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.
git clone --depth 1 https://github.com/AhmedHabiba/architorWrote 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/ahmedhabiba/architor/import-architecture)<a href="https://agentmods.dev/commands/ahmedhabiba/architor/import-architecture"><img src="https://agentmods.dev/badge/commands/ahmedhabiba/architor/import-architecture/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/commands/ahmedhabiba/architor/import-architecture"><img src="https://agentmods.dev/badge/commands/ahmedhabiba/architor/import-architecture.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.00000 | $0.01642 |
| Opus 5 | $0.00000 | $0.00821 |
| Sonnet 5 | $0.00000 | $0.00328 |
| Haiku 4.5 | $0.00000 | $0.00164 |
Grade A, and why
import-architecture 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 10d 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 — 140 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Read .arch/state.json first.
GATE CHECK:
- If
current_phaseis notnot_started, STOP: "Cannot import architecture. Current phase is [phase]. Import is only available at the start of a new project. Use /status to check progress." - If
.arch/existing-architecture.mddoes not exist, STOP: "No import document found. Runarch-agent import <source-file>from CLI first, then use this command."
Read .arch/existing-architecture.md — this is the existing architecture document to import.
Read .arch/org-context.md to check if organizational context is available.
Import Mode — Fast-Track Review
You are importing an existing architecture document. Your job is to:
- Parse the document into architecture sections
- Present each section for review, applying your adversarial reviewer standards
- Progress through all phases using the normal state machine
- Challenge — flag gaps, outdated decisions, missing NFRs, and anti-patterns
The user can /accept phases they're happy with quickly, or /refine phases that need updates.
Step 1: Parse the Document
Analyze the imported document and identify these sections (some may be missing):
- Requirements / PRD content — functional requirements, NFRs, constraints, assumptions
- Architecture pattern — monolith, microservices, event-driven, etc.
- Component map — system components and their boundaries
- Cross-cutting decisions — auth, observability, deployment, error handling, data management
- Component designs — detailed designs for individual components
If sections are missing, note them — you'll flag these as gaps in the appropriate phase.
Step 2: Phase 1 — Evaluate as PRD Analysis
Present the extracted requirements as a Phase 1 evaluation:
- Extract functional requirements (FR-001, FR-002...) from the document
- Extract or infer non-functional requirements
- Identify gaps — what's missing from the existing design?
- Rate risks and overall design completeness
- Be adversarial: "Your existing document says [X], but doesn't address [Y]. What happens when [Z]?"
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.
- 10d ago First seen · 140 lines · 0 tokens per session scan A f4a26be07298
import-architecture is a command published in the GitHub repository AhmedHabiba/architor (6 stars, last pushed 6mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,642 tokens. 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 2026-08-31.
Other commands, from other repositories
learn
Force claude-smart to extract learnings from this session now.
prototype
You are building a proof-of-concept for the current Grainulator sprint. Read CLAUDE.md for sprint context and claims.json for existing research claims.
init
Install the formatters this repository needs, with every command visible before it runs.
brand-generate
Generate an on-brand document from a saved Brand Profile.
genshijin-compress
A command for safely shortening Markdown or text files into the genshijin style.
adr-supersede
Create a new ADR that supersedes an existing one.