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 user-w-ui/search-before-build --skill search-before-build-comparegit clone --depth 1 https://github.com/user-w-ui/search-before-buildWrote 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/user-w-ui/search-before-build/search-before-build-compare)<a href="https://agentmods.dev/skills/user-w-ui/search-before-build/search-before-build-compare"><img src="https://agentmods.dev/badge/skills/user-w-ui/search-before-build/search-before-build-compare/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/user-w-ui/search-before-build/search-before-build-compare"><img src="https://agentmods.dev/badge/skills/user-w-ui/search-before-build/search-before-build-compare.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to high
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- high Anti-Refusal · line 17 Skill instructs the agent to omit warnings, disclaimers, or ethical commentary. Stripping safety caveats hides risk from the user and is a common jailbreak preamble.Fix: Remove instructions that suppress warnings, disclaimers, or ethical commentary. Let the agent surface safety-relevant caveats to the user.
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 | $0.00100 | $0.01113 |
| Opus 5 | $0.00050 | $0.00557 |
| Sonnet 5 | $0.00020 | $0.00223 |
| Haiku 4.5 | $0.00010 | $0.00111 |
Grade A, and why
search-before-build-compare 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 11d 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 — 39 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Compare an Existing Project
Research alternatives to an existing plan or implementation without changing product code.
Rules
- Read the user's explicit request, supplied files, and the current repository before asking questions.
- Prefer codebase knowledge-graph tools for code discovery when available; fall back to read-only file inspection when needed.
- Describe the project from current evidence, not aspirations. Distinguish implemented, planned, and unknown capabilities.
- Speak plainly. Use professional names for technologies, but avoid product-management jargon.
- Separate two things: what is already built or written (read it from the supplied material; never re-ask it) and the real need the project is meant to serve (often vague in an early plan). Both shape the search.
- After establishing the baseline, let the user decide whether to align the real need before searching; do not judge this yourself from how vague or complete the material looks. Offer one clear choice—align first, or compare directly—and briefly say what alignment covers.
- If the user chooses to align, clarify only the real need behind the project: ask one focused question per turn, at most five information-seeking questions total, and only about gaps that would change the candidate set or comparison. Do not re-ask what the material already supplies. Clarify only to the depth that makes retrieval accurate; do not redesign or complete the plan. If the user declines, build the fingerprint from the baseline and search directly.
- Do not use project names, README claims, Stars, or popularity as proof of functional similarity.
- Do not modify source code, plans, or unrelated documentation.
When the user chooses to align the real need, read and follow the intent-model, How to ask, and Pre-research confirmation sections of references/conversation-and-decision.md from this package to clarify just enough for accurate retrieval. Read the Recommendation meanings section of the same reference before making the final decision.
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.
- 11d ago First seen · 39 lines · 100 tokens per session scan A 3f89e1a3cedb
search-before-build-compare is a skill published in the GitHub repository user-w-ui/search-before-build (122 stars, last pushed 5d ago), licensed MIT. It adds 100 tokens to every session and 1,113 once invoked, about $0.0005 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
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…
next-partial-prefetching-adoption
Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…