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 mracal/vibe-engineering --skill vibe-start-informedgit clone --depth 1 https://github.com/mracal/vibe-engineeringWrote 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/mracal/vibe-engineering/vibe-start-informed)<a href="https://agentmods.dev/skills/mracal/vibe-engineering/vibe-start-informed"><img src="https://agentmods.dev/badge/skills/mracal/vibe-engineering/vibe-start-informed/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/mracal/vibe-engineering/vibe-start-informed"><img src="https://agentmods.dev/badge/skills/mracal/vibe-engineering/vibe-start-informed.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 | $0.00045 | $0.00682 |
| Opus 5 | $0.00023 | $0.00341 |
| Sonnet 5 | $0.00009 | $0.00136 |
| Haiku 4.5 | $0.00005 | $0.00068 |
Grade A, and why
vibe-start-informed 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.
This is a copy
91% identical to vibe-start-informed — 7 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
How it starts
The opening of the file, as written. The whole thing — 70 lines — stays where its author put it; the contents beside it link to each section on GitHub.
vibe-start-informed
Other people's documented failures count as observed failure. Research SOTA before proposing anything.
When to Use
- Brainstorming new features or capabilities
- Designing architecture for a new sub-system
- Choosing between technology approaches
- Any creative/design task where multiple valid approaches exist
Not for: Implementing already-designed specs, bug fixes, or tasks with clear requirements.
The Rule
BEFORE proposing any approach, dispatch a research agent to find real papers, real projects, and real production systems that solve the same (or adjacent) problem.
digraph start_informed {
"Design question identified" [shape=doublecircle];
"Decompose into sub-problems" [shape=box];
"Dispatch research agent (WebSearch)" [shape=box];
"For each sub-problem find:" [shape=box];
"Synthesize imported failures" [shape=box];
"NOW propose approaches" [shape=doublecircle];
"Design question identified" -> "Decompose into sub-problems";
"Decompose into sub-problems" -> "Dispatch research agent (WebSearch)";
"Dispatch research agent (WebSearch)" -> "For each sub-problem find:";
"For each sub-problem find:" -> "Synthesize imported failures";
"Synthesize imported failures" -> "NOW propose approaches";
}
Research Requirements
For each sub-problem, find:
| Requirement | Minimum | Example |
|---|---|---|
| Named projects | 2+ with stars/adoption | "Graphiti (23k stars)" |
| Papers with venue | 1+ with year | "RAPTOR (ICLR 2024)" |
| Mechanism described | What it actually does | Not marketing copy |
| Known failures | What went wrong | "Flat RAG failed at multi-hop" |
| Applicability assessment | How it maps to our system | Specific, not generic |
Red Flags
| Thought | Reality |
|---|---|
| "I already know the best approach" | You know ONE approach. Research finds others. |
| "This is too niche for research" | If someone built it, someone documented failures. |
| "Research will slow us down" | Uninformed design causes rewrites. Research prevents them. |
| "The textbook answer is obvious" | JK: "These are very very weak suggestions." Do real research. |
| "Let me just propose something" | Proposals without research are guesses with confidence. |
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 · 70 lines · 45 tokens per session scan A afb1f7e16a88
vibe-start-informed is a skill published in the GitHub repository mracal/vibe-engineering (3 stars, last pushed today), licensed MIT. It adds 45 tokens to every session and 682 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 0 findings. It is 91% identical to vibe-start-informed, differing in 7 lines, and is treated as a copy.
Other skills, from other repositories
codexkit-repository-maintenance
Use when maintaining or improving the GameStudio-CodexKIT source repository, including CI, governance, catalog, generators, adapters, packaging, documentation, versioning, or release readiness.
studio-project-scaffold
Use when running gamestudio init, status, or uninit, or bootstrapping a new or adopted game repository with AGENTS.md, HANDOFF.md, .agents/CONTRACT.md, project governance, a subsystem registry, or a per-project adapter report, plan digest, named reviewer, backup root, generated agent overlay, apply, uninstall, and…
unity-ui-art-and-motion-production
Use when new or revised Unity UI visuals, icons, panels, 9-slice sprites, component states, HUD or menu layouts, popup motion, screen transitions, or flattened UI screenshot decomposition must be produced through Figma and integrated into uGUI, NGUI, or UI Toolkit; not for UI debugging, localization-only work…
using-game-studio-skills
Use when starting any GameStudio-CodexKIT task or when a model runner is unavailable and someone requests a confidence-based PASS.
code-intelligence-contract
Use when dependency, call-chain, blast-radius, architecture, domain-flow, or unfamiliar-codebase analysis needs an optional vendor-neutral code-intelligence provider.
studio-goal-progress
Use when a KIT-managed Codex or Hermes Goal needs evidence-backed percentage, ETA range, live read-only progress views, or portable append-only progress recovery.