nimble-researcher

nimble-researcher is an agent for Claude Code from Nimbleway/agent-skills. It costs 78 tokens per session (339 once invoked), scanned A, original, MIT.

A read-only web research agent that gathers raw facts about companies, competitors, people, or topics from search results and webpages.

In plain words
What is it for?
Use it to run focused searches, extract information from selected pages, and return structured findings with sources.
Why use it?
It speeds up initial information gathering while keeping collected facts and sources separate from later interpretation.

Agent for Claude Code

Written for Claude Code: shipped in a Claude Code plugin. Also seen: model in frontmatter.

Part of the nimble plugin — 15 skills, 1 command, 2 agents shipped together

Good fit Use it to run focused searches, extract information from selected pages, and return structured findings with sources.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/nimbleway/agent-skills/nimble-researcher
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.

Clone the repo
git clone --depth 1 https://github.com/Nimbleway/agent-skills

Made for: Claude Code.

Or install nimble, the plugin that ships this one along with the rest of its 15 skills, 1 command, 2 agents.

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 nimble-researcher

README.md
[![agentmods](https://agentmods.dev/badge/agents/nimbleway/agent-skills/nimble-researcher/github.svg)](https://agentmods.dev/agents/nimbleway/agent-skills/nimble-researcher)
Your own site
<a href="https://agentmods.dev/agents/nimbleway/agent-skills/nimble-researcher"><img src="https://agentmods.dev/badge/agents/nimbleway/agent-skills/nimble-researcher/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.

agentmods 80×15 button for nimble-researcher

Your own site · 80×15
<a href="https://agentmods.dev/agents/nimbleway/agent-skills/nimble-researcher"><img src="https://agentmods.dev/badge/agents/nimbleway/agent-skills/nimble-researcher.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 78 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 339 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original 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 5.1 $0.00078 $0.00339
Opus 5 $0.00039 $0.00169
Sonnet 5 $0.00016 $0.00068
Haiku 4.5 $0.00008 $0.00034

Measured 11d ago against content hash 0e0a930e0d05, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

nimble-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 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.

agents/nimble-researcher.md · 41 lines

What it actually says

Nimble Researcher

You are a fast, focused research agent. Your job is to gather raw data from the web using the Nimble CLI and return structured results to the parent context.

How you work

  1. Receive a research task (company, competitor, person, or topic)
  2. Run targeted searches using nimble search with appropriate focus modes
  3. Extract key content from top results using nimble extract
  4. Return structured findings — facts, signals, and sources

Rules

  • Speed over depth. Return good results fast. Don't over-research.
  • Parallel everything. Make multiple Bash tool calls in a single response.
  • Structured output. Return findings as bullet points with sources.
  • No analysis. Report what you found. Don't interpret or synthesize.
  • No file writes. You are read-only. The analyst handles persistence.
  • Date-aware queries. Always include date ranges in searches for freshness.
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. 11d ago First seen · 41 lines · 78 tokens per session scan A 0e0a930e0d05

Subscribe to this mod's changes

nimble-researcher is an agent published in the GitHub repository Nimbleway/agent-skills (53 stars, last pushed 15d ago), licensed MIT. It adds 78 tokens to every session and 339 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 2026-08-30.