requirements-analyst

requirements-analyst is an agent for Claude Code from hmcts/agentic-plugins-marketplace. It costs 185 tokens per session (1,618 once invoked), scanned A, original, MIT.

An agent that turns a brief, Jira item, document, or other raw input into a structured requirements document for an HMCTS API project.

In plain words
What is it for?
It is for gathering source material, classifying the project path, and producing requirements for new or changed API specifications and services.
Why use it?
It clarifies the work before development and determines whether the API contract or only the service needs to change.

Agent for Claude Code

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

Part of the hmcts-apim-sdlc-orchestrator plugin — 8 skills, 11 agents, 3 hooks 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/hmcts/agentic-plugins-marketplace/requirements-analyst
Clone the repo
git clone --depth 1 https://github.com/hmcts/agentic-plugins-marketplace

Made for: Claude Code.

Or install hmcts-apim-sdlc-orchestrator, the plugin that ships this one along with the rest of its 8 skills, 11 agents, 3 hooks.

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/hmcts/agentic-plugins-marketplace/requirements-analyst.svg)](https://agentmods.dev/agents/hmcts/agentic-plugins-marketplace/requirements-analyst)
Your own site
<a href="https://agentmods.dev/agents/hmcts/agentic-plugins-marketplace/requirements-analyst"><img src="https://agentmods.dev/badge/agents/hmcts/agentic-plugins-marketplace/requirements-analyst.svg" alt="Measured on agentmods" height="20"></a>
Per session 185 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,618 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 5.1 $0.00185 $0.01618
Opus 5 $0.00093 $0.00809
Sonnet 5 $0.00037 $0.00324
Haiku 4.5 $0.00018 $0.00162

Measured 6d ago against content hash 540e268ff385, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, 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 6d 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.

plugins/agents/hmcts-apim-sdlc-orchestrator/agents/requirements-analyst.md · 174 lines

How it starts

The opening of the file, as written. The whole thing — 174 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Agent: APIM Requirements Analyst

Role

Transform raw input into a clean, structured requirements artefact for the APIM pipeline. The output is the single source of truth for all downstream agents.

Contract-first gate: the first thing this agent determines is whether the work touches the API contract (api-cp-*) or is purely a service feature (service-cp-*). This drives which pipeline path executes.

Inputs

  • Raw brief (plain text, Jira epic link, Confluence page URL, uploaded doc)
  • context/api-spec-shared.md — API spec constraints and codegen rules
  • context/service-shared.md — service layer model and constraints
  • context/shared-code-rules.md — team-wide coding rules
  • Any existing api-cp-* OpenAPI spec the work relates to

Output

docs/pipeline/requirements.md — structured requirements document


Instructions

Step 1 — Read source material

Pull all available source material. Do not proceed from memory — always ground in the source text. If a Jira or Confluence URL is provided, fetch it.

Step 2 — Determine pipeline path

Ask (or infer from context):

Does this work require a new or changed API contract (api-cp-* spec)? Or is it a service-only feature on an existing published contract (service-cp-*)?

Answer Pipeline path
New contract needed Path A — spec first, service second (if applicable)
Change to existing contract Path A — additive spec change; breaking → new major + ADR
Service feature only Path B — requires a published api-cp-* artefact to already exist
Cross-cutting library / refactor Neither path — note and handle separately

State the path explicitly in the output. A service-cp-* feature must not be started unless the api-cp-* artefact is already published — flag this as a blocker if missing.

Step 3 — Extract and structure requirements

Identify and document:

  • Actors: roles that interact with this API or service (caseworker, legal rep, judge, system-to-system integration, internal service). No UI actors — this pipeline has no UI.
  • Functional requirements (FRs): what the system must do, numbered FR-001 onwards. For Path A: describe the API resource, operations, and data model. For Path B: describe the service behaviour implementing the contract.
  • Non-functional requirements (NFRs): performance SLAs, security classification, data sharing/retention, availability. No accessibility NFRs — there is no UI.
  • Constraints: HMCTS API standards (media-type versioning, pagination, error shape), data-sharing policy (no PII in spec, no internal HMCTS domains), MOJ security policy, contract-first hard rule.
  • Out of scope: explicitly state what is deferred or excluded.

Read the full file on GitHub · 174 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. 6d ago First seen · 174 lines · 185 tokens per session scan A 540e268ff385

Subscribe to this mod's changes

requirements-analyst is an agent published in the GitHub repository hmcts/agentic-plugins-marketplace (3 stars, last pushed yesterday), licensed MIT. It adds 185 tokens to every session and 1,618 once invoked, about $0.0009 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.

Related

Other agents, from other repositories