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
style: drop em-dashes from v3.10.0 prose; align plugin.json surface list
Huy Tieu4c9c1ebe0b70
diff --git a/CHANGELOG.md b/CHANGELOG.mdindex d79c67c..92b75be 100644--- a/CHANGELOG.md+++ b/CHANGELOG.md@@ -7,10 +7,10 @@ All notable changes to COG (Cognition + Obsidian + Git) will be documented in th### Added#### Agent Plugins standard adoption-COG now conforms to the [Agent Plugins specification 1.0.0](https://agent-plugins.org) — the open, vendor-neutral plugin format governed by a Technical Steering Committee with representatives from Amazon, Cursor, Microsoft, OpenAI, and Vercel. Any standard-conformant client can load COG as a plugin directly from a checkout.+COG now conforms to the [Agent Plugins specification 1.0.0](https://agent-plugins.org), the open, vendor-neutral plugin format governed by a Technical Steering Committee with representatives from Amazon, Cursor, Microsoft, OpenAI, and Vercel. Any standard-conformant client can load COG as a plugin directly from a checkout.- **`plugin.json`** at the repo root: the standard manifest, validated against the published 1.0.0 schema.-- **`skills/`** at the repo root: generated mirror of `.claude/skills/` (the spec's fixed skill location; skills follow the [Agent Skills](https://agentskills.io) format). `.claude/skills/` stays canonical — regenerate with `./scripts/build-agent-plugin.sh`, never edit `skills/` by hand.+- **`skills/`** at the repo root: generated mirror of `.claude/skills/` (the spec's fixed skill location; skills follow the [Agent Skills](https://agentskills.io) format). `.claude/skills/` stays canonical: regenerate with `./scripts/build-agent-plugin.sh`, never edit `skills/` by hand.- **`scripts/build-agent-plugin.sh`**: one-command mirror rebuild, wired into `cog-update.sh` so framework updates regenerate the surface automatically.- **Validator coverage**: `validate-agent-surface.sh` now checks the manifest declares the 1.0.0 schema, the mirror matches `.claude/skills/` exactly, and the version is aligned across all four packaging manifests.diff --git a/README.md b/README.mdindex 4893625..97180c1 100644--- a/README.md+++ b/README.md@@ -59,7 +59,7 @@ COG ships a **full Claude Code surface**, a **full Antigravity surface**, plus *|---|---|---|| 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 |-| [Agent Plugins](https://agent-plugins.org) standard | Root `plugin.json` + `skills/` (33 skills) | Spec 1.0.0 conformant — any standard-aware client loads COG as a plugin |+| [Agent Plugins](https://agent-plugins.org) standard | Root `plugin.json` + `skills/` (33 skills) | Spec 1.0.0 conformant; any standard-aware client loads COG as a plugin || Cursor | Plugin manifest + rules | `.cursor-plugin/plugin.json` + `.cursorrules` || Kiro | 7 native powers | Core workflows today || Gemini CLI | 7 native commands | Core workflows today |diff --git a/plugin.json b/plugin.jsonindex 6b327dd..4f87822 100644--- a/plugin.json+++ b/plugin.json@@ -2,7 +2,7 @@"$schema": "https://agent-plugins.org/schemas/1.0.0/plugin.schema.json","name": "cog-second-brain","version": "3.10.0",- "description": "Self-evolving second brain with 33 AI agent skills, 10 agents, and people CRM. Closed-loop harness: 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. Works with Claude Code, Cursor, Kiro, Gemini CLI, Codex, and any Agent Plugins conformant client.",+ "description": "Self-evolving second brain with 33 AI agent skills, 10 agents, and people CRM. Closed-loop harness: 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. Works with Claude Code, Antigravity, Cursor, Kiro, Gemini CLI, Codex, and any Agent Plugins conformant client.","author": {"name": "Huy Tieu","email": "[email protected]",