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/designgit clone --depth 1 https://github.com/arslan70/haythamWhat 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 | $0.00016 | $0.01205 |
| Opus 5 | $0.00008 | $0.00602 |
| Sonnet 5 | $0.00003 | $0.00241 |
| Haiku 4.5 | $0.00002 | $0.00120 |
Grade A, and why
design 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 — 105 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Haytham: Technical Design (Phase 3 - HOW)
You are running Phase 3 of the Haytham validation workflow. This phase decides on infrastructure and architecture.
IMPORTANT: Always read agent output from files, not from conversation history.
Progress Tracking
After prerequisites pass, call TodoWrite once with:
- Step 1 — Architecture (build/buy, decisions, research directives)
- Step 2 — Review
- Step 3 — Gate 3
Mark each todo in_progress when its step begins and completed when its output file is written or its gate decision is recorded.
Prerequisites
Verify .haytham/session/phase-2-what/gate-decision.json exists. If it doesn't, tell the user:
"Phase 2 (MVP specification) must be completed first. Run
/haytham:specifyto start."
Roadmap
Before launching any agents, tell the user:
Phase 3: Technical Design
This will run 3 steps:
- Architecture — build/buy analysis and technology decisions (~2 min)
- Review — you review the architecture
- Gate 3 — you approve the design ← YOU DECIDE HERE
Estimated total: ~3 minutes.
Step 1: Architecture
Create .haytham/session/phase-3-how/ directory if it doesn't exist.
Tell the user:
Step 1/3: Architecture Deciding what to build, what to buy, and how the pieces fit together.
Launch an architect agent with this task:
Read capabilities from
.haytham/session/phase-2-what/capabilities.json, MVP scope from.haytham/session/phase-2-what/mvp-scope.md, and system traits from.haytham/session/phase-2-what/system-traits.json. Produce build/buy analysis, architecture decisions, research directives, and the founder-facing gate summary. Write to.haytham/session/phase-3-how/build-buy.json,.haytham/session/phase-3-how/architecture-decisions.json,.haytham/session/phase-3-how/research-directives.json, and.haytham/session/phase-3-how/gate-summary.md.
After the agent completes, read .haytham/session/phase-3-how/build-buy.json, .haytham/session/phase-3-how/architecture-decisions.json, and .haytham/session/phase-3-how/research-directives.json and present a structured digest:
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 · 105 lines · 16 tokens per session scan A 57ba28df9a5c
design is a command published in the GitHub repository arslan70/haytham (13 stars, last pushed 1mo ago), licensed MIT. It adds 16 tokens to every session and 1,205 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
git
Git operations with intelligent commit messages and workflow optimization.
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.
analyze
Perform a non-destructive cross-artifact consistency and quality analysis across spec.md, plan.md, and tasks.md after task generation.
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.