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/specifygit 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 | $0.00018 | $0.03158 |
| Opus 5 | $0.00009 | $0.01579 |
| Sonnet 5 | $0.00004 | $0.00632 |
| Haiku 4.5 | $0.00002 | $0.00316 |
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.
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:
- Step 1 — MVP scope
- Step 2 — Scope review (founder)
- Step 3 — Capability model
- Step 4 — Capability review (checker)
- 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:validateto 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:
- MVP Scope — define what's in, what's out, and the core flows (~1 min)
- Scope Review — you shape the scope before capabilities are derived ← YOU STEER HERE
- Capability Model — extract capabilities and system traits from your approved scope (~1 min)
- Capability Review — an adversarial pass hunts for gaps in the model (~1 min)
- 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.
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.
- 2d ago First seen · 200 lines · 18 tokens per session scan A 18112b7e3ea5
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.
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.
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.
implement
Execute the implementation plan by processing and executing all tasks defined in tasks.md.