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/generate-docs)<a href="https://agentmods.dev/commands/ahmedhabiba/architor/generate-docs"><img src="https://agentmods.dev/badge/commands/ahmedhabiba/architor/generate-docs/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/generate-docs"><img src="https://agentmods.dev/badge/commands/ahmedhabiba/architor/generate-docs.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 | $0.01373 |
| Opus 5.5 | $0.00000 | $0.00549 |
| Sonnet 5.5 | $0.00000 | $0.00275 |
| Haiku 4.5 | $0.00000 | $0.00137 |
Grade A, and why
generate-docs 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 2mo 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 — 164 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_phaseisfinalizationandphases.finalization.document_generatedis true: Say "Document already generated. Do you want to regenerate? Say 'yes' to regenerate or review the existing document atoutput/architecture-document.md." - If
current_phaseis notcomponentsandcurrent_phaseis notfinalization, STOP: "Cannot generate documentation. Current phase is [phase]." - If
current_phaseiscomponentsandphases.components.all_acceptedis nottrue, STOP: "All components must be accepted before generating documentation. Use /status to check which components are pending."
Read ALL architecture files:
.arch/phase1-evaluation.md.arch/phase2-methodology.md.arch/phase2-components-overview.md.arch/phase2-cross-cutting.md(if exists)- All files in
.arch/components/ - All files in
.arch/reviews/(if any) .arch/decisions.md.arch/org-context.md
Pre-Generation Validation
Before generating the document, perform these validation steps:
1. End-to-End Request Simulation
Trace 3 critical user journeys through the accepted component designs:
- Happy path: The most common user action — trace through every component it touches
- Error path: What happens when a key dependency fails — verify fallback/circuit breaker coverage
- Scale path: What happens at 10x expected load — verify scaling strategy holds
For each journey, verify:
- Every integration point between components is specified in both directions
- Data formats match (producer format = consumer expected format)
- Authentication/authorization is checked at every boundary
- Error handling is specified at every failure point
2. Risk Register
Create a risk register with probability x impact scoring:
| # | Risk | Probability (1-5) | Impact (1-5) | Score | Mitigation | Owner |
|---|
Include at minimum: technology risks, integration risks, operational risks, scale risks, security risks.
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.
- 2mo ago First seen · 164 lines · 0 tokens per session scan A a5ec7239af16
generate-docs is a command published in the GitHub repository AhmedHabiba/architor (6 stars, last pushed 7mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,373 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.
generate-docs compared with commands from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| generate-docsAhmedHabiba/architor | Command | 6 | 7mo ago | MIT | A | 0 | Claude Code |
| learnReflexioAI/claude-smart | Command | 791 | 4d ago | Apache-2.0 | A | 14 | Claude Code |
| prototypegrainulation/grainulator | Command | 86 | yesterday | MIT | A | 0 | Claude Code |
| initazrtydxb/procoder | Command | 211 | 11d ago | Apache-2.0 | A | 16 | Claude Code |
| genshijin-compressInterfaceX-co-jp/genshijin | Command | 331 | 27d ago | MIT | A | 17 | Claude Code |
| responsive-design-specialistimsaif/design-with-claude | Command | 11 | 2d ago | MIT | A | 36 | Claude Code |
| brand-generateferdinandobons/brand-docs | Command | 291 | 4mo ago | MIT | A | 0 | Claude Code |