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 ohad6k/VibeRaven --skill architecture-contextgit clone --depth 1 https://github.com/ohad6k/VibeRavenWrote 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/ohad6k/viberaven/architecture-context)<a href="https://agentmods.dev/skills/ohad6k/viberaven/architecture-context"><img src="https://agentmods.dev/badge/skills/ohad6k/viberaven/architecture-context/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/ohad6k/viberaven/architecture-context"><img src="https://agentmods.dev/badge/skills/ohad6k/viberaven/architecture-context.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 | $0.00048 | $0.01397 |
| Opus 5 | $0.00024 | $0.00698 |
| Sonnet 5 | $0.00010 | $0.00279 |
| Haiku 4.5 | $0.00005 | $0.00140 |
Grade A, and why
architecture-context 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.
How it starts
The opening of the file, as written. The whole thing — 149 lines — stays where its author put it; the contents beside it link to each section on GitHub.
VibeRaven: Architecture Context
Make the agent behave like a senior product engineer before it edits.
Hard Rule
For vague work like "build uploads", "add billing", "fix login", "make chat", or "connect Supabase": ask architecture questions first. Do not answer only "loaded".
No plan, no edits. On the turn after the user answers the questions, route to architecture-plan. That skill must produce Architecture plan: before any file writes, migrations, API changes, UI edits, commits, or final implementation summary.
Loop
product path -> questions -> architecture-plan -> route -> edit/hand off
- Name the user path.
- Ask 3-6 low-level product questions the user can answer without architecture vocabulary.
- Compare practical options.
- Recommend one architecture and why.
- Use repo, Studio, or provider MCP evidence when available for existing boundaries.
- Route answered questions to
architecture-plan. - Use
architecture-planto create the full Architecture Plan before editing. This is a hard gate. - Edit only after the plan exists and is visible in chat.
When the output names Next skill:, continue with that VibeRaven skill unless user input is required.
Continuation Turn
If the latest user message answers the numbered product questions, treat it as the answer turn even if it does not mention this skill by name. Do not restart Question Mode unless a required answer is missing.
On the answer turn:
- Run only read-only repo evidence commands if needed.
- Invoke or follow
architecture-plan; do not continue inside this skill. - The next output must start with
Architecture plan:and include workstreams, implementation sequence, risks, verification, provider/MCP proof, andNext skill:. - Only then edit, if the user asked for implementation.
If the response would start with "Implemented", "Changed", "Verification", "Done", or a file list, stop and write the Architecture Plan instead.
Question Mode
Ask low-level questions. Do not ask the user to classify "boundary", "runtime", "RLS", "source of truth", or "production invariant". Translate answers later.
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.
- 9d ago First seen · 149 lines · 48 tokens per session scan A bd425d0b138d
architecture-context is a skill published in the GitHub repository ohad6k/VibeRaven (38 stars, last pushed 1mo ago), licensed MIT. It adds 48 tokens to every session and 1,397 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
fullstack-ai-app-builder
A method for building and launching complete AI-powered web applications, from requirements and technical planning through the front end, back end, AI integration, and deployment. It is aimed at people who want to create an application without a back-end engineer.
data-charts-tako
Search and visualize the world's data - get charts, insights, and embeddable knowledge cards for finance, economics, demographics, sports, and more.
apollo-lead-finder
Two-phase Apollo.io prospecting: free People Search to discover ICP-matching leads, then selective enrichment to reveal emails/phones (credits per contact). Creates Apollo lists. Deduplicates against existing contacts by LinkedIn URL.
monorepo-management
Master monorepo management with Turborepo, Nx, and pnpm workspaces to build efficient, scalable multi-package repositories with optimized builds and dependency management. Use when setting up monorepos, optimizing builds, or managing shared dependencies.
browse-and-evaluate
Use when exploring the ai-agent-skills catalog to find, compare, and evaluate skills before installing. Always use --fields to limit output size and --dry-run before committing to an install.
render-3d-product-showcase
Assemble a premium 3D product-showcase ad from a config — four beat clips (an orbiting hero rotation, a macro push-in, a physics reveal, a typographic close) normalized to the brand-color canvas, hard-concatenated in order, closed on a deterministic Playwright brand end card, and mixed under one instrumental bed at…