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 auto-researchgit 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/auto-research)<a href="https://agentmods.dev/skills/huytieu/cog-second-brain/auto-research"><img src="https://agentmods.dev/badge/skills/huytieu/cog-second-brain/auto-research/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/huytieu/cog-second-brain/auto-research"><img src="https://agentmods.dev/badge/skills/huytieu/cog-second-brain/auto-research.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium Agent Snooping · line 6 Skill enumerates or reads other installed skills. Access to other skills' SKILL.md files or the skills directory reveals prompt instructions, capabilities, and secrets that should be invisible to peer skills.Fix: Remove all code or instructions that list or read other skills' files or directories. Skills should operate independently; cross-skill access is a privilege escalation.
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 | $0.00029 | $0.00117 |
| Opus 5 | $0.00015 | $0.00059 |
| Sonnet 5 | $0.00006 | $0.00023 |
| Haiku 4.5 | $0.00003 | $0.00012 |
Grade A, and why
auto-research 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 9d 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.
What it actually says
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.
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.
- 9d ago First seen · 11 lines · 29 tokens per session scan A 963070e90e6f
auto-research is a skill published in the GitHub repository huytieu/COG-second-brain (1,178 stars, last pushed 14d ago), licensed MIT. It adds 29 tokens to every session and 117 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
vfx-text-cursor
A video or hero-frame effect where a cursor reveals a sentence character by character with coloured trails, light streaks, and a final shimmer.
api-testing
API testing patterns for Playwright -- apiRequest fixture usage, Zod response schema creation and validation, test.step wrapping for multi-call tests, per-field negative/validation testing, path parameter fuzzing, and helper fixtures for shared setup/teardown. Use when writing or updating API test specs, adding tests…
debugging
Playwright test debugging conventions for the scaffold — reading failure messages, classifying failure modes (TimeoutError, ZodError, strict-mode violation, locator not found, network errors, schema drift), the playwright.config.ts capture defaults (trace on-first-retry, screenshot only-on-failure, video…
pr-reviewer
Reviews a Git branch as a pull request against the base branch (auto-resolved from origin/HEAD — usually main or master) using this repo's own rules — the CLAUDE.md constitution and the .claude/skills/ that apply to the changed files. Fetches the branch, switches to it, diffs it against the merge-base, routes the…
ai-native-workflow
Sole entry-point router for AI-assisted work on this Playwright scaffold — owns the 8-phase main workflow (classify → route → explore → plan+confidence → human gate → apply → verify → report), the human↔agent conversation contract, the routing matrix that picks the right specialized skill, and the confidence-gate…
data-strategy
Test data strategy for the Playwright scaffold — Faker + Zod factories for dynamic happy-path data, static TS files (.ts with as const exports — never .json) for domain-specific curated invalid sets, and the universal type-mismatch arrays in test-data/static/util/invalid-values.ts. Use when creating or editing a data…