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 v0lka/skills --skill vibe-braingit clone --depth 1 https://github.com/v0lka/skillsWrote 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/v0lka/skills/vibe-brain)<a href="https://agentmods.dev/skills/v0lka/skills/vibe-brain"><img src="https://agentmods.dev/badge/skills/v0lka/skills/vibe-brain/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/v0lka/skills/vibe-brain"><img src="https://agentmods.dev/badge/skills/v0lka/skills/vibe-brain.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00067 | $0.02331 |
| Opus 5 | $0.00034 | $0.01166 |
| Sonnet 5 | $0.00013 | $0.00466 |
| Haiku 4.5 | $0.00007 | $0.00233 |
Grade A, and why
vibe-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 10d 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 — 193 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Vibe Brain — Task Prioritizer
When invoked, do a thorough four-phase analysis and return exactly ONE task: the most impactful thing to do right now, explained conversationally.
Trigger phrases
Invoke this skill when the user says any of:
- "Hey, what are we going to do today, Brain?"
- "What should I work on?"
- "What's next?"
- "What's the top priority?"
- "Pick a task for me"
- Any variant asking for task selection or prioritization
Phase 1: Gather context
Do all of the following in parallel where possible. You are gathering raw material, not analyzing yet.
1.1 Project structure
- List the top-level directory tree (
ls -la,tree -L 2if available) - Read package manifests:
package.json,Cargo.toml,go.mod,pyproject.toml,Makefile, etc. - Identify the tech stack, build system, and test runner
1.2 Codebase scan
- Search for TODO, FIXME, HACK, XXX markers across the codebase
- Search for
@deprecated,DEPRECATED,BROKENannotations - Check for skipped tests:
it.skip,test.skip,xtest,#[ignore],t.Skip,pytest.mark.skip - Look for empty catch blocks,
// eslint-disable,# type: ignore,noqa— signs of deferred cleanup - Find files with high churn (recent git history):
git log --oneline --since="2 weeks ago" --name-only
1.3 Documentation
- Read
README.md,AGENTS.md,SECURITY.md,CONTRIBUTING.md,DEVELOPMENT.md,ARCHITECTURE.md, etc - Read any
docs/or project-level specs, ADRs, or decision logs - Read open issues if an issue tracker is referenced
1.4 Memory and knowledge
- Call memory retrieval for project-related memories (project introduction, tech stack, conventions, lessons learned)
- Retrieve knowledge modules from the codebase if available
Phase 2: Extract candidates
From the gathered context, build a mental list of candidate tasks. Look for:
| Signal | What it means |
|---|---|
| TODO / FIXME | Explicitly deferred work — the developer already knew it needed doing |
| Skipped test | A test that was disabled but not deleted — likely a known bug or incomplete feature |
| Empty error handler | Swallowed errors hiding real problems |
| High-churn file | Volatile code — may be unstable, under active development, or poorly designed |
| Missing tests | Untested critical paths — high risk |
| Documentation gap | Docs that reference non-existent files, outdated commands, or missing sections |
| Recent unfinished commit | A commit message like "WIP", "tmp", "checkpoint" — interrupted work |
| Open TODO in roadmap | Planned work from specs/roadmap that hasn't been started |
| Dependency warning | Deprecated APIs, security advisories, pinned outdated versions |
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 10d ago First seen · 193 lines · 67 tokens per session scan A d0b1ea36fd96
vibe-brain is a skill published in the GitHub repository v0lka/skills (18 stars, last pushed 1mo ago), licensed MIT. It adds 67 tokens to every session and 2,331 once invoked, about $0.0003 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
syndic
Gère un parc de copropriétés en France avec vue portfolio consolidée. Couvre administration, comptabilité (décret 2005, plan comptable copro, 5 annexes), assemblées générales (convocation, PV, notification), appels de fonds, travaux, fournisseurs, recouvrement d'impayés et transition de syndic. Maîtrise les majorités…
template-instantiation
Creates .NET projects from templates with validated parameters, smart defaults, Central Package Management adaptation, and latest NuGet version resolution. USE FOR: creating new dotnet projects, scaffolding solutions with multiple projects, installing or uninstalling template packages, creating projects that respect…
note-improvement
Capture an out-of-scope improvement opportunity so it doesn't get lost. Use when the user asks to "note improvement", "save improvement", "track this for later", "remember this improvement", "note this idea", "log improvement", "backlog this", or "park this idea". Also invoke proactively when noticing something…
Product Strategy
A comprehensive skill for product strategy — covering frameworks, opportunity sizing, prioritization, roadmap building, OKRs, and stakeholder management. From early-stage discovery to mature product org execution.
handover-admin
Generate comprehensive admin documentation for AEM Edge Delivery Services project handover. Use when handing over admin responsibilities, onboarding a new site administrator, or documenting admin procedures — e.g., "admin guide", "admin documentation", "admin handover".
to-issues
A planning aid that breaks a PRD or technical specification into small implementation issues, each covering a complete, demonstrable piece of work.