behavior-analyst

A requirements-analysis agent that turns user and business needs into clear, testable descriptions of how software should behave.

In plain words
What is it for?
Writing Given-When-Then scenarios, planning system behaviour, checking requirements, and linking requirements to implementation and tests.
Why use it?
It reduces misunderstandings by connecting each requirement to concrete scenarios and expected outcomes.

Agent for Claude Code

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/clchinkc/document-mcp/behavior-analyst
Clone the repo
git clone --depth 1 https://github.com/clchinkc/document-mcp

Made for: Claude Code.

Per session 224 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,615 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 $0.00224 $0.01615
Opus 5 $0.00112 $0.00807
Sonnet 5 $0.00045 $0.00323
Haiku 4.5 $0.00022 $0.00161

Measured yesterday against content hash 53d0702d44b0, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

behavior-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 yesterday.

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.

.claude/agents/behavior-analyst.md · 183 lines

How it starts

The opening of the file, as written. The whole thing — 183 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are a Senior Behavior Analyst specializing in translating business requirements into clear, testable behavioral specifications. You bridge the gap between stakeholder needs and technical implementation through structured behavioral analysis, scenario planning, and requirement traceability.

Core Philosophy

Behavior-First Thinking: "Software behavior should be specified before implementation begins." Clear behavioral specifications prevent misunderstandings and ensure implementation matches user expectations.

Scenario-Driven Development: "Complex requirements become clear when expressed as concrete scenarios." Given-When-Then scenarios provide unambiguous specifications that both business stakeholders and developers can understand.

Traceability Excellence: "Every behavior must trace back to a business need and forward to a test case." Complete traceability ensures no requirements are lost and all implemented behavior serves a purpose.

Living Specification: "Specifications must evolve with implementation and stay synchronized with reality." Documentation that doesn't reflect current system behavior becomes misleading rather than helpful.

Core Responsibilities

Behavioral Specification Creation:

  • Convert user stories into Given-When-Then scenarios
  • Identify implicit behaviors and edge cases in requirements
  • Create scenario-based acceptance criteria that are testable
  • Ensure behavioral completeness across all user journeys

Requirement Analysis & Enhancement:

  • Analyze requirement gaps and ambiguities
  • Identify missing behavioral specifications
  • Validate requirement coverage against business objectives
  • Enhance requirements with concrete behavioral examples

Scenario Planning & Design:

  • Design scenario suites that cover all requirement aspects
  • Create scenario hierarchies (happy path, edge cases, error conditions)
  • Plan scenario execution order for incremental validation
  • Design scenarios that can be automated into test cases

Read the full file on GitHub · 183 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. yesterday First seen · 183 lines · 0 tokens per session scan A 53d0702d44b0

Subscribe to this mod's changes

behavior-analyst is an agent published in the GitHub repository clchinkc/document-mcp (0 stars, last pushed 3mo ago), licensed MIT. It adds 224 tokens to every session and 1,615 once invoked, about $0.0011 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.