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.
git clone --depth 1 https://github.com/timurgaleev/vibestackWrote 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/rules/timurgaleev/vibestack/skills)<a href="https://agentmods.dev/rules/timurgaleev/vibestack/skills"><img src="https://agentmods.dev/badge/rules/timurgaleev/vibestack/skills/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/rules/timurgaleev/vibestack/skills"><img src="https://agentmods.dev/badge/rules/timurgaleev/vibestack/skills.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 | $0.00817 | $0.00817 |
| Opus 5 | $0.00409 | $0.00409 |
| Sonnet 5 | $0.00163 | $0.00163 |
| Haiku 4.5 | $0.00082 | $0.00082 |
Grade A, and why
skills 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 yesterday.
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 — 69 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Skill Routing
These are vibestack skills — slash commands that carry a full workflow. When a task matches one, prefer the skill over improvising: invoke it before starting the work.
Availability: If a skill below is installed, use it. If it isn't present on this machine, proceed normally — these are suggestions, not hard dependencies.
Ordering: Process skills come first. Brainstorm or plan before implementing; investigate before fixing. Then run the implementation and review skills.
Task → skill
| When the task is… | Use |
|---|---|
| Plan a feature, refactor, or architecture change | /plan-eng-review, /autoplan |
| Weigh product scope or the bigger problem | /plan-ceo-review |
| Turn a rough intent into a precise spec | /spec |
| Implement a feature or bugfix with tests | /tdd |
| Debug an error, test failure, or odd behavior | /investigate |
| Review a diff before merge | /code-review, /review |
| Tidy code for reuse/simplicity (no bug hunt) | /simplify |
| Audit security | /cso |
| QA a running web app | /qa (fixes), /qa-only (report) |
| Verify a change actually works end to end | /verify |
| Ship: commit, PR, version, changelog | /ship |
| Merge, deploy, and confirm production health | /land-and-deploy |
| Update docs after shipping | /document-release, /document-generate |
| Review a UI/visual change | /design-review, /plan-design-review |
| Save or restore working context across sessions | /context-save, /context-restore |
| Record or review a session learning | /learn |
| Check code-quality health or find refactors | /health, /improve-arch |
Second opinion from another model
The deliberation plugin delegates
a question to GPT, Gemini, Grok or an OpenRouter model. It is optional
(install.sh -D); where it is absent, carry on without it.
| When the task is… | Use |
|---|---|
| Review a diff with a pass/fail gate | /codex review |
| Put one question to several models at once | /deliberation:ask-all |
| Settle a contested design decision | /deliberation:consensus |
| Ask one named model | /deliberation:ask-gpt, :ask-gemini, :ask-grok, :ask-openrouter |
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.
- yesterday First seen · 69 lines · 817 tokens per session scan A 8f8067236e3f
skills is a cursor rule published in the GitHub repository timurgaleev/vibestack (6 stars, last pushed yesterday), licensed MIT. It adds 817 tokens to every session, about $0.0041 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 2026-09-19.
Other cursor rules, from other repositories
tech-writer
Guide the AI to act as a Senior Technical Writer, focusing on clear and concise documentation.
ai-expert
Guide the AI to act as an AI/ML/MLOps Expert, integrating modern AI tooling, including AI agents, AI-powered IDEs, MCP servers, and online AI-powered tools.
back-end-dev
Guide the AI to act as a Senior Back-End Developer, focusing on modern back-end languages and frameworks.
product-owner
Guide the AI to act as a Senior Product Owner with strong UI/UX design capabilities, focusing on user-centric product development.
devops
Guide the AI to act as a Modern DevOps Engineer, specializing in AWS, Azure, and Google Cloud Platform.
architect
Guide the AI to act as a Software Architect, focusing on system design and scalability.