COG is an AI-assisted second brain that stores knowledge in Markdown files and uses agents, skills, and version control to evolve it over time. It helps people manage knowledge and contacts while supporting several coding-agent tools; the catalogue entries are COG’s skills, agents, instructions, rules, and plugin surfaces.
Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx agentmods add instructions/huytieu/cog-second-brain/agents-mdgit clone --depth 1 https://github.com/huytieu/COG-second-brainWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/instructions/huytieu/cog-second-brain/agents-md)<a href="https://agentmods.dev/instructions/huytieu/cog-second-brain/agents-md"><img src="https://agentmods.dev/badge/instructions/huytieu/cog-second-brain/agents-md.svg" alt="Measured on agentmods" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5 | $0.11064 | $0.11064 |
| Opus 5 | $0.05532 | $0.05532 |
| Sonnet 5 | $0.02213 | $0.02213 |
| Haiku 4.5 | $0.01106 | $0.01106 |
Grade A, and why
COG-second-brain AGENTS.md scanned grade A with 1 finding against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 5d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
2. Classifies claims: environment-dependent (verify with `ls`/`curl`/`gh`) vs preference/judgment (check only for contradiction with newer entries) How it starts
The opening of the file, as written. The whole thing — 1,040 lines — stays where its author put it; the contents beside it link to each section on GitHub.
COG: Agentic Second Brain - Universal Agent Commands
This document defines the available commands/skills for AI agents interacting with COG (Cognition + Obsidian + Git) - a self-evolving agentic second brain system.
Compatible with: OpenAI agents, Claude (via this file), and any AI that reads markdown.
Note: Claude Code users should use
.claude/skills/and Kiro users should use.kiro/powers/for native support. This file serves as universal documentation for all other agents.
Available Commands
/onboarding
Description: Personalize COG for your workflow - creates profile, interests, and watchlist files with a smart, conversational setup.
Triggers:
/onboarding- "onboarding"
- "setup COG"
- "setup my profile"
- "get started"
Purpose: Welcome new users and collect essential information to personalize their COG experience through natural conversation - not sequential form-filling. Creates profile documents stored as markdown files within the vault.
How it works:
- Asks ONE open-ended question: "Tell me about yourself - name, role, and what you're interested in"
- Intelligently parses the response to extract name, role, interests, projects, news sources, and competitive watchlist
- Only asks a follow-up if required info (name, role, interests) is still missing
- Asks about agent mode preference (solo vs team) during confirmation
- Confirms extracted info before creating files
- Matches role to a role pack (
.claude/roles/*.md) for personalized skill and integration recommendations - Discovers integrations — presents role-specific recommendations, asks which tools the user already uses
- Creates
00-inbox/MY-PROFILE.mdwith role_pack, agent_mode, and preferences - Creates
00-inbox/MY-INTERESTS.mdwith topics for daily briefs - Creates
00-inbox/MY-INTEGRATIONS.mdwith active/disabled integrations - Optionally creates project structures in
04-projects/and03-professional/COMPETITIVE-WATCHLIST.md(only if mentioned) - Generates a welcome guide with role-ordered skills and integration status
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 5d ago First seen · 1,040 lines · 11,064 tokens per session scan A 9c1afc2a88ff
COG-second-brain AGENTS.md is an instructions file published in the GitHub repository huytieu/COG-second-brain (1,162 stars, last pushed 10d ago), licensed MIT. It adds 11,064 tokens to every session, about $0.0553 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other instructions, from other repositories
framework AGENTS.md
AGENTS.md instructions for ai-driven-dev/framework, covering agents.md, behavior, communication, action and memory management.
agentic-playwright data-strategy.instructions.md
Instructions for idavidov13/agentic-playwright, covering data strategy, critical, file locations, instructions and phase 1: classify the value you need.
agentic-playwright config.instructions.md
Instructions for idavidov13/agentic-playwright, covering configuration, critical, file locations, instructions and phase 1: understand how env files are loaded.
agentic-playwright enums.instructions.md
Instructions for idavidov13/agentic-playwright, covering enums, critical, file locations, instructions and phase 1: decide if the value belongs in an enum.
repo-context-mcp AGENTS.md
Instructions for nduc99911/repo-context-mcp, covering agents.md — repo-context-mcp, project, layout, commands and conventions.
brain-os AGENTS.md
Instructions for brainOS-HQ/brain-os, covering agents.md, context, the hard rule, tool routing (in order) and mutation safety.