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.
git 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/rules/unievolver/dep-scout/research-before-build)<a href="https://agentmods.dev/rules/unievolver/dep-scout/research-before-build"><img src="https://agentmods.dev/badge/rules/unievolver/dep-scout/research-before-build/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/rules/unievolver/dep-scout/research-before-build"><img src="https://agentmods.dev/badge/rules/unievolver/dep-scout/research-before-build.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 | $0.00671 | $0.00671 |
| Opus 5 | $0.00336 | $0.00336 |
| Sonnet 5 | $0.00134 | $0.00134 |
| Haiku 4.5 | $0.00067 | $0.00067 |
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 — 58 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)
Before writing any non-trivial functionality from scratch, you MUST first check whether a mature, well-maintained package already solves it — in whatever language the current project uses.
When to use dep-scout
Call the dep-scout MCP tools whenever you are about to:
- Implement a capability that is likely a solved problem (HTTP client, parsing, serialization, auth, retries, rate limiting, dates, state management, UI components, validation, CLI args, async utilities…).
- Add or choose a dependency.
- Hand-roll an algorithm or protocol that a library probably provides.
- Build an MCP server (check for an existing one first).
Workflow
- Call
find_packageswith a short description of what you want to build and theecosystemof the current project:rust(crates.io) ·npm(JS/TS/frontend) ·python(PyPI) ·go(pkg.go.dev) ·maven(Java/Kotlin) ·nuget(.NET).- Aliases work:
js/ts/frontend→ npm,py→ python,golang→ go,java/kotlin/gradle→ maven,dotnet/csharp→ nuget,rs→ rust. - Examples:
{query:"async http client", ecosystem:"rust"},{query:"date picker", ecosystem:"frontend"},{query:"json", ecosystem:"dotnet"}.
- Read the ranked candidates and their reuse scores:
- Score ≥ 78 (✅): strongly prefer reusing it.
- Score 58–77 (🟡): usable; address the listed warnings first.
- Score < 58 (🟠/🔴): be cautious; compare alternatives or justify your own.
- For a serious candidate, call
inspect_package(exact name + ecosystem) to verify license, deprecation/yank status, and runtime/version requirements before adding the dependency. (Go: full module path; Maven:group:artifact.) - Before writing your own MCP server, call
find_mcp_serversto look for an existing one in the official registry. - Only write a feature from scratch if no suitable package exists, and say so explicitly (one line) with the reason.
Notes
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 · 58 lines · 671 tokens per session scan A 676b60ec4e3c
research-before-build is a cursor rule published in the GitHub repository unievolver/dep-scout (1 stars, last pushed 2mo ago), licensed MIT. It adds 671 tokens to every session, about $0.0034 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 cursor rules, from other repositories
ponytail
Ponytail, lazy senior dev mode. Always pick the simplest solution that works.
angular-20
This rule provides comprehensive best practices and coding standards for Angular development, focusing on modern TypeScript, standalone components, signals, and performance optimizations.
dev-standard
Apache Superset development standards and guidelines for Cursor IDE.
cli-error-handling
CLI command error handling patterns.
prefer-direct-imports-over-module-mocks
Prefer extracting a testable core over vi.mock / vi.resetModules when unit tests need to reach production logic entangled with config, env, or singletons.
control-plane-descriptors
Control plane descriptor and instance implementation patterns.