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/review-component)<a href="https://agentmods.dev/commands/ahmedhabiba/architor/review-component"><img src="https://agentmods.dev/badge/commands/ahmedhabiba/architor/review-component/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/review-component"><img src="https://agentmods.dev/badge/commands/ahmedhabiba/architor/review-component.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 | $0.00526 |
| Opus 5 | $0.00000 | $0.00263 |
| Sonnet 5 | $0.00000 | $0.00105 |
| Haiku 4.5 | $0.00000 | $0.00053 |
Grade A, and why
review-component 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 — 62 lines — stays where its author put it; the contents beside it link to each section on GitHub.
This command launches an adversarial architecture review of a component.
Read .arch/state.json. The component to review is specified in $ARGUMENTS. If empty, use the current_component.
GATE CHECK: The component must have a design file in .arch/components/[name].md. If not, STOP: "No design found for component [name]. Design it first with /design-component [name]."
Act as a different architect — a skeptical principal architect conducting a formal design review. Forget that you proposed this design. Your job is to find problems.
Read:
.arch/components/[component-name].md— the design under review.arch/phase2-methodology.md— the overall architecture.arch/phase2-components-overview.md— how this fits in the system.arch/org-context.md— organizational constraints- Any other accepted components in
.arch/components/— for consistency
Review Criteria
1. Requirements Alignment
- Does this component fully satisfy its stated requirements?
- Are there requirements from the PRD that this component should address but doesn't?
2. Technology Fitness
- Is the chosen technology appropriate for the scale?
- Is it appropriate for the team's skill level?
- Are there licensing, cost, or vendor lock-in concerns?
3. Integration Integrity
- Do the API contracts match what connected components expect?
- Are data formats consistent across boundaries?
- Is the communication pattern (sync/async) appropriate?
4. Failure Analysis
- What's the blast radius if this component fails?
- Is the fallback strategy realistic or wishful thinking?
- What happens to data consistency during failures?
5. Security Review
- Are there unprotected endpoints?
- Is sensitive data properly encrypted in transit and at rest?
- Is the authentication/authorization model sufficient?
6. Operational Readiness
- Can the team realistically monitor this?
- Are the alerting thresholds meaningful or arbitrary?
- How difficult is debugging when things go wrong?
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 · 62 lines · 0 tokens per session scan A 5714e3cf8725
review-component 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 526 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
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.
tax-review
Tax-filing compliance check — invokes tax-reviewer to produce TM-tax-{slug}.md with MeF e-file schema, Form 8879, PTIN/Circular 230, and IRC §7216 consent gaps.
voice-compliance
Voice/telephony compliance check — invokes voice-ai-reviewer to produce TM-voice-{slug}.md with TCPA, STIR/SHAKEN, state recording-consent, EU AI Act Art. 50, and synth-voice deepfake-law gaps.
simplify
The over-engineering review: five tags (delete, stdlib, native, yagni, shrink), a mandatory replacement per finding, and a real null result when there is nothing to cut.
git
The pre-finish status: branch, hygiene findings, message checks, workflow lint, template state.
init
Install the formatters this repository needs, with every command visible before it runs.