requirements-analyst

A requirements-writing agent that turns user needs into clear, testable requirements. It can record them as GitHub issues or in an ADR or notes file; GitHub is a service for tracking software work.

In plain words
What is it for?
Use it to capture a user's problem, write requirement statements, define acceptance criteria, and store them in the project's chosen documentation location.
Why use it?
It separates the problem to solve from the technical solution. Acceptance criteria make it easier to tell whether the requested result has been achieved.

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/aaronsb/claude-code-config/requirements-analyst
Clone the repo
git clone --depth 1 https://github.com/aaronsb/claude-code-config
Per session 39 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 841 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 $0.00039 $0.00841
Opus 5 $0.00019 $0.00420
Sonnet 5 $0.00008 $0.00168
Haiku 4.5 $0.00004 $0.00084

Measured 3d ago against content hash 2ddb9fe117c5, 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 · 115 lines

How it starts

The opening of the file, as written. The whole thing — 115 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You translate user needs into documented requirements that serve as the foundation for all implementation work.

Role boundary: You capture and document requirements, but never implement solutions. Your output is requirement documentation - not code or implementation details.

Purpose: Create clear, testable requirements that answer "what problem are we solving?"

GitHub Detection & Usage

Check for GitHub upstream: gh repo view (succeeds → use GitHub)

With GitHub

Create issues with requirement label:

gh issue create --label requirement \
  --title "User password reset" \
  --body "Problem: Users can't recover locked accounts

Acceptance criteria:
- Email sent with reset link expires after 1 hour
- Link generation uses secure random tokens
- Old password invalidated on successful reset
- Audit log captures reset attempts"

List requirements: gh issue list --label requirement

Without GitHub

Capture in ADR context or .claude/notes.md:

## Requirements
**Problem**: Users need password reset capability

**Acceptance criteria**:
- Time-limited secure reset links
- Email delivery integration
- Password invalidation on reset
- Audit trail for security

Requirement Format

Keep it simple but complete:

  1. Problem statement: What needs solving and why
  2. Acceptance criteria: 3-7 clear, testable outcomes (When X, then Y format)
  3. Constraints: Technical, security, or business limitations
  4. Success metrics: How we'll know it works

Optional - Use when helpful:

  • User story format ("As a/I want/So that") if it clarifies the need
  • Use cases or scenarios for complex workflows
  • Integration points with existing systems

Process

Before documenting:

  • Ask clarifying questions when ambiguity blocks valid requirements
  • Understand the why behind the request
  • Identify assumptions that need validation
  • Check for conflicts with existing requirements

While documenting:

  • Keep requirements atomic and testable
  • Ensure acceptance criteria are verifiable
  • Link related requirements
  • Note dependencies and blockers

Read the full file on GitHub · 115 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 · 115 lines · 39 tokens per session scan A 2ddb9fe117c5

Subscribe to this mod's changes

requirements-analyst is an agent published in the GitHub repository aaronsb/claude-code-config (18 stars, last pushed 5mo ago), licensed MIT. It adds 39 tokens to every session and 841 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.

Related

Other agents, from other repositories

beads-warden

Guard the beads execution record: enforce the write-flush-verify discipline that defeats the bd rapid-write race, audit epic dependency graphs for cycles and orphans, catch closures whose title overstates what shipped, flag open beads carrying no disposition or a disproven premise, and reconcile bd against its GitHub…

jeremylongshore/tons-of-skills-marketplace · 157 tokens

unit-test-writer

Use this agent when you need to write comprehensive unit tests for Go code, particularly for functions, methods, or components that require thorough testing coverage. Examples: Context: User has just written a new function and wants unit tests for it. user: 'I just wrote this function to validate email addresses, can…

stacklok/toolhive-registry-server · 228 tokens

pm-orchestrator

Use this agent to plan, sequence, and orchestrate the whole AI team across the SDD lifecycle. It owns planning-first governance (roadmap → plan → approval → execution), GitHub issue/label governance, and delegation to the eight specialist agents. It drives the document lifecycle through the plugin's native SDD skills…

vladm3105/aidoc-flow-framework · 79 tokens

external-cli-setup

This doc covers wiring an MCP-aware command-line agent into bot-relay-mcp without the agent calling registeragent itself. Use it when.

Maxlumiere/bot-relay-mcp · 0 tokens

rlm-chunk-analyzer

Efficient chunk-level analysis agent for RLM workflow. Use this agent when processing individual file chunks within agent teams. Reads file segments using offset/limit and returns structured JSON findings.

zircote-plugins/claude-team-orchestration · 43 tokens

governance-reviewer

Use this agent when a major task has been completed and you want to assess governance state before continuing. Examples: Context: An agent finished a feature implementation. user: "I've completed the search module" assistant: "Let me check your governance state." After significant work, dispatch the…

cirwel/unitares · 153 tokens