specify

A guided workflow for defining an MVP's scope and capabilities after an idea has been validated. MVP means the smallest planned version of a product that can be built and assessed.

In plain words
What is it for?
Use it to define MVP scope, review that scope, model the product's capabilities, and record the resulting decisions. It requires the preceding validation phase.
Why use it?
It turns a validated idea into a concrete list of what the first version should include, with review gates before moving on.

Command

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 commands/arslan70/haytham/specify
Clone the repo
git clone --depth 1 https://github.com/arslan70/haytham
Per session 18 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 3,158 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 $0.00018 $0.03158
Opus 5 $0.00009 $0.01579
Sonnet 5 $0.00004 $0.00632
Haiku 4.5 $0.00002 $0.00316

Measured 2d ago against content hash 18112b7e3ea5, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

specify 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.

commands/specify.md · 200 lines

How it starts

The opening of the file, as written. The whole thing — 200 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Haytham: MVP Specification (Phase 2 - WHAT)

You are running Phase 2 of the Haytham validation workflow. This phase defines what the MVP includes and models its capabilities.

IMPORTANT: Always read agent output from files, not from conversation history.

Progress Tracking

After prerequisites pass, call TodoWrite once with:

  1. Step 1 — MVP scope
  2. Step 2 — Scope review (founder)
  3. Step 3 — Capability model
  4. Step 4 — Capability review (checker)
  5. Step 5 — Gate 2

Mark each todo in_progress when its step begins and completed when its output file is written or its gate decision is recorded. If the founder requests scope or capability revisions, set the relevant todo back to in_progress for the re-run.

Prerequisites

Verify .haytham/session/phase-1-why/gate-decision.json exists. If it doesn't, tell the user:

"Phase 1 (validation) must be completed first. Run /haytham:validate to start."

Read the gate decision. If the recommendation was NO-GO and the user didn't override, warn:

"Phase 1 recommended NO-GO. Are you sure you want to proceed with MVP specification?"

Roadmap

Before launching any agents, tell the user:

Phase 2: MVP Specification

This will run 5 steps:

  1. MVP Scope — define what's in, what's out, and the core flows (~1 min)
  2. Scope Review — you shape the scope before capabilities are derived ← YOU STEER HERE
  3. Capability Model — extract capabilities and system traits from your approved scope (~1 min)
  4. Capability Review — an adversarial pass hunts for gaps in the model (~1 min)
  5. Gate 2 — you approve the final capabilities ← YOU DECIDE HERE

Estimated total: ~5 minutes.

Step 1: MVP Scope

Create .haytham/session/phase-2-what/ directory if it doesn't exist.

Tell the user:

Step 1/5: MVP Scope Translating the validated idea into a concrete MVP definition. What's in, what's out, and what the core user flow looks like.

Launch an mvp-scoper agent with this task:

Read the validation report from .haytham/session/phase-1-why/validation-report.md, idea analysis from .haytham/session/phase-1-why/idea-analysis.md, and concept anchor from .haytham/session/phase-1-why/concept-anchor.json. Define the MVP scope. Write to .haytham/session/phase-2-what/mvp-scope.md.

Read the full file on GitHub · 200 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 · 200 lines · 18 tokens per session scan A 18112b7e3ea5

Subscribe to this mod's changes

specify is a command published in the GitHub repository arslan70/haytham (13 stars, last pushed 1mo ago), licensed MIT. It adds 18 tokens to every session and 3,158 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 2026-08-30.