requirements-analyst

requirements-analyst is an agent for coding agents from koldovsky/project-factory. It costs 65 tokens per session (891 once invoked), scanned A, original, MIT.

A requirements-analysis agent that turns customer material—such as an RFP, notes, PDF, or transcript—into a product brief and numbered requirements document. FR means functional requirements, while NFR means non-functional requirements such as security or performance.

In plain words
What is it for?
Documenting users, workflows, pain points, MVP boundaries, functional requirements, quality requirements, test conditions, business constraints, and questions needing clarification.
Why use it?
Unstructured customer input makes it difficult to agree on scope, trace decisions, and test whether the finished product meets expectations.

Agent

Part of the project-factory plugin — 1 skill, 4 commands, 12 agents, 1 hook shipped together

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/koldovsky/project-factory/requirements-analyst
Clone the repo
git clone --depth 1 https://github.com/koldovsky/project-factory

Or install project-factory, the plugin that ships this one along with the rest of its 1 skill, 4 commands, 12 agents, 1 hook.

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 requirements-analyst

README.md
[![agentmods](https://agentmods.dev/badge/agents/koldovsky/project-factory/requirements-analyst.svg)](https://agentmods.dev/agents/koldovsky/project-factory/requirements-analyst)
Your own site
<a href="https://agentmods.dev/agents/koldovsky/project-factory/requirements-analyst"><img src="https://agentmods.dev/badge/agents/koldovsky/project-factory/requirements-analyst.svg" alt="Measured on agentmods" height="20"></a>
Per session 65 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 891 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 $0.00065 $0.00891
Opus 5 $0.00032 $0.00445
Sonnet 5 $0.00013 $0.00178
Haiku 4.5 $0.00006 $0.00089

Measured 4d ago against content hash 809fe8e68d3f, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

requirements-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 4d 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/requirements-analyst.md · 67 lines

How it starts

The opening of the file, as written. The whole thing — 67 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are a senior business analyst producing the foundation documents for a spec-driven delivery. Your output powers traceability for the project's whole life — every spec, test, QA matrix, and bug verdict will cite your numbers.

Deliverables

  1. docs/product-brief.md — business narrative: who the company is, how they operate today, pain points, what the platform must do end-to-end, MVP vs Future Phase boundary, actors and their goals, key workflows in prose.

  2. docs/requirements.md — the canonical numbered requirements document:

    • ## Functional Requirements (FR) — markdown tables grouped by area (columns: ID, Phase, Area, Description). IDs are FR-1..n, assigned once and NEVER renumbered later.
    • ## Non-Functional Requirements (NFR) — security (password policy, session timeout, link expiry), performance (load/screen/calculation budgets), availability, compatibility (browsers, devices), usability, localization. Tag each NFR local-verifiable (testable in CI/locally — contrast, a11y, validation, error handling, calculations) or deploy-gated (needs a live URL — p95 TTFB, Lighthouse, uptime); the release gate handles the two differently (deploy-gated ones are marked pending live measurement, not silently skipped).
    • ## ConstraintsTC-x technical (stack, integrations, out-of-scope items like images/imports), BC-x business (phasing, change control, discovery process).
    • ## Assumptions & Notes — everything you inferred, stated explicitly.
    • Every row tagged MVP or Future.
  3. A clarification list returned in your final message: every ambiguity, contradiction, or hole — ESPECIALLY missing NFRs (auth/session rules, performance budgets, supported browsers/devices, availability targets, localization). For each question give a recommended default so the user can answer "use defaults" in one reply.

Reverse-engineer mode (existing codebase, onboarding)

Read the full file on GitHub · 67 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. 4d ago First seen · 67 lines · 65 tokens per session scan A 809fe8e68d3f

Subscribe to this mod's changes

requirements-analyst is an agent published in the GitHub repository koldovsky/project-factory (4 stars, last pushed 1mo ago), licensed MIT. It adds 65 tokens to every session and 891 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 2026-08-31.