Borrowing it
Nothing to install: this file belongs to regenrek/oplink-mcp. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/regenrek/oplink-mcp/main/.cursor/commands/research-better-lib.mdgit clone --depth 1 https://github.com/regenrek/oplink-mcpWrote 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/commands/regenrek/oplink-mcp/research-better-lib)<a href="https://agentmods.dev/commands/regenrek/oplink-mcp/research-better-lib"><img src="https://agentmods.dev/badge/commands/regenrek/oplink-mcp/research-better-lib.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 | $0.00000 | $0.01464 |
| Opus 5 | $0.00000 | $0.00732 |
| Sonnet 5 | $0.00000 | $0.00293 |
| Haiku 4.5 | $0.00000 | $0.00146 |
Grade A, and why
research-better-lib 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.
How it starts
The opening of the file, as written. The whole thing — 102 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Research Template: Find a Modern, Faster Library than a Baseline
Use this template to evaluate alternatives to any baseline library. Replace placeholders like <BASELINE_LIB>, <DOMAIN/USE‑CASE>, <CANDIDATE_LIBS> before posting or running the search.
Problem statement
- Goal: Find a modern, faster JavaScript/TypeScript library for <DOMAIN/USE‑CASE> that outperforms <BASELINE_LIB> in latency and bundle size while maintaining or improving relevance/quality.
- Context: Runs in Node 18+/browser, ESM‑first, TS types, no native deps; list size 5k–50k items (adjust to your scale); return top‑N suggestions per query.
Success metrics (make these explicit)
- P95 latency/query: target <1 ms at 10k items; <5 ms at 50k items (Node laptop). Adjust as needed.
- Bundle size: <25 KB min+gzip for core (no heavy optional modules).
- Quality: NDCG@5 (or task‑specific metric) ≥ <BASELINE_LIB> on the same corpus (≥1.0x).
- Features: multi‑field weights, typo tolerance, diacritics, highlight ranges, incremental updates.
- DX: ESM, TS types, active maintenance (<6 months since last release), permissive license.
Scope and exclusions
- In‑scope: in‑memory, client/Node libraries (no servers, no external indexes).
- Out‑of‑scope: hosted/search servers unless used only for comparison; heavy NLP stacks unless used for query expansion (phase 2).
Concrete research question to post/search
- “Which modern JS/TS libraries outperform <BASELINE_LIB> for <DOMAIN/USE‑CASE> at 10k–50k items, with ESM, TS types, and <25 KB gzip bundle? Compare <CANDIDATE_LIBS> by p95 latency, relevance (NDCG@5 or equivalent), bundle size, multi‑field weighting, and maintenance.”
Search queries (copy/paste)
- benchmark “<BASELINE_LIB>” vs <CANDIDATE_A> vs <CANDIDATE_B> js performance
- “<CANDIDATE_A> vs <BASELINE_LIB>” latency relevance “typescript” “esm”
- “<CANDIDATE_B>” library benchmark fuzzy search (adjust for your domain)
- <CANDIDATE_C> benchmark bundle size “diacritics” “highlight”
- <CANDIDATE_D> bm25 javascript benchmark “multi field”
- <CANDIDATE_E> js benchmark in‑memory search
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 · 102 lines · 0 tokens per session scan A 71b78d8bc9eb
research-better-lib is a command published in the GitHub repository regenrek/oplink-mcp (10 stars, last pushed 9mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,464 tokens. 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 commands, from other repositories
checklist
Generate a custom checklist for the current feature based on user requirements.
clarify
Identify underspecified areas in the current feature spec by asking up to 5 highly targeted clarification questions and encoding answers back into the spec.
specify
Create or update the feature specification from a natural language feature description.
converge
Assess the current codebase against the feature's spec, plan, and tasks, then append any remaining unbuilt work as new tasks to tasks.md so implement can complete it.
implement
Execute the implementation plan by processing and executing all tasks defined in tasks.md.
analyze
Perform a non-destructive cross-artifact consistency and quality analysis across spec.md, plan.md, and tasks.md after task generation.