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 unievolver/dep-scout --skill skillgit clone --depth 1 https://github.com/unievolver/dep-scoutWrote 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/unievolver/dep-scout/skill)<a href="https://agentmods.dev/skills/unievolver/dep-scout/skill"><img src="https://agentmods.dev/badge/skills/unievolver/dep-scout/skill/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/unievolver/dep-scout/skill"><img src="https://agentmods.dev/badge/skills/unievolver/dep-scout/skill.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 | $0.00088 | $0.00664 |
| Opus 5 | $0.00044 | $0.00332 |
| Sonnet 5 | $0.00018 | $0.00133 |
| Haiku 4.5 | $0.00009 | $0.00066 |
Grade A, and why
research-before-build 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 10d 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 — 50 lines — stays where its author put it; the contents beside it link to each section on GitHub.
先查再造 / Research before you build
A portable skill that pairs with the dep-scout MCP server. Its job: stop AI agents from reinventing wheels by always checking the right registry — crates.io (Rust), npm (JS/TS/frontend), PyPI (Python), pkg.go.dev (Go), Maven Central (Java/Kotlin) or NuGet (.NET) — for a mature, maintained package first.
How to apply
When you are about to build a non-trivial piece of functionality:
- Search first. Call
find_packageswith keywords describing the capability plus the project'secosystem(rust|npm|python|go|maven|nuget;js/ts/frontend→ npm,py→ python,golang→ go,java/kotlin→ maven,dotnet/csharp→ nuget). Examples:{query:"async http client", ecosystem:"rust"},{query:"react date picker", ecosystem:"frontend"},{query:"json", ecosystem:"dotnet"}. - Read the scores. dep-scout ranks candidates 0–100 on popularity,
maintenance recency, version stability, and metadata completeness:
≥ 78✅ strongly recommended — reuse it.58–77🟡 usable — resolve the listed warnings first.< 58🟠/🔴 — compare alternatives or justify a from-scratch build.
- Vet the finalist. Call
inspect_packagewith the exact name + ecosystem to confirm license, deprecation/yank status, and runtime/version requirements before depending on it. - Reuse tooling too. Before building an MCP server, call
find_mcp_serversto check the official registry for an existing one. - Decide explicitly. Reuse the best fit, or state in one line why nothing suitable exists and you are implementing it yourself.
Notes
- Pass the ecosystem of the project you're editing. Frontend frameworks (React,
Vue, Svelte, Angular…) all live on
npm. - PyPI has no public full-text search API, so Python search is name-oriented:
prefer concrete library names, or use
inspect_packagedirectly.
Why
Most "new" features are solved problems. A maintained package carries fewer bugs, better security, and lower long-term cost than a hand-rolled reimplementation. The default should be reuse; building from scratch is the exception that needs a reason.
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.
- 10d ago First seen · 50 lines · 88 tokens per session scan A a54c0abb79ed
research-before-build is a skill published in the GitHub repository unievolver/dep-scout (1 stars, last pushed 2mo ago), licensed MIT. It adds 88 tokens to every session and 664 once invoked, about $0.0004 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
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…