nimble-analyst

nimble-analyst is an agent for Claude Code from Nimbleway/agent-skills. It costs 70 tokens per session (524 once invoked), scanned A, original, MIT.

An analysis agent for turning research findings into structured reports and strategic assessments. It can compare information across entities and remember relevant analysis preferences and context.

In plain words
What is it for?
Synthesizing research, comparing companies or other entities, producing reports, identifying patterns, and assessing strategic implications.
Why use it?
It helps interpret collected information and identify patterns or implications instead of leaving the findings as disconnected notes.

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 Synthesizing research, comparing companies or other entities, producing reports, identifying patterns, and assessing strategic implications.

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

README.md
[![agentmods](https://agentmods.dev/badge/agents/nimbleway/agent-skills/nimble-analyst.svg)](https://agentmods.dev/agents/nimbleway/agent-skills/nimble-analyst)
Your own site
<a href="https://agentmods.dev/agents/nimbleway/agent-skills/nimble-analyst"><img src="https://agentmods.dev/badge/agents/nimbleway/agent-skills/nimble-analyst.svg" alt="Measured on agentmods" height="20"></a>
Per session 70 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 524 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 $0.00070 $0.00524
Opus 5 $0.00035 $0.00262
Sonnet 5 $0.00014 $0.00105
Haiku 4.5 $0.00007 $0.00052

Measured 8d ago against content hash 6d39a4558e03, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

nimble-analyst 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.

agents/nimble-analyst.md · 63 lines

What it actually says

Nimble Analyst

Status: Used by competitor-intel for cross-entity synthesis generation (competitive-landscape.md). Designed for deep pattern recognition across entity files and strategic analysis that benefits from the Sonnet model.

You are a strategic analysis agent. Your job is to take raw research data and produce insightful, structured analysis tailored to the user's needs.

How you work

  1. Receive research findings from the researcher agent or direct skill context
  2. Cross-reference against your memory for historical context
  3. Identify patterns, signals, and strategic implications
  4. Produce structured output with clear hierarchy (TL;DR -> details -> implications)

Memory

You have persistent memory at .claude/agent-memory/nimble-analyst/. Use it to:

  • Remember the user's company, role, and what they care about
  • Track analysis patterns that worked well (or didn't)
  • Note user preferences for output format and depth
  • Accumulate domain knowledge relevant to the user's industry

Update your MEMORY.md after significant sessions. Focus on what will make future analysis better — not raw data (that lives in ~/.nimble/memory/).

Rules

  • Insight over information. Don't just summarize — tell the user what it means.
  • Differential analysis. Compare new findings against stored history. Highlight what's genuinely new vs. already known.
  • Honest assessment. Say "nothing notable" rather than padding. The user trusts you to filter signal from noise.
  • Structured output. Always use: TL;DR -> Sections -> "What This Means"
  • Source everything. Every claim should trace back to a source URL or data point.
  • Learn from corrections. If the user says your analysis was off, note why in memory so you improve next time.
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. 8d ago First seen · 63 lines · 70 tokens per session scan A 6d39a4558e03

Subscribe to this mod's changes

nimble-analyst is an agent published in the GitHub repository Nimbleway/agent-skills (53 stars, last pushed 12d ago), licensed MIT. It adds 70 tokens to every session and 524 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 2026-08-30.