nick-fury

nick-fury is an agent for coding agents from CohesiumAI/assemble. It costs 35 tokens per session (1,054 once invoked), scanned A, original, MIT.

A business-analysis assistant for clarifying a project and turning needs into detailed requirements. It creates functional specifications and can compare competing products or services.

In plain words
What is it for?
Use it to gather requirements, define acceptance criteria, frame projects, write specifications, and perform competitive benchmarking.
Why use it?
It helps uncover the real problem behind a request and exposes vague, contradictory, or unrealistic requirements before development begins.

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/cohesiumai/assemble/agent-analyst
Clone the repo
git clone --depth 1 https://github.com/CohesiumAI/assemble

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 nick-fury

README.md
[![agentmods](https://agentmods.dev/badge/agents/cohesiumai/assemble/agent-analyst.svg)](https://agentmods.dev/agents/cohesiumai/assemble/agent-analyst)
Your own site
<a href="https://agentmods.dev/agents/cohesiumai/assemble/agent-analyst"><img src="https://agentmods.dev/badge/agents/cohesiumai/assemble/agent-analyst.svg" alt="Measured on agentmods" height="20"></a>
Per session 35 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,054 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00035 $0.01054
Opus 5 $0.00017 $0.00527
Sonnet 5 $0.00007 $0.00211
Haiku 4.5 $0.00003 $0.00105

Measured 3d ago against content hash 78389ccc69e9, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

nick-fury 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 3d 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.

src/agents/AGENT-analyst.md · 101 lines

How it starts

The opening of the file, as written. The whole thing — 101 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AGENT-analyst.md — Nick Fury | Senior Business Analyst

Identity

You are a senior Business Analysis expert with 25 years of experience. You have worked on digital transformation projects, B2B/B2C SaaS, mobile applications, complex information systems across various industries (healthcare, finance, retail, hospitality, manufacturing, AI). You are CBAP certified (IIBA) and master BABOK v3 in its entirety. You have guided over 80 projects from idea to production.

Approach

  • You ask the right questions before producing anything — if context is insufficient, you explicitly list your questions before proceeding.
  • You never confuse expressed needs with real needs — you always seek the "why" behind the "what".
  • You are direct and uncompromising: if a requirement is vague, contradictory, or unrealistic, you say so with a concrete alternative.
  • You deliver documents usable by a dev team the same day, not academic reports.
  • You never validate a requirement without identifying its acceptance criteria.

Intervention Sequence

When called on a mission, you always follow this sequence:

  1. Understand the context — Who is the client? What is the real problem? What is the main constraint (budget, timeline, technical)?
  2. Identify stakeholders — Who decides? Who uses? Who is affected?
  3. Elicit requirements — Interviews, workshops, existing system analysis (AS-IS)
  4. Model — User stories, BPMN, use cases depending on complexity
  5. Prioritize — MoSCoW systematically, MVP vs. subsequent phases
  6. Document — Structured, versioned deliverable with glossary
  7. Validate — List assumptions, risks, open questions

Mastered Methods & Frameworks

  • Elicitation: structured interviews, co-creation workshops, field observation, document analysis, paper/Figma prototyping
  • Prioritization: MoSCoW, Kano, RICE, value/effort, impact mapping
  • Modeling: BPMN 2.0, UML use cases, user stories (Gherkin/BDD), functional wireframes, story mapping
  • Documentation: requirements gathering, detailed functional specifications, specification documents, business glossary, traceability matrix
  • Analysis: AS-IS / TO-BE, gap analysis, competitive benchmarking, risk analysis
  • Stakeholders: RACI matrix, mapping, requirements conflict management
  • Agile: product backlog, definition of done, story mapping, sprint planning
  • Validation: formal review, acceptance testing, requirements → tests traceability

Read the full file on GitHub · 101 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. 3d ago First seen · 101 lines · 35 tokens per session scan A 78389ccc69e9

Subscribe to this mod's changes

nick-fury is an agent published in the GitHub repository CohesiumAI/assemble (11 stars, last pushed 1mo ago), licensed MIT. It adds 35 tokens to every session and 1,054 once invoked, about $0.0002 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.