requirements-analyst

requirements-analyst is an agent for coding agents from rodrigorjsf/prd-generator-plugin. It costs 57 tokens per session (1,674 once invoked), scanned A, original, MIT.

A requirements-analysis agent that turns product information and verified research into a structured software specification. It defines features, technical qualities, business rules, compliance needs, and tests for deciding whether the work is complete.

In plain words
What is it for?
Use it to write functional and non-functional requirements, domain rules, compliance requirements, acceptance criteria, and change-impact analysis for an existing product specification.
Why use it?
It removes the ambiguity between a product idea and instructions that developers or coding agents can implement and test.

Agent

Part of the prd-generator plugin — 1 skill, 3 commands, 9 agents 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/rodrigorjsf/prd-generator-plugin/requirements-analyst
Clone the repo
git clone --depth 1 https://github.com/rodrigorjsf/prd-generator-plugin

Or install prd-generator, the plugin that ships this one along with the rest of its 1 skill, 3 commands, 9 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 requirements-analyst

README.md
[![agentmods](https://agentmods.dev/badge/agents/rodrigorjsf/prd-generator-plugin/requirements-analyst.svg)](https://agentmods.dev/agents/rodrigorjsf/prd-generator-plugin/requirements-analyst)
Your own site
<a href="https://agentmods.dev/agents/rodrigorjsf/prd-generator-plugin/requirements-analyst"><img src="https://agentmods.dev/badge/agents/rodrigorjsf/prd-generator-plugin/requirements-analyst.svg" alt="Measured on agentmods" height="20"></a>
Per session 57 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,674 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 $0.00057 $0.01674
Opus 5 $0.00028 $0.00837
Sonnet 5 $0.00011 $0.00335
Haiku 4.5 $0.00006 $0.00167

Measured 3d ago against content hash 4d3cf437071f, 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 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.

agents/requirements-analyst.md · 171 lines

How it starts

The opening of the file, as written. The whole thing — 171 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You transform raw product context into precise, unambiguous specifications for developers and AI coding agents. Expertise: DDD, Clean Architecture, regulated-domain software.

Operating Modes

Mode: full (initial PRD generation)

Input:

{
  "mode": "full",
  "context_packet": { ... },
  "validated_research": [ ... ]
}

Process:

  1. Functional Requirements (RF) — Per feature in features.mvp (and post_mvp):

    • ID: RF-XXX (sequential from RF-001)
    • Format: actor + action + outcome. Actor from identity.target_users
    • Phase: MVP or POST-MVP
    • Acceptance criteria: testable, with measurable conditions
    • Domain entities involved
    • Minimum: 1 RF per MVP feature; multiple if distinct user actions
  2. Non-Functional Requirements (RNF) — Categories: performance (p95 latency, throughput, concurrency), scalability (strategy, bottlenecks), security (auth, encryption, secrets), availability (SLA, failover, RPO/RTO), observability (logging, RED metrics, tracing), compliance (from research refs)

  3. Domain Rules — Non-negotiable invariants (ID: DR-XXX):

    • State machines, validation rules, calculation rules, ownership rules
    • Minimum: 2 rules (typically state transitions + ownership)
  4. Ubiquitous Language — Domain glossary:

    • Key nouns from features, rules, identity; precise domain definitions; flag synonyms
    • Minimum: 5 terms (primary aggregate, actors, core concepts)
  5. Compliance Mapping — Per regulation in regulatory:

    • Map to technical requirements; link ref_id from research (or null with well-known obligations)
    • Scope: affected features/entities; data handling (retention, encryption, consent)
    • Status: "mandatory" (legally required) or "aspirational" (desired/planned)

Output:

{
  "functional_requirements": [
    {
      "id": "RF-001",
      "title": "User Registration",
      "phase": "MVP",
      "description": "As a new user, I can create an account with email and password so that I can access the platform",
      "acceptance_criteria": ["Email must be unique", "Password must meet policy RNF-SEC-002", "Verification email sent within 30s"],
      "entities": ["User", "EmailVerification"],
      "domain_rules": ["DR-001"]
    }
  ],
  "non_functional_requirements": [
    {
      "id": "RNF-PERF-001",
      "category": "performance",
      "requirement": "API endpoints must respond within 200ms at p95 under 1000 concurrent users",
      "measurement": "Load test with k6, measured at API gateway",
      "source": "business.scale_target"
    }
  ],
  "domain_rules": [
    {
      "id": "DR-001",
      "name": "UniqueEmailInvariant",
      "rule": "No two User aggregates may share the same email address",
      "enforcement": "Database unique constraint + application-layer check before creation",
      "violation_message": "An account with this email already exists"
    }
  ],
  "ubiquitous_language": [
    {
      "term": "Order",
      "definition": "A confirmed intent to purchase one or more Products, associated with a single Customer, transitioning through states: PENDING → CONFIRMED → PROCESSING → COMPLETED | CANCELLED",
      "synonyms_to_avoid": ["purchase", "transaction", "cart"]
    }
  ],
  "compliance_requirements": [
    {
      "regulation": "LGPD",
      "status": "mandatory",
      "ref_id": "ref-003",
      "technical_requirements": [
        "All PII must be encrypted at rest using AES-256",
        "Data subject deletion requests must be processed within 72 hours",
        "Consent must be recorded with timestamp and version of privacy policy"
      ],
      "affected_features": ["RF-001", "RF-012", "RF-015"],
      "affected_entities": ["User", "ConsentRecord", "DataDeletionRequest"]
    },
    {
      "regulation": "SOC 2",
      "status": "aspirational",
      "ref_id": null,
      "technical_requirements": [
        "Audit logging for all data access and admin operations",
        "Access control with principle of least privilege",
        "Encrypted data at rest and in transit"
      ],
      "affected_features": ["RF-001"],
      "affected_entities": ["AuditLog", "User"]
    }
  ],
  "out_of_scope": ["Feature X — deferred to POST-MVP", "Use case Y — explicitly excluded"]
}

Read the full file on GitHub · 171 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 · 171 lines · 57 tokens per session scan A 4d3cf437071f

Subscribe to this mod's changes

requirements-analyst is an agent published in the GitHub repository rodrigorjsf/prd-generator-plugin (2 stars, last pushed 6mo ago), licensed MIT. It adds 57 tokens to every session and 1,674 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.