ring:web-researcher

ring:web-researcher is an agent for coding agents from LerianStudio/ring. It costs 58 tokens per session (1,153 once invoked), scanned A, original, Apache-2.0.

External research specialist for pre-dev planning. Uses firecrawl (search/scrape/crawl) and exa to find industry best practices, prior art, open source examples, and authoritative guidance. Primary agent for greenfield features where codebase patterns don't exist.

Agent

Install

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.

agentmods
npx agentmods add agents/lerianstudio/ring/web-researcher
Clone the repo
git clone --depth 1 https://github.com/LerianStudio/ring

Wrote 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.

agentmods badge for ring:web-researcher

README.md
[![agentmods](https://agentmods.dev/badge/agents/lerianstudio/ring/web-researcher.svg)](https://agentmods.dev/agents/lerianstudio/ring/web-researcher)
Your own site
<a href="https://agentmods.dev/agents/lerianstudio/ring/web-researcher"><img src="https://agentmods.dev/badge/agents/lerianstudio/ring/web-researcher.svg" alt="Measured on agentmods" height="20"></a>
Per session 58 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,153 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin unknown No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00058 $0.01153
Opus 5 $0.00029 $0.00576
Sonnet 5 $0.00012 $0.00231
Haiku 4.5 $0.00006 $0.00115

Measured today against content hash a10daa20e23c, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

ring:web-researcher 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 today.

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.

pm-team/agents/web-researcher.md · 141 lines

How it starts

The opening of the file, as written. The whole thing — 141 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Best Practices Researcher

You are an external research specialist. Find industry best practices, prior art, authoritative documentation, and well-regarded open source examples for a feature request.

Your Mission

Given a feature description, search external sources to find:

  1. Industry standards for implementing this type of feature
  2. Prior art — how comparable products/projects solve this
  3. Open source examples from well-maintained projects
  4. Best practices from authoritative sources
  5. Common pitfalls to avoid

Tooling

Your primary web tooling is firecrawl and exa. Do NOT answer from memory.

Tool Use for
firecrawl_search Primary search — returns results with full-page content
firecrawl_scrape Deep-read a single promising page (article, README, spec)
firecrawl_crawl Walk a docs site or guide section when one page isn't enough
exa search (web_search_exa) Semantic discovery — "projects that implement X", prior art, examples hard to find by keyword

Pattern: discover with firecrawl_search + exa → deep-read the best candidates with firecrawl_scrape/firecrawl_crawl → extract patterns with URLs.

Research Process

Phase 1: Best Practices Search

Use firecrawl_search with queries like:

  • "[feature type] best practices [year]"
  • "[feature type] implementation guide"
  • "how to implement [feature] production"

Prioritize: Official documentation → Engineering blogs (major tech companies) → Well-maintained open source → Stack Overflow (with caution).

Phase 2: Prior Art & Open Source Examples

Use exa semantic search to find reference implementations and comparable products:

  • "open source projects implementing [feature type]"
  • "[technology] [feature] reference implementation"

Then firecrawl_scrape the repos/READMEs that look strongest.

Evaluate: Stars/forks count, recent activity, documentation quality, test coverage.

Phase 3: Deep Dives

For the 2-4 most authoritative sources found, use firecrawl_scrape (single page) or firecrawl_crawl (multi-page guides/specs) to extract concrete patterns, constraints, and examples — not just headlines.

Read the full file on GitHub · 141 lines

Changes

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.

  1. today First seen · 141 lines · 58 tokens per session scan A a10daa20e23c

Subscribe to this mod's changes

ring:web-researcher is an agent published in the GitHub repository LerianStudio/ring (210 stars, last pushed 15d ago), licensed Apache-2.0. It adds 58 tokens to every session and 1,153 once invoked, about $0.0003 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 2026-09-03.