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 skills add huytieu/COG-second-brain --skill url-dumpgit 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/skills/huytieu/cog-second-brain/url-dump)<a href="https://agentmods.dev/skills/huytieu/cog-second-brain/url-dump"><img src="https://agentmods.dev/badge/skills/huytieu/cog-second-brain/url-dump.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 5.1 | $0.00021 | $0.00108 |
| Opus 5 | $0.00010 | $0.00054 |
| Sonnet 5 | $0.00004 | $0.00022 |
| Haiku 4.5 | $0.00002 | $0.00011 |
Grade A, and why
url-dump scanned grade A with 0 findings 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 8d 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.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
This is a copy
80% identical to auto-research — 6 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
What it actually says
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.
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.
- 8d ago First seen · 11 lines · 21 tokens per session scan A 90456e080d1b
url-dump is a skill published in the GitHub repository huytieu/COG-second-brain (1,175 stars, last pushed 13d ago), licensed MIT. It adds 21 tokens to every session and 108 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it A with 0 findings. It is 80% identical to auto-research, differing in 6 lines, and is treated as a copy.
Other skills, from other repositories
memory
Persistent memory system for the agent. Two-tier storage: user (/.agents/memory/MEMORY.md) and project ( /MEMORY.md). Five memory networks: experiences, world knowledge, beliefs, reflections, entity summaries. Task closure ("we're done", etc.) triggers a mandatory task-done memory sweep (remember subagents per…
llm-wiki
Karpathy's LLM Wiki: build/query interlinked markdown KB.
task-agent-eliza-bridge
Use when spawning a Claude Code, Codex, Gemini, Aider, or other CLI task agent whose work needs parent Eliza runtime context. Covers the read-only loopback bridge for character, room, memory, and active workspace state.
kb-builder
Build an Obsidian-compatible knowledge base from public web sources using the TinyFish CLI. Use this skill when a user wants a builder-grade markdown knowledge base on a technical topic, asks for a structured research vault, or wants a topic compiled from live public sources into interlinked markdown files. Supports…
karpathy-llm-wiki
Use when building or maintaining a personal LLM-powered knowledge base. Triggers: ingesting sources into a wiki, querying wiki knowledge, linting wiki quality, 'add to wiki', 'what do I know about', or any mention of 'LLM wiki' or 'Karpathy wiki'.
10-learn
Capture durable project learnings. Use when the user wants to remember, record, or formalize a decision, convention, lesson, pitfall, reusable workflow, or review finding. Not for preferences or temporary notes.