1.0.0",[26,27,28,29],"cross model benchmark","compare claude gpt gemini","benchmark skill across models","which model should I use",[31,32,33],"Bash","Read","AskUserQuestion",1,"master","4aa004da461d820f4ea5499e58eb8d196cf99016","community\u002Fgstack\u002Fg\u002Fgarrytan_gstack_benchmark-models",0,"https:\u002F\u002Fgithub.com\u002FLord1Egypt\u002Fawesome-skill-forge","https:\u002F\u002Fskill-explorer-rho.vercel.app","https:\u002F\u002Fgithub.com\u002FLord1Egypt","Unbreakable. Unstoppable. Unmatched⚡.\r\n Speaker of machine tongues 🤖  | World-builder of decentralized dreams 🌐 | Defender of the digital realm🛡️.","2026-06-10 08:21:01",{"source":8,"skillName":5,"commands":45,"prompt":55,"zipAvailable":56},[46,49,52],{"tool":47,"command":48},"npx","npx skills add Lord1Egypt\u002Fawesome-skill-forge --skill benchmark-models",{"tool":50,"command":51},"bunx","bunx skills add Lord1Egypt\u002Fawesome-skill-forge --skill benchmark-models",{"tool":53,"command":54},"pnpm","pnpm dlx skills add Lord1Egypt\u002Fawesome-skill-forge --skill benchmark-models","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FLord1Egypt\u002Fawesome-skill-forge\u002Fblob\u002Fmaster\u002Fcommunity\u002Fgstack\u002Fg\u002Fgarrytan_gstack_benchmark-models\u002FSKILL.md",true,[],[59,66,73,80,87,94],{"skillNo":60,"name":61,"nameZh":6,"description":62,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":63,"categories":64,"keywords":65,"publishedAt":19},"01M785WKJB99G3STR1NF9NRTJW","youtube-content","YouTube transcripts to summaries, threads, blogs.","https:\u002F\u002Fgithub.com\u002FLord1Egypt\u002Fawesome-skill-forge\u002Fblob\u002Fmaster\u002Fskills\u002Fyoutube-content\u002FSKILL.md",[],[],{"skillNo":67,"name":68,"nameZh":6,"description":69,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":70,"categories":71,"keywords":72,"publishedAt":19},"01M785WEFHB0G2S9YA6EPR3H0E","xurl","X\u002FTwitter via xurl CLI: post, search, DM, media, v2 API.","https:\u002F\u002Fgithub.com\u002FLord1Egypt\u002Fawesome-skill-forge\u002Fblob\u002Fmaster\u002Fskills\u002Fxurl\u002FSKILL.md",[],[],{"skillNo":74,"name":75,"nameZh":6,"description":76,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":77,"categories":78,"keywords":79,"publishedAt":19},"01M785W98EDN4EFJXJPMQEHCRC","touchdesigner-mcp","Control a running TouchDesigner instance via twozero MCP — create operators, set parameters, wire connections, execute Python, build real-time visuals. 36 native tools.","https:\u002F\u002Fgithub.com\u002FLord1Egypt\u002Fawesome-skill-forge\u002Fblob\u002Fmaster\u002Fskills\u002Ftouchdesigner-mcp\u002FSKILL.md",[],[],{"skillNo":81,"name":82,"nameZh":6,"description":83,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":84,"categories":85,"keywords":86,"publishedAt":19},"01M785W5S9FP3QBH2V191E025P","test-driven-development","TDD: enforce RED-GREEN-REFACTOR, tests before code.","https:\u002F\u002Fgithub.com\u002FLord1Egypt\u002Fawesome-skill-forge\u002Fblob\u002Fmaster\u002Fskills\u002Ftest-driven-development\u002FSKILL.md",[],[],{"skillNo":88,"name":89,"nameZh":6,"description":90,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":91,"categories":92,"keywords":93,"publishedAt":19},"01M785W2AS08NSSH9YATCV6FJB","teams-meeting-pipeline","Operate the Teams meeting summary pipeline via Hermes CLI — summarize meetings, inspect pipeline status, replay jobs, manage Microsoft Graph subscriptions.","https:\u002F\u002Fgithub.com\u002FLord1Egypt\u002Fawesome-skill-forge\u002Fblob\u002Fmaster\u002Fskills\u002Fteams-meeting-pipeline\u002FSKILL.md",[],[],{"skillNo":95,"name":96,"nameZh":6,"description":97,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":98,"categories":99,"keywords":100,"publishedAt":19},"01M785VXKW4T34BTP1SCHW1R7F","systematic-debugging","4-phase root cause debugging: understand bugs before fixing.","https:\u002F\u002Fgithub.com\u002FLord1Egypt\u002Fawesome-skill-forge\u002Fblob\u002Fmaster\u002Fskills\u002Fsystematic-debugging\u002FSKILL.md",[],[]]