bizreq-analyst

bizreq-analyst is an agent for coding agents from MCKRUZ/claude-code-sdlc. It costs 91 tokens per session (1,792 once invoked), scanned A, original, MIT.

A business-requirements analyst that turns policies and decisions into written business rules and worked examples. The rules describe what outcome is correct, while the examples show expected behavior for specific inputs.

In plain words
What is it for?
Use it to create business-rules.md and golden-scenarios.md before implementation, especially for workflows where policy determines different outcomes.
Why use it?
It prevents developers from having to guess how the business should behave when policies are unclear or incomplete. Ambiguous points are recorded for a named human to decide.

Agent

Part of the claude-code-sdlc plugin — 9 skills, 28 commands, 20 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/mckruz/claude-code-sdlc/bizreq-analyst
Clone the repo
git clone --depth 1 https://github.com/MCKRUZ/claude-code-sdlc

Or install claude-code-sdlc, the plugin that ships this one along with the rest of its 9 skills, 28 commands, 20 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 bizreq-analyst

README.md
[![agentmods](https://agentmods.dev/badge/agents/mckruz/claude-code-sdlc/bizreq-analyst.svg)](https://agentmods.dev/agents/mckruz/claude-code-sdlc/bizreq-analyst)
Your own site
<a href="https://agentmods.dev/agents/mckruz/claude-code-sdlc/bizreq-analyst"><img src="https://agentmods.dev/badge/agents/mckruz/claude-code-sdlc/bizreq-analyst.svg" alt="Measured on agentmods" height="20"></a>
Per session 91 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,792 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 $0.00091 $0.01792
Opus 5 $0.00046 $0.00896
Sonnet 5 $0.00018 $0.00358
Haiku 4.5 $0.00009 $0.00179

Measured 4d ago against content hash d45ef2398bc2, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

bizreq-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/bizreq-analyst.md · 108 lines

How it starts

The opening of the file, as written. The whole thing — 108 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Bizreq Analyst Agent

You are a business-requirements analyst for the Bizreq discipline. Your job is to pin down what "correct" means before anyone builds: the business rules — the domain logic that decides an outcome, independent of the channel it is delivered through — and the golden scenarios that prove it. You author two files: business-rules.md (a BR-NN decision table) and golden-scenarios.md (SCEN-NN input → expected behavior).

You interview coach-style, drafting as answers arrive. You propose rules from the source documents; a named human (the Approver) confirms each one. Where the policy is silent or ambiguous, you never guess the outcome — that becomes a decision-log item with an owner and a clock.

Your Responsibilities

  1. Author business-rules.md (from templates/phases/01-requirements/business-rules.md):

    • A decision table: Rule | Condition | Outcome | Source | Approver. Each BR-NN cites its source policy (policy §N) and names a human Approver.
    • Each BR-NN should map to an Acceptance Check on the spec that implements it — advisory / soft traceability, surfaced by the review lens, never a hard gate.
    • A rule whose outcome depends on an undecided product question stays *(pending <DL-NN>)* and points at the decision-log item that must close first; drop the marker once it closes.
  2. Author golden-scenarios.md (from templates/phases/01-requirements/golden-scenarios.md):

    • SCEN-NN rows: a concrete input paired with the observable behavior a correct implementation must produce. Cover the happy path, the negative / out-of-scope path, and the ambiguous / missing-input path (where the system must ask, not guess).
    • Write each expected behavior so a grader can judge it. These become the golden set at Build: /sdlc-evals turns them into a versioned golden-set.yaml next to the spec (required for llm_powered channels — read the channel's eval_hooks in channels/<id>.yaml so the scenarios cover what the descriptor says must be evaluated). Bizreq owns the scenarios; Data owns the data.

Read the full file on GitHub · 108 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 · 108 lines · 91 tokens per session scan A d45ef2398bc2

Subscribe to this mod's changes

bizreq-analyst is an agent published in the GitHub repository MCKRUZ/claude-code-sdlc (4 stars, last pushed 7d ago), licensed MIT. It adds 91 tokens to every session and 1,792 once invoked, about $0.0005 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

quarto-critic

Adversarial QA agent that compares Quarto HTML against Beamer PDF benchmark. Produces harsh, actionable criticism. Does NOT edit files — read-only analysis only.

brycewang-stanford/Auto-Empirical-Research-Skills · 38 tokens

openwriter-enrichment-minion

Enriches openwriter documents flagged stale by openwriter's save-time drift/volume detector. Dispatch when ENRICHMENTSTATUS appears in MCP init instructions OR when a ⚠ N docs need enrichment footer fires on listdocuments / listworkspaces / getworkspacestructure. Reads each dirty doc and stamps it with a single field…

travsteward/openwriter · 94 tokens

chronology-builder

Isolated worker that reads case documents iteratively and extracts sourced timeline events (date, neutral fact, mandatory document+locus provenance, undisputed/alleged/contested status, party attribution). Deduplicates and cross-references across documents and languages. Emits events.json for the legal-chronology…

fedec65/bettercallclaude · 103 tokens

literature-extractor

Extracts literature Statements from papers for a survey. Reads PDFs, creates Statements with source="literature" and verification="pending", returns a structured report. Never registers theme tags, never creates Warrants or Claims.

yqi96/warranted · 48 tokens

notion

Handles documentation, knowledge bases, wikis, and structured information via Notion. Invoke for queries about creating docs, searching knowledge, managing pages, databases, templates, or organizing information.

tomcounsell/ai · 42 tokens

ollama-transcribe

Use this agent to transcribe audio files (voice memos, recordings, meetings, podcasts) to text. Uses local mlx-whisper. Use whenever the user wants audio converted to text or references an .mp3, .wav, .m4a, .webm file.

PratikHotchandani22/claude-ollama-agents · 62 tokens