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 skills/poteto/brainmaxxing/brainnpx skills add poteto/brainmaxxing --skill braingit clone --depth 1 https://github.com/poteto/brainmaxxingWhat 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 | $0.00043 | $0.00583 |
| Opus 5 | $0.00022 | $0.00292 |
| Sonnet 5 | $0.00009 | $0.00117 |
| Haiku 4.5 | $0.00004 | $0.00058 |
Grade A, and why
brain 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 2d 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.
How it starts
The opening of the file, as written. The whole thing — 68 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Brain
Persistent memory across sessions. Obsidian vault at brain/.
The brain is the foundation of the entire workflow — every agent, skill, and session reads it. Low-quality or speculative content degrades everything downstream. Before adding anything, ask: "Does this genuinely improve how the system operates?" If the answer isn't a clear yes, don't write it.
Before Writing
Read brain/index.md first. Then read the relevant entrypoint for your topic:
brain/principles.mdfor principle updates
For directories without a dedicated index file yet, scan nearby files directly and edit an existing note when possible.
Structure
brain/
├── index.md <- root entry point, links to everything
├── principles.md <- index for principles/
├── principles/ <- engineering and design principles
├── codebase/ <- project-specific knowledge and gotchas
└── plans/ <- feature plans
Rules:
- One topic per file.
brain/codebase/deploy-gotchas.md, not a mega-file. - Maintain existing index entrypoints:
brain/index.md,brain/principles.md. - If you introduce a new top-level category, add an index-style entrypoint for it (links only, no inlined content).
brain/index.mdis the root. Every brain file must be reachable from it.- File names: lowercase, hyphenated.
worktree-gotchas.md.
Wikilinks
Format: [[section/file-name]]. Resolution order: same directory, then relative path, then vault root. Heading anchors ([[file#heading]]) are stripped during resolution.
Writing Style
- Bullets over prose. No preamble.
- Plain markdown with
# Title. No Obsidian frontmatter. - Keep notes under ~50 lines. Split if longer.
After Writing
Update brain/index.md for any files you added or removed. Also update the relevant entrypoint when applicable. Keep indexes link-only and scannable.
Durability Test
Ask: "Would I include this in a prompt for a different task?"
- Yes -> write to
brain/. It's durable knowledge. - No, it's plan-specific -> update the plan's docs instead.
- No, it's a skill issue -> update the skill file directly.
- No, it needs follow-up work -> file a todo.
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.
- 2d ago First seen · 68 lines · 43 tokens per session scan A e8235f569404
brain is a skill published in the GitHub repository poteto/brainmaxxing (269 stars, last pushed 6mo ago), licensed MIT. It adds 43 tokens to every session and 583 once invoked, about $0.0002 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
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
babysit-pr
Babysit a GitHub pull request after creation by continuously polling review comments, CI checks/workflow runs, and mergeability state until the PR is merged/closed or user help is required. Diagnose failures, retry likely flaky failures up to 3 times, auto-fix/push branch-related issues when appropriate, and keep…
imagegen
Generate or edit raster images when the task benefits from AI-created bitmap visuals such as photos, illustrations, textures, sprites, mockups, or transparent-background cutouts. Use when Codex should create a brand-new image, transform an existing image, or derive visual variants from references, and the output…
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…