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 commands/arslan70/haytham/haythamgit 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/commands/arslan70/haytham/haytham)<a href="https://agentmods.dev/commands/arslan70/haytham/haytham"><img src="https://agentmods.dev/badge/commands/arslan70/haytham/haytham.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 | $0.00010 | $0.09715 |
| Opus 5 | $0.00005 | $0.04858 |
| Sonnet 5 | $0.00002 | $0.01943 |
| Haiku 4.5 | $0.00001 | $0.00971 |
Grade A, and why
haytham 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 — 759 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Haytham: Startup Idea Validation & Specification
You are orchestrating a 4-phase startup validation workflow. Follow each phase in order. Do not skip phases. In normal mode, do not proceed to the next phase without user approval at the gate. In BATCH_MODE, auto-approve all gates and skip all interactive review steps.
IMPORTANT: Always read agent output from files, not from conversation history. Before each phase, verify previous phase output files exist by reading them.
Progress Tracking
After the Setup section completes, call TodoWrite once to register the full pipeline as todos. Use these exact items:
- Phase 1 — Idea validation (WHY)
- Phase 1 gate — founder approves verdict
- Phase 2 — MVP scope & capabilities (WHAT)
- Phase 2 gate — founder approves capabilities
- Phase 3 — Architecture (HOW)
- Phase 3 gate — founder approves design
- Phase 4 — OpenSpec generation
- Final review
Mark the active item in_progress when starting the phase and completed when its output files are written and the digest is shown. Only one item in_progress at a time. If a gate triggers a re-run of the preceding phase, set that phase back to in_progress.
Upstream Dependencies
| Phase | Agent | Reads From |
|---|---|---|
| 1 | idea-analyst | .haytham/project.yaml (user input) |
| 1 | market-researcher | phase-1-why/idea-analysis.md, phase-1-why/concept-anchor.json |
| 1 | competitor-researcher | phase-1-why/idea-analysis.md, phase-1-why/concept-anchor.json |
| 1 | research-briefer | phase-1-why/idea-analysis.md, phase-1-why/market-research.md, phase-1-why/competitor-research.md |
| 1 | report-synthesizer | phase-1-why/research-brief.md, phase-1-why/concept-anchor.json, phase-1-why/competitor-research.md, phase-1-why/founder-corrections.json (if exists), references/benchmarks.md |
| 2 | mvp-scoper | phase-1-why/validation-report.md, phase-1-why/idea-analysis.md, phase-1-why/concept-anchor.json |
| 2 | capability-modeler | phase-2-what/mvp-scope.md, phase-1-why/idea-analysis.md, phase-1-why/concept-anchor.json |
| 2 | capability-checker | phase-2-what/mvp-scope.md, phase-2-what/capabilities.json, phase-1-why/concept-anchor.json |
| 3 | architect | phase-2-what/capabilities.json, phase-2-what/system-traits.json, phase-2-what/mvp-scope.md |
| 4 | spec-generator | phase-2-what/capabilities.json, phase-2-what/mvp-scope.md, phase-2-what/system-traits.json, phase-3-how/architecture-decisions.json, phase-3-how/build-buy.json, phase-1-why/concept-anchor.json |
| 5 | build (command) | phase-4-specs/openspec/, phase-3-how/research-directives.json |
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 · 759 lines · 10 tokens per session scan A 4bea541e9aa7
haytham is a command published in the GitHub repository arslan70/haytham (13 stars, last pushed 1mo ago), licensed MIT. It adds 10 tokens to every session and 9,715 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.
Other commands, from other repositories
checklist
Generate a custom checklist for the current feature based on user requirements.
clarify
Identify underspecified areas in the current feature spec by asking up to 5 highly targeted clarification questions and encoding answers back into the spec.
specify
Create or update the feature specification from a natural language feature description.
converge
Assess the current codebase against the feature's spec, plan, and tasks, then append any remaining unbuilt work as new tasks to tasks.md so implement can complete it.
implement
Execute the implementation plan by processing and executing all tasks defined in tasks.md.
analyze
Perform a non-destructive cross-artifact consistency and quality analysis across spec.md, plan.md, and tasks.md after task generation.