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/analyze-prd)<a href="https://agentmods.dev/commands/ahmedhabiba/architor/analyze-prd"><img src="https://agentmods.dev/badge/commands/ahmedhabiba/architor/analyze-prd/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/analyze-prd"><img src="https://agentmods.dev/badge/commands/ahmedhabiba/architor/analyze-prd.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 | $0.01322 |
| Opus 5 | $0.00000 | $0.00661 |
| Sonnet 5 | $0.00000 | $0.00264 |
| Haiku 4.5 | $0.00000 | $0.00132 |
Grade A, and why
analyze-prd 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 9d 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 — 121 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_phase is anything other than not_started or evaluation, STOP and say:
"Cannot start PRD analysis. Current phase is [phase]. Use /status to check progress."
Read the PRD from .arch/prd.md.
Organization Context Check
Read .arch/org-context.md. Check if it is the unmodified template by looking for placeholder text like "[e.g.," or "[Your Organization Name]" or checking if key sections (Team Profile, Current Technology Stack) contain only template instructions.
If org-context.md appears to be filled in (has real values, not template placeholders):
- Set
phases.evaluation.org_context_loaded= true - Set
phases.evaluation.org_context_source= "file" - Proceed to PRD evaluation below
If org-context.md is empty or still has template placeholders:
-
Say: "I notice
.arch/org-context.mdis not filled in. Organizational context directly affects architecture decisions — team size, tech stack, and constraints determine what patterns are feasible.I can either: A. Run a discovery interview (~5 minutes, 15 questions) — I'll generate org-context.md from your answers B. Skip it — I'll proceed with explicit assumptions marked throughout
Which do you prefer?"
If user chooses A (interview), conduct in 3 blocks:
Block 1: Scale & Complexity
- What's your team size? How many developers, DevOps, QA?
- What's the seniority distribution? (mostly senior, mixed, mostly junior)
- What's your current tech stack? (backend language, frontend, database, cloud provider)
- What's your expected scale? (concurrent users, requests/sec, data volume per day)
- Is this greenfield or replacing/extending an existing system?
Present all 5 questions. Wait for answers before proceeding to Block 2.
Block 2: Team Reality
- What technologies has your team successfully operated in production?
- What technologies have you tried and abandoned? Why?
- Do you have dedicated DevOps/Platform/DBA roles, or do developers handle infrastructure?
- What's your CI/CD maturity? (manual deploys, basic pipelines, full GitOps)
- What monitoring/observability do you currently use?
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.
- 9d ago First seen · 121 lines · 0 tokens per session scan A 0f9101066bdd
analyze-prd 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 1,322 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
octo-schedule
Manage scheduled workflow jobs for the Claude Octopus scheduler.
octo-scheduler
Manage the Claude Octopus scheduled workflow runner daemon.
discover
Run a full product discovery cycle — from outcome definition through opportunity mapping, prioritisation, and experiment design. Use when the team isn't sure what to build next, or before writing a PRD for a complex feature space.
specmanager-build
Build one phase of a SpecManager feature's plan via the builder subagent. Stops at the phase boundary; never advances.
execute
Execute the next available tracked task with TDD, pre-commit validation, PR creation, AI code review, and issue tracker bridge sync.
linear-bulk
Apply the same change to many Linear issues at once. Dry-run by default.