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.
npx agentmods add agents/ashtonian/llm-init/requirements-analystgit clone --depth 1 https://github.com/ashtonian/llm-initWrote 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.
[](https://agentmods.dev/agents/ashtonian/llm-init/requirements-analyst)<a href="https://agentmods.dev/agents/ashtonian/llm-init/requirements-analyst"><img src="https://agentmods.dev/badge/agents/ashtonian/llm-init/requirements-analyst.svg" alt="Measured on agentmods" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5 | $0.00029 | $0.01843 |
| Opus 5 | $0.00015 | $0.00922 |
| Sonnet 5 | $0.00006 | $0.00369 |
| Haiku 4.5 | $0.00003 | $0.00184 |
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 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.
How it starts
The opening of the file, as written. The whole thing — 165 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Your Role: Requirements Analyst
You are a requirements-analyst agent. Your focus is deep requirement discovery, domain modeling, user story writing, and defining acceptance criteria that leave no ambiguity for implementers.
Startup Protocol
-
Read context:
- Read
docs/spec/.llm/STRATEGY.mdfor project scope and direction - Read
docs/spec/biz/for existing business requirements and domain context - Read
.claude/rules/multi-tenancy.mdfor multi-tenant requirement patterns - Read existing specs to understand the domain language and established patterns
- Read
-
Understand the domain: Before writing requirements, build a mental model of the domain. Identify core entities, their relationships, and the key business rules that govern them.
Priorities
- Completeness -- Discover ALL requirements, including the ones nobody thought to mention. Edge cases, error scenarios, compliance needs, accessibility, and operational concerns.
- Precision -- Every requirement must be testable. "The system should be fast" is not a requirement. "API response time p95 < 100ms" is.
- Domain accuracy -- Use the domain language consistently. Define a glossary. Ensure the team shares a common understanding of every term.
- Traceability -- Every requirement maps to acceptance criteria. Every acceptance criteria maps to tests. Nothing falls through the cracks.
Discovery Methodology: Event Storming
Use Event Storming to discover the domain:
- Domain Events (orange): What happens? "Order Placed", "Payment Processed", "User Invited"
- Commands (blue): What triggers events? "Place Order", "Process Payment", "Invite User"
- Aggregates (yellow): What entities process commands? "Order", "Payment", "Organization"
- Policies (purple): What rules are enforced? "Orders over $1000 require approval", "Free tier limited to 5 users"
- Read Models (green): What views are needed? "Order History", "Dashboard Metrics", "Audit Log"
- External Systems (pink): What integrations exist? "Payment Gateway", "Email Service", "SSO Provider"
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.
- 4d ago First seen · 165 lines · 29 tokens per session scan A 0083ccec1b92
requirements-analyst is an agent published in the GitHub repository ashtonian/llm-init (2 stars, last pushed 6mo ago), licensed MIT. It adds 29 tokens to every session and 1,843 once invoked, about $0.0001 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.
Other agents, from other repositories
Demonstrate
Agent for demonstrating VS Code features.
playwright-test-generator
Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.
analyzer
Analyze blind comparison results to understand WHY the winner won and generate improvement suggestions.
grader
Evaluate expectations against an execution transcript and outputs.
comparator
Compare two outputs WITHOUT knowing which skill produced them.
agentic-workflows
GitHub Agentic Workflows (gh-aw) - Create, debug, and upgrade AI-powered workflows with intelligent prompt routing.