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 ash1794/vibe-engineering --skill research-before-designgit clone --depth 1 https://github.com/ash1794/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/ash1794/vibe-engineering/research-before-design)<a href="https://agentmods.dev/skills/ash1794/vibe-engineering/research-before-design"><img src="https://agentmods.dev/badge/skills/ash1794/vibe-engineering/research-before-design.svg" alt="Measured on agentmods" 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 | $0.00036 | $0.00574 |
| Opus 5 | $0.00018 | $0.00287 |
| Sonnet 5 | $0.00007 | $0.00115 |
| Haiku 4.5 | $0.00004 | $0.00057 |
Grade A, and why
vibe-research-before-design 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 8d 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.
Copies of this mod
1 near-identical copy found in the catalogue:
- vibe-research-before-design — 100% identical, 0 lines differ
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.
vibe-research-before-design
Before proposing any design, architecture, or technology choice — research first. "Other people's documented failures count as observed failure."
When to Use This Skill
- Designing a new feature or system
- Choosing between technologies, frameworks, or patterns
- Making architectural decisions with long-term consequences
- The user asks "how should we build X?"
- You're about to say "I recommend..." for a design choice
When NOT to Use This Skill
- Implementing an already-designed spec (the research was done at design time)
- Fixing a bug (use
vibe-debugging-journalinstead) - Simple refactoring with no architectural implications
- The user has explicitly chosen a technology and wants implementation
Steps
-
Identify the design question — What decision are we making? What are the key constraints?
-
Dispatch research — For each major sub-problem, find:
- 2+ named real-world projects/libraries with adoption metrics (GitHub stars, npm downloads, production users)
- 1+ academic paper or technical blog with year and venue/source
- The mechanism — how does it actually work? (Not marketing copy)
- Known failures — what went wrong for others?
- Applicability assessment — does this fit our constraints?
-
Synthesize findings — Present a comparison table:
Option Adoption Mechanism Known Failures Fit -
Make a recommendation — Based on evidence, not intuition. State confidence level.
-
Record the decision — Use
vibe-decision-journalto log the choice and alternatives.
Red Flags
- "This is obvious, we should just use X" — If it's obvious, proving it takes 2 minutes
- "I've used X before" — Past experience ≠ current best option
- "Everyone uses X" — Popularity ≠ fitness for your constraints
- "Let me just start building and we'll figure it out" — The most expensive approach
Output Format
Research Summary
- Decision: [What we're deciding]
- Constraints: [Key constraints]
- Options Evaluated: X
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.
- 8d ago First seen · 68 lines · 36 tokens per session scan A 9bf9c30414fe
vibe-research-before-design is a skill published in the GitHub repository ash1794/vibe-engineering (10 stars, last pushed 3mo ago), licensed MIT. It adds 36 tokens to every session and 574 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 2026-08-31.
Other skills, from other repositories
resolve-plugins
Curate Claude Code skill / MCP / hook picks against live upstream sources and pin them in .claude/settings.json. Adding a process harness (a paired skill set) is an ordinary pick this door handles. Reads stack from docs/techstack.md, workflow signal from docs/overview.md + existing pins, then live-queries six source…
refresh
Use when an existing contextualizer's references may have drifted from current upstream state — typically weekly, or whenever a few days of upstream changes have accumulated — to bring them back into agreement.
using-skill-engine
When the user mentions skill-engine or "the engine" without naming a specific workflow, or wants first-run setup. Inspects .claude/skills/-context/ install state (and any pending -context.proposed/ proposals) across all three install levels, then dispatches to engine-bootstrap when no contextualizer exists, to…
apply
Use when a staged proposal has been reviewed and signed off — REVIEW.md Step 3 ticked reviewed or provisional — and is ready to promote into the live contextualizer.
config-set
Use when changing an engine-wide config value — currently diff.tool, the command /skill-engine:review prints for inspecting a proposed-vs-live diff.
my-adhd-caveman
Self-contained output mode: ADHD actable structure (action first, numbered steps, one next action, one-line progress) plus caveman diction (drop fluff/articles, fragments, fewer tokens). Use when the user says "adhd-caveman", "my-adhd-caveman", or invokes /my-adhd-caveman. Needs no other skills.