Self-evolving second brain with 35 AI skills, 10 agents, and people CRM. Closed-loop harness: a V-model verification lifecycle where the worker never grades its own homework. Plus paired anti-slop design skills for marketing and product UI. Works with Claude Code, Cursor, Kiro, Gemini CLI, Codex.
Python agent-loopagent-pluginsagent-skillsagenticai-agentsclaude-codeclosed-loopcursorgarry-tangbraingstackknowledge-managementloop-engineeringobsidianpeople-crmproductivitysecond-brainself-evolvingverification-harnessworker-agents
feat: add Antigravity agent format support (v3.9.0) (#23)
Muhammed Baqer Ahmedacf9b42ae87c
diff --git a/.agents/agents/brief-people-updater.md b/.agents/agents/brief-people-updater.mdnew file mode 100644index 0000000..fb6bf4f--- /dev/null+++ b/.agents/agents/brief-people-updater.md@@ -0,0 +1,9 @@+---+name: brief-people-updater+description: Update people profiles in 05-knowledge/people/ with new information from brief data, meetings, or Slack+subagent: true+model: flash+---++Read `.claude/agents/brief-people-updater.md` and adopt that role exactly, including its Output Rule — write results+to a file and return only a short status plus the file path.diff --git a/.agents/agents/fix-agent.md b/.agents/agents/fix-agent.mdnew file mode 100644index 0000000..406c8c6--- /dev/null+++ b/.agents/agents/fix-agent.md@@ -0,0 +1,9 @@+---+name: fix-agent+description: Targeted fixes after task-verifier returns FAIL:fixable. Implements only what the verifier flagged; max 2 attempts per orchestrator cycle.+subagent: true+model: flash+---++Read `.claude/agents/fix-agent.md` and adopt that role exactly — implement only what the verifier flagged,+max 2 attempts per orchestrator cycle.diff --git a/.agents/agents/harvest-curator.md b/.agents/agents/harvest-curator.mdnew file mode 100644index 0000000..610d178--- /dev/null+++ b/.agents/agents/harvest-curator.md@@ -0,0 +1,10 @@+---+name: harvest-curator+description: Draft session learnings from harvest staging into lizard-ready adoption notes. Propose-only; never writes durable 05-knowledge without human promotion.+subagent: true+model: flash+---++Read `.claude/agents/harvest-curator.md` and adopt that role exactly, including its Output Rule — write results+to a file and return only a short status plus the file path. Propose-only: never write durable `05-knowledge/`+content without human promotion.diff --git a/.agents/agents/integration-verifier.md b/.agents/agents/integration-verifier.mdnew file mode 100644index 0000000..c01e8a1--- /dev/null+++ b/.agents/agents/integration-verifier.md@@ -0,0 +1,9 @@+---+name: integration-verifier+description: Read-only CP-4 gate. Cross-task wiring and global acceptance for multi-task specs. Cannot edit files.+subagent: true+model: flash+---++Read `.claude/agents/integration-verifier.md` and adopt that role exactly. This is a read-only gate — do not+edit files.diff --git a/.agents/agents/task-verifier.md b/.agents/agents/task-verifier.mdnew file mode 100644index 0000000..c50bb4b--- /dev/null+++ b/.agents/agents/task-verifier.md@@ -0,0 +1,9 @@+---+name: task-verifier+description: Read-only verification gate. Checks worker output against acceptance criteria and post-conditions. Cannot edit files or mutate external state.+subagent: true+model: flash+---++Read `.claude/agents/task-verifier.md` and adopt that role exactly. This is a read-only gate — do not edit+files or mutate external state.diff --git a/.agents/agents/worker-data-collector.md b/.agents/agents/worker-data-collector.mdnew file mode 100644index 0000000..85a3b4e--- /dev/null+++ b/.agents/agents/worker-data-collector.md@@ -0,0 +1,9 @@+---+name: worker-data-collector+description: Collect data from GitHub, Slack, Jira, Linear, or file system. Structured extraction only — no synthesis.+subagent: true+model: flash+---++Read `.claude/agents/worker-data-collector.md` and adopt that role exactly, including its Output Rule — write results+to a file and return only a short status plus the file path.diff --git a/.agents/agents/worker-executor.md b/.agents/agents/worker-executor.mdnew file mode 100644index 0000000..84d8ca1--- /dev/null+++ b/.agents/agents/worker-executor.md@@ -0,0 +1,9 @@+---+name: worker-executor+description: Execute pre-approved mutations — Jira transitions, Linear updates, API calls, build commands.+subagent: true+model: flash+---++Read `.claude/agents/worker-executor.md` and adopt that role exactly, including its Output Rule — write results+to a file and return only a short status plus the file path.diff --git a/.agents/agents/worker-file-ops.md b/.agents/agents/worker-file-ops.mdnew file mode 100644index 0000000..3d8bc7c--- /dev/null+++ b/.agents/agents/worker-file-ops.md@@ -0,0 +1,9 @@+---+name: worker-file-ops+description: Read, write, and organize vault files. Metadata updates, file moves, profile updates.+subagent: true+model: flash+---++Read `.claude/agents/worker-file-ops.md` and adopt that role exactly, including its Output Rule — write results+to a file and return only a short status plus the file path.diff --git a/.agents/agents/worker-publisher.md b/.agents/agents/worker-publisher.mdnew file mode 100644index 0000000..b7713eb--- /dev/null+++ b/.agents/agents/worker-publisher.md@@ -0,0 +1,9 @@+---+name: worker-publisher+description: Execute publishing operations — Slack, Confluence, Notion, webhooks. Receives final content and posts it.+subagent: true+model: flash+---++Read `.claude/agents/worker-publisher.md` and adopt that role exactly, including its Output Rule — write results+to a file and return only a short status plus the file path.diff --git a/.agents/agents/worker-researcher.md b/.agents/agents/worker-researcher.mdnew file mode 100644index 0000000..8240c17--- /dev/null+++ b/.agents/agents/worker-researcher.md@@ -0,0 +1,9 @@+---+name: worker-researcher+description: Web research agent. Searches, fetches URLs, extracts facts and evidence. No synthesis — just structured findings.+subagent: true+model: flash+---++Read `.claude/agents/worker-researcher.md` and adopt that role exactly, including its Output Rule — write results+to a file and return only a short status plus the file path.diff --git a/.agents/rules/cog.md b/.agents/rules/cog.mdnew file mode 100644index 0000000..c42575a--- /dev/null+++ b/.agents/rules/cog.md@@ -0,0 +1,11 @@+---+description: COG framework operating policy+---++Read `CLAUDE.md` at the repository root and treat every section marked+`ALWAYS APPLY` / `MUST APPLY` as binding.++Antigravity substitutions:+- `.claude/skills/<name>/SKILL.md` → read that path directly; it is authoritative.+- `.claude/agents/<name>.md` workers → `.agents/agents/<name>.md`, invoked via `invoke_subagent`.+- Model Routing table: `sonnet` → `model: flash`; the lead/orchestrator role is this session.diff --git a/.agents/skills/auto-research/SKILL.md b/.agents/skills/auto-research/SKILL.mdnew file mode 100644index 0000000..c7342d2--- /dev/null+++ b/.agents/skills/auto-research/SKILL.md@@ -0,0 +1,10 @@+---+name: auto-research+description: Deep strategic research engine — decomposes questions into parallel research threads, spawns multiple agents, and synthesizes into actionable strategic analysis+---++Read `.claude/skills/auto-research/SKILL.md` and execute it exactly as written — that file is the authoritative+playbook. Then follow `.agents/rules/cog.md`.++Antigravity substitution: where the playbook delegates to a `.claude/agents/<name>`+worker, invoke `.agents/agents/<name>.md` via `invoke_subagent` instead.diff --git a/.agents/skills/braindump/SKILL.md b/.agents/skills/braindump/SKILL.mdnew file mode 100644index 0000000..b19e748--- /dev/null+++ b/.agents/skills/braindump/SKILL.md@@ -0,0 +1,10 @@+---+name: braindump+description: Quick capture of raw thoughts with intelligent domain classification and competitive intelligence extraction+---++Read `.claude/skills/braindump/SKILL.md` and execute it exactly as written — that file is the authoritative+playbook. Then follow `.agents/rules/cog.md`.++Antigravity substitution: where the playbook delegates to a `.claude/agents/<name>`+worker, invoke `.agents/agents/<name>.md` via `invoke_subagent` instead.diff --git a/.agents/skills/closed-loop/SKILL.md b/.agents/skills/closed-loop/SKILL.mdnew file mode 100644index 0000000..ba2109e--- /dev/null+++ b/.agents/skills/closed-loop/SKILL.md@@ -0,0 +1,10 @@+---+name: closed-loop+description: V-model execute: CP-2 plan → CP-3 build → CP-3v component verify → CP-4 integration verify (full) → CP-5 acceptance. Worker never grades its own homework; evidence rows trace back to AC-n. Use via /execute.+---++Read `.claude/skills/closed-loop/SKILL.md` and execute it exactly as written — that file is the authoritative+playbook. Then follow `.agents/rules/cog.md`.++Antigravity substitution: where the playbook delegates to a `.claude/agents/<name>`+worker, invoke `.agents/agents/<name>.md` via `invoke_subagent` instead.diff --git a/.agents/skills/comprehensive-analysis/SKILL.md b/.agents/skills/comprehensive-analysis/SKILL.mdnew file mode 100644index 0000000..c1f7352--- /dev/null+++ b/.agents/skills/comprehensive-analysis/SKILL.md@@ -0,0 +1,10 @@+---+name: comprehensive-analysis+description: Deep-dive 7-day analysis across all data sources for weekly reviews, board prep, and strategic planning+---++Read `.claude/skills/comprehensive-analysis/SKILL.md` and execute it exactly as written — that file is the authoritative+playbook. Then follow `.agents/rules/cog.md`.++Antigravity substitution: where the playbook delegates to a `.claude/agents/<name>`+worker, invoke `.agents/agents/<name>.md` via `invoke_subagent` instead.diff --git a/.agents/skills/content-factory/SKILL.md b/.agents/skills/content-factory/SKILL.mdnew file mode 100644index 0000000..86bb44d--- /dev/null+++ b/.agents/skills/content-factory/SKILL.md@@ -0,0 +1,10 @@+---+name: content-factory+description: Autonomous content pipeline - scout announcements in your field, triage by trend momentum and personal angle, produce posts/blogs/videos in your voice with ledger-based dedup, hard volume caps, and screenshot-verified publishing+---++Read `.claude/skills/content-factory/SKILL.md` and execute it exactly as written — that file is the authoritative+playbook. Then follow `.agents/rules/cog.md`.++Antigravity substitution: where the playbook delegates to a `.claude/agents/<name>`+worker, invoke `.agents/agents/<name>.md` via `invoke_subagent` instead.diff --git a/.agents/skills/create-user-story/SKILL.md b/.agents/skills/create-user-story/SKILL.mdnew file mode 100644index 0000000..7337083--- /dev/null+++ b/.agents/skills/create-user-story/SKILL.md@@ -0,0 +1,10 @@+---+name: create-user-story+description: Create user stories with duplicate checking across any project tracker (Linear, GitHub Issues, Jira)+---++Read `.claude/skills/create-user-story/SKILL.md` and execute it exactly as written — that file is the authoritative+playbook. Then follow `.agents/rules/cog.md`.++Antigravity substitution: where the playbook delegates to a `.claude/agents/<name>`+worker, invoke `.agents/agents/<name>.md` via `invoke_subagent` instead.diff --git a/.agents/skills/daily-brief/SKILL.md b/.agents/skills/daily-brief/SKILL.mdnew file mode 100644index 0000000..d97304f--- /dev/null+++ b/.agents/skills/daily-brief/SKILL.md@@ -0,0 +1,10 @@+---+name: daily-brief+description: Generate personalized news intelligence with verified sources (7-day freshness requirement)+---++Read `.claude/skills/daily-brief/SKILL.md` and execute it exactly as written — that file is the authoritative+playbook. Then follow `.agents/rules/cog.md`.++Antigravity substitution: where the playbook delegates to a `.claude/agents/<name>`+worker, invoke `.agents/agents/<name>.md` via `invoke_subagent` instead.diff --git a/.agents/skills/daily-journal/SKILL.md b/.agents/skills/daily-journal/SKILL.mdnew file mode 100644index 0000000..ab65374--- /dev/null+++ b/.agents/skills/daily-journal/SKILL.md@@ -0,0 +1,10 @@+---+name: daily-journal+description: A passive daily work journal that Claude keeps FOR you so you never have to write it yourself. Append short entries after meaningful work (what was done, what you focused on, artifacts touched) to 01-daily/journal/YYYY-MM-DD.md. Run a guided reflection at night or in the morning. Use when you run /daily-journal, say "log this to my journal", "add to today's journal", "reflect on today/yesterday", or when finishing a meaningful chunk of work in any session.+---++Read `.claude/skills/daily-journal/SKILL.md` and execute it exactly as written — that file is the authoritative+playbook. Then follow `.agents/rules/cog.md`.++Antigravity substitution: where the playbook delegates to a `.claude/agents/<name>`+worker, invoke `.agents/agents/<name>.md` via `invoke_subagent` instead.diff --git a/.agents/skills/data-forms/SKILL.md b/.agents/skills/data-forms/SKILL.mdnew file mode 100644index 0000000..ef5209c--- /dev/null+++ b/.agents/skills/data-forms/SKILL.md@@ -0,0 +1,10 @@+---+name: data-forms+description: Pick the right way to represent a dataset so a reader gets the finding in three seconds — a catalog of 20+ chart and diagram forms with when-to-use and failure modes, plus the encoding decisions that make any of them readable (takeaway headline, direct labels, kill the axis, highlight-and-mute, show the caveat). Style-agnostic — use with whatever palette or design system the destination already has. Use when charting survey results, benchmark data, usage metrics, or research findings for a post, brief, deck, or report, and whenever the default bar chart feels like it's burying the point.+---++Read `.claude/skills/data-forms/SKILL.md` and execute it exactly as written — that file is the authoritative+playbook. Then follow `.agents/rules/cog.md`.++Antigravity substitution: where the playbook delegates to a `.claude/agents/<name>`+worker, invoke `.agents/agents/<name>.md` via `invoke_subagent` instead.diff --git a/.agents/skills/editorial-illustrations/SKILL.md b/.agents/skills/editorial-illustrations/SKILL.mdnew file mode 100644index 0000000..368c7d8--- /dev/null+++ b/.agents/skills/editorial-illustrations/SKILL.md@@ -0,0 +1,10 @@+---+name: editorial-illustrations+description: Generate meaning-carrying editorial data-illustrations in the monotykamary / Linear aesthetic (near-black grayscale, Inter display + mono labels, hairline framed figures) with a single coral accent. This is a GENERATIVE GUIDE, not a template gallery: it teaches the "claim -> geometry" method so any session can invent the RIGHT figure for what a post actually argues, then render it as a self-contained, theme-aware, reduced-motion-safe HTML/SVG figure. Use when writing/illustrating a blog post, essay, spec, or slide and you want a chart, diagram, or illustration that carries a thesis (not decoration) in the house style. Triggers: "make a chart/diagram/illustration for this", "visualize this argument", "monotykamary/Linear style figure", "editorial graphic".+---++Read `.claude/skills/editorial-illustrations/SKILL.md` and execute it exactly as written — that file is the authoritative+playbook. Then follow `.agents/rules/cog.md`.++Antigravity substitution: where the playbook delegates to a `.claude/agents/<name>`+worker, invoke `.agents/agents/<name>.md` via `invoke_subagent` instead.diff --git a/.agents/skills/export-open-issues/SKILL.md b/.agents/skills/export-open-issues/SKILL.mdnew file mode 100644index 0000000..b88f5e1--- /dev/null+++ b/.agents/skills/export-open-issues/SKILL.md@@ -0,0 +1,10 @@+---+name: export-open-issues+description: Audit and export open issues from any project tracker with summary analysis and vault archival+---++Read `.claude/skills/export-open-issues/SKILL.md` and execute it exactly as written — that file is the authoritative+playbook. Then follow `.agents/rules/cog.md`.++Antigravity substitution: where the playbook delegates to a `.claude/agents/<name>`+worker, invoke `.agents/agents/<name>.md` via `invoke_subagent` instead.diff --git a/.agents/skills/generate-prd/SKILL.md b/.agents/skills/generate-prd/SKILL.mdnew file mode 100644index 0000000..8299007--- /dev/null+++ b/.agents/skills/generate-prd/SKILL.md@@ -0,0 +1,10 @@+---+name: generate-prd+description: Generate product requirements documents with optional publishing to Confluence or other wiki platforms+---++Read `.claude/skills/generate-prd/SKILL.md` and execute it exactly as written — that file is the authoritative+playbook. Then follow `.agents/rules/cog.md`.++Antigravity substitution: where the playbook delegates to a `.claude/agents/<name>`+worker, invoke `.agents/agents/<name>.md` via `invoke_subagent` instead.diff --git a/.agents/skills/generate-release-notes/SKILL.md b/.agents/skills/generate-release-notes/SKILL.mdnew file mode 100644index 0000000..6ded908--- /dev/null+++ b/.agents/skills/generate-release-notes/SKILL.md@@ -0,0 +1,10 @@+---+name: generate-release-notes+description: Generate categorized release notes from any source (GitHub, Linear, Jira, or manual input) with optional publishing+---++Read `.claude/skills/generate-release-notes/SKILL.md` and execute it exactly as written — that file is the authoritative+playbook. Then follow `.agents/rules/cog.md`.++Antigravity substitution: where the playbook delegates to a `.claude/agents/<name>`+worker, invoke `.agents/agents/<name>.md` via `invoke_subagent` instead.diff --git a/.agents/skills/harvest/SKILL.md b/.agents/skills/harvest/SKILL.mdnew file mode 100644index 0000000..673f736--- /dev/null+++ b/.agents/skills/harvest/SKILL.md@@ -0,0 +1,10 @@+---+name: harvest+description: Capture durable session learnings, stage for human promotion to 05-knowledge/lizard, and propose skill/CLAUDE.md patches. Triggered by /harvest, SessionEnd hook staging, or nightly enhance. Never writes durable knowledge without your approval.+---++Read `.claude/skills/harvest/SKILL.md` and execute it exactly as written — that file is the authoritative+playbook. Then follow `.agents/rules/cog.md`.++Antigravity substitution: where the playbook delegates to a `.claude/agents/<name>`+worker, invoke `.agents/agents/<name>.md` via `invoke_subagent` instead.diff --git a/.agents/skills/knowledge-consolidation/SKILL.md b/.agents/skills/knowledge-consolidation/SKILL.mdnew file mode 100644index 0000000..1797981--- /dev/null+++ b/.agents/skills/knowledge-consolidation/SKILL.md@@ -0,0 +1,10 @@+---+name: knowledge-consolidation+description: Build frameworks from scattered insights across all braindumps and notes+---++Read `.claude/skills/knowledge-consolidation/SKILL.md` and execute it exactly as written — that file is the authoritative+playbook. Then follow `.agents/rules/cog.md`.++Antigravity substitution: where the playbook delegates to a `.claude/agents/<name>`+worker, invoke `.agents/agents/<name>.md` via `invoke_subagent` instead.diff --git a/.agents/skills/loop-engineering/SKILL.md b/.agents/skills/loop-engineering/SKILL.mdnew file mode 100644index 0000000..938de4e--- /dev/null+++ b/.agents/skills/loop-engineering/SKILL.md@@ -0,0 +1,10 @@+---+name: loop-engineering+description: Shared loop-engineering reference for COG skills - the agent loop, deterministic verifiers, termination conditions, in-loop context management, and named patterns. Invoke when designing or debugging a skill that iterates (search-verify-retry, scan-until-dry, fetch-retry-gate).+---++Read `.claude/skills/loop-engineering/SKILL.md` and execute it exactly as written — that file is the authoritative+playbook. Then follow `.agents/rules/cog.md`.++Antigravity substitution: where the playbook delegates to a `.claude/agents/<name>`+worker, invoke `.agents/agents/<name>.md` via `invoke_subagent` instead.diff --git a/.agents/skills/meeting-transcript/SKILL.md b/.agents/skills/meeting-transcript/SKILL.mdnew file mode 100644index 0000000..e668ea2--- /dev/null+++ b/.agents/skills/meeting-transcript/SKILL.md@@ -0,0 +1,10 @@+---+name: meeting-transcript+description: Process meeting recordings and notes into structured decisions, action items, and team dynamics with intelligent noise filtering+---++Read `.claude/skills/meeting-transcript/SKILL.md` and execute it exactly as written — that file is the authoritative+playbook. Then follow `.agents/rules/cog.md`.++Antigravity substitution: where the playbook delegates to a `.claude/agents/<name>`+worker, invoke `.agents/agents/<name>.md` via `invoke_subagent` instead.diff --git a/.agents/skills/memory-hygiene/SKILL.md b/.agents/skills/memory-hygiene/SKILL.mdnew file mode 100644index 0000000..4c1bdf4--- /dev/null+++ b/.agents/skills/memory-hygiene/SKILL.md@@ -0,0 +1,10 @@+---+name: memory-hygiene+description: Periodic trust sweep of persistent memory and durable knowledge notes - re-verifies environment-dependent claims against the live environment, stamps last_verified + confidence, and proposes archiving drifted entries+---++Read `.claude/skills/memory-hygiene/SKILL.md` and execute it exactly as written — that file is the authoritative+playbook. Then follow `.agents/rules/cog.md`.++Antigravity substitution: where the playbook delegates to a `.claude/agents/<name>`+worker, invoke `.agents/agents/<name>.md` via `invoke_subagent` instead.diff --git a/.agents/skills/museum-art/SKILL.md b/.agents/skills/museum-art/SKILL.mdnew file mode 100644index 0000000..d0bd22b--- /dev/null+++ b/.agents/skills/museum-art/SKILL.md@@ -0,0 +1,10 @@+---+name: museum-art+description: Source authentic, high-res PUBLIC-DOMAIN artwork from museum open-access APIs (Met, Cleveland, SMK, Rijksmuseum, NGA, Art Institute of Chicago, Getty, Smithsonian) instead of AI-generated or generic-stock imagery. The default move whenever a visual needs an aesthetic, credible image (blog heroes, decks, social cards, essay/spec figures). Verified keyless recipes + licensing rules inside.+---++Read `.claude/skills/museum-art/SKILL.md` and execute it exactly as written — that file is the authoritative+playbook. Then follow `.agents/rules/cog.md`.++Antigravity substitution: where the playbook delegates to a `.claude/agents/<name>`+worker, invoke `.agents/agents/<name>.md` via `invoke_subagent` instead.diff --git a/.agents/skills/no-ai-slop/SKILL.md b/.agents/skills/no-ai-slop/SKILL.mdnew file mode 100644index 0000000..3bf4b34--- /dev/null+++ b/.agents/skills/no-ai-slop/SKILL.md@@ -0,0 +1,10 @@+---+name: no-ai-slop+description: Edit drafts into sharper, more human writing while preserving the writer's personal voice, or detect AI-slop patterns without rewriting. Use when the user wants a draft clearer, more direct, more opinionated, or less AI-sounding, or asks whether writing reads as AI.+---++Read `.claude/skills/no-ai-slop/SKILL.md` and execute it exactly as written — that file is the authoritative+playbook. Then follow `.agents/rules/cog.md`.++Antigravity substitution: where the playbook delegates to a `.claude/agents/<name>`+worker, invoke `.agents/agents/<name>.md` via `invoke_subagent` instead.diff --git a/.agents/skills/onboarding/SKILL.md b/.agents/skills/onboarding/SKILL.mdnew file mode 100644index 0000000..cefd9f3--- /dev/null+++ b/.agents/skills/onboarding/SKILL.md@@ -0,0 +1,10 @@+---+name: onboarding+description: Personalize COG for your workflow - creates profile, interests, and watchlist files with guided setup (run this first!)+---++Read `.claude/skills/onboarding/SKILL.md` and execute it exactly as written — that file is the authoritative+playbook. Then follow `.agents/rules/cog.md`.++Antigravity substitution: where the playbook delegates to a `.claude/agents/<name>`+worker, invoke `.agents/agents/<name>.md` via `invoke_subagent` instead.diff --git a/.agents/skills/product-ui-taste/SKILL.md b/.agents/skills/product-ui-taste/SKILL.mdnew file mode 100644index 0000000..ad9dba2--- /dev/null+++ b/.agents/skills/product-ui-taste/SKILL.md@@ -0,0 +1,10 @@+---+name: product-ui-taste+description: Anti-slop skill for PRODUCT UI - dashboards, data tables, forms, multi-step flows, settings, list/detail, app shells. The agent reads the surface, budgets the frame first, and ships dense interfaces that are correct at every edge case (overflow, long labels, empty/error/loading states, i18n expansion, keyboard/a11y). House-system-first; maps to Carbon/Polaris/Atlaskit/Fluent/Primer/Material3/Radix-shadcn/Ant. The counterpart to taste-skill, which owns landing/portfolio/marketing.+---++Read `.claude/skills/product-ui-taste/SKILL.md` and execute it exactly as written — that file is the authoritative+playbook. Then follow `.agents/rules/cog.md`.++Antigravity substitution: where the playbook delegates to a `.claude/agents/<name>`+worker, invoke `.agents/agents/<name>.md` via `invoke_subagent` instead.diff --git a/.agents/skills/publish-to-confluence/SKILL.md b/.agents/skills/publish-to-confluence/SKILL.mdnew file mode 100644index 0000000..8d47618--- /dev/null+++ b/.agents/skills/publish-to-confluence/SKILL.md@@ -0,0 +1,10 @@+---+name: publish-to-confluence+description: Publish any markdown file from the vault to Confluence with format conversion and approval gate+---++Read `.claude/skills/publish-to-confluence/SKILL.md` and execute it exactly as written — that file is the authoritative+playbook. Then follow `.agents/rules/cog.md`.++Antigravity substitution: where the playbook delegates to a `.claude/agents/<name>`+worker, invoke `.agents/agents/<name>.md` via `invoke_subagent` instead.diff --git a/.agents/skills/retro/SKILL.md b/.agents/skills/retro/SKILL.mdnew file mode 100644index 0000000..d6d953b--- /dev/null+++ b/.agents/skills/retro/SKILL.md@@ -0,0 +1,10 @@+---+name: retro+description: CP-7 retrospective: audit checkpoints, evidence quality, action items, and harvest candidates. Closes the V-model cycle and feeds the next run. Use via /retro after ship, escalate, or significant session.+---++Read `.claude/skills/retro/SKILL.md` and execute it exactly as written — that file is the authoritative+playbook. Then follow `.agents/rules/cog.md`.++Antigravity substitution: where the playbook delegates to a `.claude/agents/<name>`+worker, invoke `.agents/agents/<name>.md` via `invoke_subagent` instead.diff --git a/.agents/skills/review-cockpit/SKILL.md b/.agents/skills/review-cockpit/SKILL.mdnew file mode 100644index 0000000..63d1339--- /dev/null+++ b/.agents/skills/review-cockpit/SKILL.md@@ -0,0 +1,10 @@+---+name: review-cockpit+description: Produce and continuously maintain ONE living review document for a multi-item session — a cockpit header (Progress checklist, Working folder, Context) plus per-item review cards that you approve or request changes on directly in the doc or side panel. Use whenever a session has multiple deliverables you need to review/approve (meeting-processing + planning, multi-ticket work, briefs with several drafts, any "do X, then plan/draft Y and Z"). The doc is the interaction surface: you edit it (or reply in chat) to approve/change; the agent keeps it live as work progresses.+---++Read `.claude/skills/review-cockpit/SKILL.md` and execute it exactly as written — that file is the authoritative+playbook. Then follow `.agents/rules/cog.md`.++Antigravity substitution: where the playbook delegates to a `.claude/agents/<name>`+worker, invoke `.agents/agents/<name>.md` via `invoke_subagent` instead.diff --git a/.agents/skills/scout/SKILL.md b/.agents/skills/scout/SKILL.mdnew file mode 100644index 0000000..c8d612a--- /dev/null+++ b/.agents/skills/scout/SKILL.md@@ -0,0 +1,10 @@+---+name: scout+description: Evaluate URLs and tools — check vault coverage, assess relevance, recommend save or skip+---++Read `.claude/skills/scout/SKILL.md` and execute it exactly as written — that file is the authoritative+playbook. Then follow `.agents/rules/cog.md`.++Antigravity substitution: where the playbook delegates to a `.claude/agents/<name>`+worker, invoke `.agents/agents/<name>.md` via `invoke_subagent` instead.diff --git a/.agents/skills/taste-skill/SKILL.md b/.agents/skills/taste-skill/SKILL.mdnew file mode 100644index 0000000..78d7e8c--- /dev/null+++ b/.agents/skills/taste-skill/SKILL.md@@ -0,0 +1,10 @@+---+name: taste-skill+description: Anti-slop frontend skill for landing pages, portfolios, and redesigns. The agent reads the brief, infers the right design direction, and ships interfaces that do not look templated. Real design systems when applicable, audit-first on redesigns, strict pre-flight check.+---++Read `.claude/skills/taste-skill/SKILL.md` and execute it exactly as written — that file is the authoritative+playbook. Then follow `.agents/rules/cog.md`.++Antigravity substitution: where the playbook delegates to a `.claude/agents/<name>`+worker, invoke `.agents/agents/<name>.md` via `invoke_subagent` instead.diff --git a/.agents/skills/team-brief/SKILL.md b/.agents/skills/team-brief/SKILL.mdnew file mode 100644index 0000000..d4ff136--- /dev/null+++ b/.agents/skills/team-brief/SKILL.md@@ -0,0 +1,10 @@+---+name: team-brief+description: Generate daily team intelligence brief by cross-referencing GitHub, Linear, Slack, PostHog, meetings, and braindumps with two-way Linear sync-back+---++Read `.claude/skills/team-brief/SKILL.md` and execute it exactly as written — that file is the authoritative+playbook. Then follow `.agents/rules/cog.md`.++Antigravity substitution: where the playbook delegates to a `.claude/agents/<name>`+worker, invoke `.agents/agents/<name>.md` via `invoke_subagent` instead.diff --git a/.agents/skills/ultragoal/SKILL.md b/.agents/skills/ultragoal/SKILL.mdnew file mode 100644index 0000000..bcf018a--- /dev/null+++ b/.agents/skills/ultragoal/SKILL.md@@ -0,0 +1,10 @@+---+name: ultragoal+description: Run a large, multi-session goal (e.g. shipping a whole side product) through the full V-model closed loop, one phase at a time, with cross-session state and a final north-star acceptance gate. Ultragoals never downgrade the lane: every phase runs CP-1→CP-6 with adversarial verification. Use via /ultragoal.+---++Read `.claude/skills/ultragoal/SKILL.md` and execute it exactly as written — that file is the authoritative+playbook. Then follow `.agents/rules/cog.md`.++Antigravity substitution: where the playbook delegates to a `.claude/agents/<name>`+worker, invoke `.agents/agents/<name>.md` via `invoke_subagent` instead.diff --git a/.agents/skills/update-cog/SKILL.md b/.agents/skills/update-cog/SKILL.mdnew file mode 100644index 0000000..626ef2d--- /dev/null+++ b/.agents/skills/update-cog/SKILL.md@@ -0,0 +1,10 @@+---+name: update-cog+description: Check for and apply upstream COG framework updates (skills, docs, scripts) without touching personal content+---++Read `.claude/skills/update-cog/SKILL.md` and execute it exactly as written — that file is the authoritative+playbook. Then follow `.agents/rules/cog.md`.++Antigravity substitution: where the playbook delegates to a `.claude/agents/<name>`+worker, invoke `.agents/agents/<name>.md` via `invoke_subagent` instead.diff --git a/.agents/skills/update-knowledge-base/SKILL.md b/.agents/skills/update-knowledge-base/SKILL.mdnew file mode 100644index 0000000..9467da2--- /dev/null+++ b/.agents/skills/update-knowledge-base/SKILL.md@@ -0,0 +1,10 @@+---+name: update-knowledge-base+description: Maintain and update product knowledge base from releases, features, and project changes with optional wiki sync+---++Read `.claude/skills/update-knowledge-base/SKILL.md` and execute it exactly as written — that file is the authoritative+playbook. Then follow `.agents/rules/cog.md`.++Antigravity substitution: where the playbook delegates to a `.claude/agents/<name>`+worker, invoke `.agents/agents/<name>.md` via `invoke_subagent` instead.diff --git a/.agents/skills/url-dump/SKILL.md b/.agents/skills/url-dump/SKILL.mdnew file mode 100644index 0000000..6444921--- /dev/null+++ b/.agents/skills/url-dump/SKILL.md@@ -0,0 +1,10 @@+---+name: url-dump+description: Quick capture URLs with automatic content extraction, insights, and categorization into knowledge booklets+---++Read `.claude/skills/url-dump/SKILL.md` and execute it exactly as written — that file is the authoritative+playbook. Then follow `.agents/rules/cog.md`.++Antigravity substitution: where the playbook delegates to a `.claude/agents/<name>`+worker, invoke `.agents/agents/<name>.md` via `invoke_subagent` instead.diff --git a/.agents/skills/weekly-checkin/SKILL.md b/.agents/skills/weekly-checkin/SKILL.mdnew file mode 100644index 0000000..424c460--- /dev/null+++ b/.agents/skills/weekly-checkin/SKILL.md@@ -0,0 +1,10 @@+---+name: weekly-checkin+description: Cross-domain pattern analysis and strategic reflection for weekly review+---++Read `.claude/skills/weekly-checkin/SKILL.md` and execute it exactly as written — that file is the authoritative+playbook. Then follow `.agents/rules/cog.md`.++Antigravity substitution: where the playbook delegates to a `.claude/agents/<name>`+worker, invoke `.agents/agents/<name>.md` via `invoke_subagent` instead.diff --git a/.claude-plugin/plugin.json b/.claude-plugin/plugin.jsonindex 64704dc..ce1fd66 100644--- a/.claude-plugin/plugin.json+++ b/.claude-plugin/plugin.json@@ -1,7 +1,7 @@{"name": "cog-second-brain",- "version": "3.8.1",- "description": "Self-evolving second brain with 33 AI agent skills, 10 agents, and people CRM. Closed-loop harness release: a V-model verification lifecycle (spec to evidence, criterion-traced checkpoints), read-only verifier agents that observe artifacts instead of trusting worker summaries, risk lanes, multi-session ultragoals with a north-star acceptance gate, plus craft skills for writing, visual work, and a paired anti-slop design system for marketing and product UI. Inspired by Garry Tan's gstack specialist sessions, gbrain knowledge patterns, and dwarves-kit closed-loop execution. Works with Claude Code, Cursor, Kiro, Gemini CLI, Codex, and any markdown-reading agent.",+ "version": "3.9.0",+ "description": "Self-evolving second brain with 33 AI agent skills, 10 agents, and people CRM. Closed-loop harness release: a V-model verification lifecycle (spec to evidence, criterion-traced checkpoints), read-only verifier agents that observe artifacts instead of trusting worker summaries, risk lanes, multi-session ultragoals with a north-star acceptance gate, plus craft skills for writing, visual work, and a paired anti-slop design system for marketing and product UI. Inspired by Garry Tan's gstack specialist sessions, gbrain knowledge patterns, and dwarves-kit closed-loop execution. Works with Claude Code, Antigravity, Cursor, Kiro, Gemini CLI, Codex, and any markdown-reading agent.","author": {"name": "Huy Tieu","url": "https://github.com/huytieu"@@ -27,6 +27,7 @@"daily-brief","team-intelligence","claude-code",+ "antigravity","cursor","kiro","gemini-cli",@@ -305,11 +306,12 @@"progressiveDisclosure": true,"nativeSurfaces": {"claudeCode": 33,+ "antigravity": 33,"kiro": 7,"geminiCli": 7,"agentsMd": 33},- "description": "Self-contained skills with worker delegation and a read-only verification layer, full Claude Code surface, core native Kiro/Gemini surfaces, and AGENTS.md as the universal fallback"+ "description": "Self-contained skills with worker delegation and a read-only verification layer, full Claude Code and Antigravity surfaces, core native Kiro/Gemini surfaces, and AGENTS.md as the universal fallback"}}}diff --git a/.github/MARKETPLACE.md b/.github/MARKETPLACE.mdindex 0dacb3a..fc10371 100644--- a/.github/MARKETPLACE.md+++ b/.github/MARKETPLACE.md@@ -66,7 +66,7 @@ Preferred install flow:```bashgit clone https://github.com/huytieu/COG-second-brain.gitcd COG-second-brain-# Open in Claude Code, Cursor, Kiro, Gemini CLI, Codex, or another AGENTS-compatible agent+# Open in Claude Code, Antigravity, Cursor, Kiro, Gemini CLI, Codex, or another AGENTS-compatible agent```Skills.sh install:diff --git a/CHANGELOG.md b/CHANGELOG.mdindex 45fe3c0..dd2c3fb 100644--- a/CHANGELOG.md+++ b/CHANGELOG.md@@ -2,6 +2,25 @@All notable changes to COG (Cognition + Obsidian + Git) will be documented in this file.+## [3.9.0] - 2026-07-29++### Added++#### Antigravity agent format support+A full native surface for Antigravity (agy CLI + IDE), matching Claude Code's coverage: all 33 skills and all 10 agents (6 workers + 4 verifiers).++- **`.agents/skills/<name>/SKILL.md`** — one pointer stub per skill. Each stub carries the same `name`/`description` frontmatter as its Claude Code counterpart, then delegates: "Read `.claude/skills/<name>/SKILL.md` and execute it exactly as written — that file is the authoritative playbook." `.claude/skills/` stays the single source of truth; the Antigravity surface never forks the playbook content.+- **`.agents/agents/<name>.md`** — one pointer stub per agent, same pattern. Read-only verification gates (`task-verifier`, `integration-verifier`) get accurate, non-templated pointer text rather than the generic worker "Output Rule" line, since they don't write files.+- **`.agents/rules/cog.md`** — the Antigravity operating-policy entry point. Reads `CLAUDE.md` at the repo root and applies it, with explicit substitutions: `.claude/agents/<name>` workers → `.agents/agents/<name>.md` via `invoke_subagent`; the Model Routing table's `sonnet` → `model: flash`.++### Changed+- **Agent Support Matrix** (`README.md`, `docs/AGENT-SUPPORT.md`) now lists Antigravity as a full surface alongside Claude Code and `AGENTS.md`.+- `cog-update.sh` `FRAMEWORK_FILES` gained all 44 `.agents/*` paths, so `/update-cog` keeps the Antigravity surface current going forward.+- Packaging rule 2 in `docs/AGENT-SUPPORT.md` now requires updating the matching Antigravity stub whenever a Claude Code skill changes.++### Known follow-up+- `scripts/validate-agent-surface.sh` does not yet check `.agents/` parity against `.claude/skills/` — drift between the two surfaces would currently go undetected by the validator. Left out of this change to keep it scoped to adding the surface itself.+## [3.8.1] - 2026-07-27### Addeddiff --git a/COG-VERSION b/COG-VERSIONindex f280719..a5c4c76 100644--- a/COG-VERSION+++ b/COG-VERSION@@ -1 +1 @@-3.8.1+3.9.0diff --git a/README.md b/README.mdindex 0ccb505..e993bf6 100644--- a/README.md+++ b/README.md@@ -4,7 +4,7 @@[Quick Start](#quick-start) | [Skills](#skills) | [Features](#features-at-a-glance) | [FAQ](#faq) | [SETUP.md](SETUP.md)-> Works with [Claude Code](https://claude.ai/download) • [Cursor](https://cursor.com/) • [Kiro](https://kiro.dev/) • [Gemini CLI](https://github.com/google-gemini/gemini-cli) • [OpenAI Codex](https://github.com/openai/codex) • any AI that reads markdown+> Works with [Claude Code](https://claude.ai/download) • Antigravity • [Cursor](https://cursor.com/) • [Kiro](https://kiro.dev/) • [Gemini CLI](https://github.com/google-gemini/gemini-cli) • [OpenAI Codex](https://github.com/openai/codex) • any AI that reads markdown>> Inspired by [Garry Tan's gstack](https://github.com/garrytan/gstack) and [gbrain](https://github.com/garrytan/gbrain)@@ -37,6 +37,7 @@ cd COG-second-brain| Agent | Command | How it finds skills ||---|---|---|| Claude Code | `code .` → "Run onboarding" | `.claude/skills/` |+| Antigravity | Open folder → "Run onboarding" | `.agents/skills/` + `.agents/rules/cog.md` || Cursor | Open folder → "Run onboarding" | `.cursor-plugin/` + `.cursorrules` || Kiro | Open folder → "setup COG" | `.kiro/powers/` || Gemini CLI | `gemini` → `/onboarding` | `GEMINI.md` + `.gemini/commands/` |@@ -52,11 +53,12 @@ Done — COG is personalized and ready in ~2 minutes. See [SETUP.md](SETUP.md) f## Agent Support Matrix-COG ships a **full Claude Code surface** plus **core native surfaces** for Kiro and Gemini CLI, with `AGENTS.md` as the universal fallback for Codex and other markdown-reading agents.+COG ships a **full Claude Code surface**, a **full Antigravity surface**, plus **core native surfaces** for Kiro and Gemini CLI, with `AGENTS.md` as the universal fallback for Codex and other markdown-reading agents.| Surface | Current support | Notes ||---|---|---|| Claude Code | 33 native skills + 10 agents (6 workers + 4 verifiers) | Full first-class surface |+| Antigravity | 33 skills + 10 agents (pointer-stub format) | Full surface — thin stubs in `.agents/` delegate to the `.claude/` playbooks, which stay authoritative || Cursor | Plugin manifest + rules | `.cursor-plugin/plugin.json` + `.cursorrules` || Kiro | 7 native powers | Core workflows today || Gemini CLI | 7 native commands | Core workflows today |@@ -231,6 +233,7 @@ COG-second-brain/├── .claude/skills/ # Claude Code skills (33)├── .claude/agents/ # Worker agent definitions (6)├── .claude/roles/ # Role packs (7) — personalized recommendations+├── .agents/ # Antigravity (agy CLI + IDE) — pointer stubs to .claude/├── .kiro/powers/ # Kiro powers├── .gemini/commands/ # Gemini CLI commands├── AGENTS.md # Universal agent docsdiff --git a/cog-update.sh b/cog-update.shindex 5684649..68830a6 100755--- a/cog-update.sh+++ b/cog-update.sh@@ -111,6 +111,52 @@ FRAMEWORK_FILES=(".kiro/powers/cog-url-dump/POWER.md"".kiro/powers/cog-update/POWER.md"+ # Antigravity (agy CLI + IDE)+ ".agents/rules/cog.md"+ ".agents/skills/auto-research/SKILL.md"+ ".agents/skills/braindump/SKILL.md"+ ".agents/skills/closed-loop/SKILL.md"+ ".agents/skills/comprehensive-analysis/SKILL.md"+ ".agents/skills/content-factory/SKILL.md"+ ".agents/skills/create-user-story/SKILL.md"+ ".agents/skills/daily-brief/SKILL.md"+ ".agents/skills/daily-journal/SKILL.md"+ ".agents/skills/data-forms/SKILL.md"+ ".agents/skills/editorial-illustrations/SKILL.md"+ ".agents/skills/export-open-issues/SKILL.md"+ ".agents/skills/generate-prd/SKILL.md"+ ".agents/skills/generate-release-notes/SKILL.md"+ ".agents/skills/harvest/SKILL.md"+ ".agents/skills/knowledge-consolidation/SKILL.md"+ ".agents/skills/loop-engineering/SKILL.md"+ ".agents/skills/meeting-transcript/SKILL.md"+ ".agents/skills/memory-hygiene/SKILL.md"+ ".agents/skills/museum-art/SKILL.md"+ ".agents/skills/no-ai-slop/SKILL.md"+ ".agents/skills/onboarding/SKILL.md"+ ".agents/skills/product-ui-taste/SKILL.md"+ ".agents/skills/publish-to-confluence/SKILL.md"+ ".agents/skills/retro/SKILL.md"+ ".agents/skills/review-cockpit/SKILL.md"+ ".agents/skills/scout/SKILL.md"+ ".agents/skills/taste-skill/SKILL.md"+ ".agents/skills/team-brief/SKILL.md"+ ".agents/skills/ultragoal/SKILL.md"+ ".agents/skills/update-cog/SKILL.md"+ ".agents/skills/update-knowledge-base/SKILL.md"+ ".agents/skills/url-dump/SKILL.md"+ ".agents/skills/weekly-checkin/SKILL.md"+ ".agents/agents/brief-people-updater.md"+ ".agents/agents/worker-data-collector.md"+ ".agents/agents/worker-executor.md"+ ".agents/agents/worker-file-ops.md"+ ".agents/agents/worker-publisher.md"+ ".agents/agents/worker-researcher.md"+ ".agents/agents/task-verifier.md"+ ".agents/agents/integration-verifier.md"+ ".agents/agents/fix-agent.md"+ ".agents/agents/harvest-curator.md"+# Gemini CLI".gemini/commands/onboarding.toml"".gemini/commands/braindump.toml"diff --git a/docs/AGENT-SUPPORT.md b/docs/AGENT-SUPPORT.mdindex 130d3c6..3762ccc 100644--- a/docs/AGENT-SUPPORT.md+++ b/docs/AGENT-SUPPORT.md@@ -9,6 +9,7 @@ This document is the packaging contract: it tells contributors and maintainers w| Surface | Shipped format | Coverage | Status ||---|---|---:|---|| Claude Code | `.claude/skills/*/SKILL.md` | 33 skills | Full native surface |+| Antigravity | `.agents/skills/*/SKILL.md` + `.agents/agents/*.md` | 33 skills + 10 agents | Full surface (pointer-stub format — delegates to `.claude/`, which stays authoritative) || Universal agent docs | `AGENTS.md` | 17 commands | Full documented fallback || Kiro | `.kiro/powers/*/POWER.md` | 7 powers | Core workflows only || Gemini CLI | `.gemini/commands/*.toml` + `.gemini/skills/*.md` | 7 commands | Core workflows only |@@ -35,7 +36,7 @@ These surfaces should expose the complete public COG command set:- `publish-to-confluence`- `update-knowledge-base`-Today, **Claude Code** and **`AGENTS.md`** are the full surfaces.+Today, **Claude Code**, **Antigravity**, and **`AGENTS.md`** are the full surfaces.### Core surfacesThese surfaces intentionally cover the most common personal workflows first:@@ -54,12 +55,13 @@ Today, **Kiro** and **Gemini CLI** are core surfaces.If you add, remove, rename, or materially change a public COG skill:1. Update the **Claude skill** in `.claude/skills/`-2. Update **`AGENTS.md`** for the universal surface-3. Update **`.claude-plugin/plugin.json`** so marketplace metadata stays truthful-4. Update **README / SETUP / this file** if counts or support levels change-5. If the skill is supported natively in Kiro or Gemini, update those files too-6. Add new framework files to `FRAMEWORK_FILES` in `cog-update.sh`-7. Run `./scripts/validate-agent-surface.sh`+2. Update the matching **Antigravity pointer stub** in `.agents/skills/<name>/SKILL.md` (same template as the existing stubs — `name` + `description` only change, the body always points back at `.claude/skills/<name>/SKILL.md` as authoritative)+3. Update **`AGENTS.md`** for the universal surface+4. Update **`.claude-plugin/plugin.json`** so marketplace metadata stays truthful+5. Update **README / SETUP / this file** if counts or support levels change+6. If the skill is supported natively in Kiro or Gemini, update those files too+7. Add new framework files to `FRAMEWORK_FILES` in `cog-update.sh`+8. Run `./scripts/validate-agent-surface.sh`## Validationdiff --git a/marketplace-entry.json b/marketplace-entry.jsonindex cea047c..fe4b9f8 100644--- a/marketplace-entry.json+++ b/marketplace-entry.json@@ -6,8 +6,8 @@"email": "[email protected]","url": "https://github.com/huytieu"},- "description": "Self-evolving second brain with 33 AI skills, 10 agents, and people CRM. Closed-loop harness release: V-model verification lifecycle with criterion-traced evidence, read-only verifier agents, risk lanes, multi-session ultragoals with a north-star acceptance gate, craft skills for writing and visuals, and paired anti-slop design skills for marketing and product UI. Inspired by Garry Tan's gstack and gbrain, and dwarves-kit. Works with Claude Code, Cursor, Kiro, Gemini CLI, Codex.",- "version": "3.8.1",+ "description": "Self-evolving second brain with 33 AI skills, 10 agents, and people CRM. Closed-loop harness release: V-model verification lifecycle with criterion-traced evidence, read-only verifier agents, risk lanes, multi-session ultragoals with a north-star acceptance gate, craft skills for writing and visuals, and paired anti-slop design skills for marketing and product UI. Inspired by Garry Tan's gstack and gbrain, and dwarves-kit. Works with Claude Code, Antigravity, Cursor, Kiro, Gemini CLI, Codex.",+ "version": "3.9.0","keywords": ["second-brain","garry-tan",@@ -16,6 +16,7 @@"ai-agents","obsidian","claude-code",+ "antigravity","cursor","worker-agents","people-crm",