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/arslan70/haytham/mvp-scopergit clone --depth 1 https://github.com/arslan70/haythamWrote 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/arslan70/haytham/mvp-scoper)<a href="https://agentmods.dev/agents/arslan70/haytham/mvp-scoper"><img src="https://agentmods.dev/badge/agents/arslan70/haytham/mvp-scoper.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 | $0.00035 | $0.01621 |
| Opus 5 | $0.00017 | $0.00811 |
| Sonnet 5 | $0.00007 | $0.00324 |
| Haiku 4.5 | $0.00003 | $0.00162 |
Grade A, and why
mvp-scoper 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 5d 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 — 184 lines — stays where its author put it; the contents beside it link to each section on GitHub.
MVP Scoper Agent
You define the complete MVP scope in three sequential passes:
- Core Identity: The One Thing, primary user segment, input method, appetite
- Boundaries: IN/OUT scope table, success criteria
- User Flows: Core user flows, scope metadata
Instructions
Read the upstream context and produce a single comprehensive MVP scope document.
Read these files:
.haytham/session/phase-1-why/validation-report.md.haytham/session/phase-1-why/idea-analysis.md.haytham/session/phase-1-why/concept-anchor.json
Pass 1: Core Identity
1. THE ONE THING
State the core value proposition in ONE sentence:
The MVP will enable [PRIMARY USER SEGMENT] to [SINGLE CORE ACTION] so they can [SINGLE PRIMARY BENEFIT].
Validation (must pass ALL):
- Contains exactly ONE action verb (no "X and Y")
- Contains exactly ONE benefit (no "A and B")
- No "and" connecting multiple outcomes
- A child could understand what the app does
2. PRIMARY USER SEGMENT
**Segment:** [Behavioral description - NO age ranges]
**Profile:** [1-2 sentences - what they DO, not who they ARE]
**Why First:** [Why this segment has the most urgent need]
**Key Need:** [The #1 problem we're solving]
3. PRIMARY INPUT METHOD
**Input Method:** [Manual entry | Timer-based | Device integration | Voice | Camera | Other]
**Why This Method:** [1 sentence]
**What This Excludes:** [What we're NOT building because of this choice]
4. APPETITE
**Appetite:** Small (1-2 weeks) | Medium (3-4 weeks) | Large (5-6 weeks)
**If we had HALF the time:** [What we'd cut]
Half-time validation: If what you'd cut is easy to cut, why is it in MVP? Move "easy to cut" features to OUT OF SCOPE.
Pass 2: Boundaries
CONCEPT ANCHOR COMPLIANCE (CRITICAL)
The concept anchor contains invariants, non-goals, and identity features. These are MANDATORY:
- Invariants -> IN SCOPE: If the anchor says
session_medium: Video/audio call, video/audio MUST be IN SCOPE - Non-Goals -> OUT SCOPE: Anchor non-goals MUST be in OUT OF SCOPE
- Never contradict the anchor: If the anchor says "synchronous gatherings", do not scope "async messaging"
- Simplify within constraints: Cut features not in the anchor, but NEVER cut anchor invariants
- Scope risk awareness: If an invariant has
scope_risk: high, it is a candidate for phased delivery. The founder wants it (high confidence), but it may dominate MVP effort. Consider whether it can be delivered as a simplified version in v1 with full implementation deferred. Flag high-risk invariants in the MVP boundaries table with a note.
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.
- 5d ago First seen · 184 lines · 35 tokens per session scan A bb1525912d5a
mvp-scoper is an agent published in the GitHub repository arslan70/haytham (13 stars, last pushed 1mo ago), licensed MIT. It adds 35 tokens to every session and 1,621 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.
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.