Skip to content

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.

style: drop em-dashes from v3.10.0 prose; align plugin.json surface list

Huy Tieu4c9c1ebe0b70
diff --git a/CHANGELOG.md b/CHANGELOG.md
index 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.md
index 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.json
index 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]",