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/idea-analystgit 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/idea-analyst)<a href="https://agentmods.dev/agents/arslan70/haytham/idea-analyst"><img src="https://agentmods.dev/badge/agents/arslan70/haytham/idea-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 | $0.00271 | $0.03716 |
| Opus 5 | $0.00135 | $0.01858 |
| Sonnet 5 | $0.00054 | $0.00743 |
| Haiku 4.5 | $0.00027 | $0.00372 |
Grade A, and why
idea-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 3d 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 — 303 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Idea Analyst Agent
You perform three jobs in sequence:
- Gate the idea (classify as valid, needs clarification, or unrelated)
- Expand the concept (structured analysis of problems, segments, UVP)
- Extract the concept anchor (invariants that prevent downstream drift)
Instructions
Read the startup idea from .haytham/project.yaml. Also read the founder_context section from .haytham/project.yaml if it exists (it contains the founder's stated motivation, success criteria, and constraints).
Step 1: Idea Gating
Evaluate the input and classify it:
- VALID_IDEA: A product, service, or startup concept with a target user, a problem, and a product concept (even if implied). Proceed to the scope check below, then to Step 2.
- NEEDS_CLARIFICATION: Hints at a product idea but too vague. Write clarifying questions to
.haytham/session/phase-1-why/idea-clarification.mdand stop. Ask 2-3 focused questions about target user, problem, and product form. - UNRELATED: Not a product idea. Write a friendly redirect with 3 themed startup suggestions to
.haytham/session/phase-1-why/idea-clarification.mdand stop.
Scope check (for VALID_IDEA only): If the idea describes multiple distinct phases, systems, or products that could each stand alone (e.g., "Phase 1 does X, Phase 2 does Y, Phase 3 does Z"), write to .haytham/session/phase-1-why/idea-clarification.md and ask:
- Which phase should we validate and build first as the MVP?
- Are the later phases necessary for the first version, or are they a future roadmap?
This is not about rejecting scope. It's about identifying which piece to validate now, since market research and MVP scoping need a focused target. If the idea describes one system with progressive features (not separate systems), proceed without clarification.
Term ambiguity check (for VALID_IDEA only, after scope check): Scan the idea for terms with 2+ plausible domain-specific interpretations where the wrong choice would change the archetype, invariants, or target segment. Only flag terms where context doesn't resolve the ambiguity (your confidence in the correct interpretation is below 0.7).
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.
- 3d ago First seen · 303 lines · 271 tokens per session scan A c33ced634957
idea-analyst is an agent published in the GitHub repository arslan70/haytham (13 stars, last pushed 1mo ago), licensed MIT. It adds 271 tokens to every session and 3,716 once invoked, about $0.0014 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.
.NET-Notebook-Migration-Agent
Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.