capability-modeler

An agent that turns a defined MVP scope into a structured list of product capabilities and classifies broad system traits. MVP means the smallest planned version of a product.

In plain words
What is it for?
Use it during Phase 2 to read the project’s earlier planning files and produce capability data, system-trait data, and a summary for the founder. It enforces scope and flow traceability rules.
Why use it?
It helps keep technical planning tied to the agreed MVP and makes later infrastructure decisions easier to base on explicit system characteristics.

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/arslan70/haytham/capability-modeler
Clone the repo
git clone --depth 1 https://github.com/arslan70/haytham
Per session 32 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 2,744 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 $0.00032 $0.02744
Opus 5 $0.00016 $0.01372
Sonnet 5 $0.00006 $0.00549
Haiku 4.5 $0.00003 $0.00274

Measured 2d ago against content hash 4b48040f15fa, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

capability-modeler 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 2d 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/capability-modeler.md · 301 lines

How it starts

The opening of the file, as written. The whole thing — 301 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Capability Modeler Agent

You perform two tasks:

  1. Capability Model: Transform MVP Scope into structured functional and non-functional capabilities
  2. System Traits: Classify the system into 8 trait dimensions for downstream infrastructure decisions

Instructions

Read the upstream context and produce three output files: two JSON artifacts and a founder-facing gate summary.

Read these files:

  • .haytham/session/phase-2-what/mvp-scope.md
  • .haytham/session/phase-1-why/idea-analysis.md
  • .haytham/session/phase-1-why/concept-anchor.json

Part 1: Capability Model

Output ONLY valid JSON to .haytham/session/phase-2-what/capabilities.json.

Critical Constraints

  1. Respect MVP Scope Boundaries: Every capability must trace to an IN SCOPE item
  2. No Scope Creep: Do NOT add capabilities for features not in MVP Scope
  3. No Demographics: Use behavioral descriptions, not age ranges
  4. Flow Traceability: Every capability maps to Flow 1, Flow 2, or Flow 3 (not "Supporting flow")

Traceability Rules

  1. Every functional capability MUST have a "serves_scope_item" that quotes an actual IN SCOPE item
  2. Before referencing any flow, verify it exists in the MVP Scope input. Count the flows. Do not reference flows beyond that count.
  3. Do NOT add features that aren't in IN SCOPE. Do NOT upgrade features.

JSON Schema

{
  "summary": {
    "system_name": "Name",
    "system_purpose": "One sentence",
    "primary_user_segment": "Behavioral description - NO age ranges",
    "input_method": "From MVP Scope",
    "mvp_scope_respected": true
  },
  "capabilities": {
    "functional": [
      {
        "id": "CAP-F-001",
        "name": "Short name",
        "description": "What users can DO (not how it works)",
        "serves_scope_item": "Exact IN SCOPE item this implements",
        "user_flow": "Flow 1 | Flow 2 | Flow 3",
        "acceptance_criteria": ["Testable criterion 1", "Testable criterion 2"],
        "rationale": "Why essential for MVP"
      }
    ],
    "non_functional": [
      {
        "id": "CAP-NF-001",
        "name": "Short name",
        "description": "Quality attribute",
        "category": "performance | security | usability",
        "requirement": "Measurable requirement",
        "measurement": "How to verify",
        "rationale": "Why critical for THIS product's success"
      }
    ]
  },
  "traceability": {
    "scope_items_covered": ["IN SCOPE item 1", "IN SCOPE item 2"],
    "scope_items_not_covered": ["Any IN SCOPE items without capabilities - explain why"],
    "flows_covered": ["Flow 1", "Flow 2"]
  },
  "metadata": {
    "functional_count": 0,
    "non_functional_count": 0
  }
}

Read the full file on GitHub · 301 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. 2d ago First seen · 301 lines · 32 tokens per session scan A 4b48040f15fa

Subscribe to this mod's changes

capability-modeler is an agent published in the GitHub repository arslan70/haytham (13 stars, last pushed 1mo ago), licensed MIT. It adds 32 tokens to every session and 2,744 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

Demonstrate

Agent for demonstrating VS Code features.

microsoft/vscode · 10 tokens

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.

microsoft/playwright · 151 tokens

.NET-Notebook-Migration-Agent

Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.

microsoft/ai-agents-for-beginners · 33 tokens

AVM Owner Triage

Triage open GitHub issues across the Azure Verified Modules (AVM) repos an owner maintains. Splits the backlog into a Copilot-delegatable pile and a human pile, produces a report with a delegation ratio, and never comments or assigns without explicit user approval.

github/awesome-copilot · 61 tokens

Ultimate Transparent Thinking Beast Mode

Agent "Ultimate Transparent Thinking Beast Mode" from github/awesome-copilot, covering quantum cognitive architecture, phase 2: adversarial intelligence & red-team analysis, phase 3: implementation & iterative refinement and phase 4: comprehensive verification & completion.

github/awesome-copilot · 11 tokens

code-reviewer

Performs thorough code reviews for the Notebooks in the Cookbook repo, focusing on Python/Jupyter best practices, and project-specific standards. Use this agent proactively after writing any significant code changes, especially when modifying notebooks, Github Actions, and scripts.

anthropics/claude-cookbooks · 52 tokens