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/help)<a href="https://agentmods.dev/commands/ahmedhabiba/architor/help"><img src="https://agentmods.dev/badge/commands/ahmedhabiba/architor/help/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/help"><img src="https://agentmods.dev/badge/commands/ahmedhabiba/architor/help.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 | $0.00565 |
| Opus 5.5 | $0.00000 | $0.00226 |
| Sonnet 5.5 | $0.00000 | $0.00113 |
| Haiku 4.5 | $0.00000 | $0.00056 |
Grade A, and why
help 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.
What it actually says
Read .arch/state.json to determine current phase.
Display available commands and contextual guidance:
ARCHITECTURE AGENT — COMMAND REFERENCE
WORKFLOW COMMANDS:
/analyze-prd Phase 1: Evaluate the PRD
/propose-methodology Phase 2: Architecture pattern (2A), components (2B), cross-cutting (2C)
/design-component [n] Phase 3: Design a specific component in detail
/generate-docs Phase 4: Validate and generate final architecture document
DECISION COMMANDS:
/accept Accept current proposal (phase, sub-phase, or component)
/refine [feedback] Request changes to current proposal
/alternative [request] Request a completely different approach
/reopen [target] [why] Reopen accepted phase/component (max 2 per project)
REVIEW COMMANDS:
/review-component [n] Launch adversarial review of a component
/decision-log [filter] Show all decisions (optional: filter by topic)
/status Show current project state and progress
SETUP:
/help Show this reference
Then based on current phase, show contextual guidance:
If not_started: "Start by placing your PRD in .arch/prd.md and optionally filling out .arch/org-context.md. Then run /analyze-prd. If org-context is empty, the agent will interview you."
If evaluation: "You're in Phase 1. Review the PRD analysis and either /accept, /refine, or provide answers to gap questions."
If methodology: Check sub-phase state:
- If pattern not accepted: "You're in Phase 2A (Pattern). Review the architecture pattern.
/acceptto proceed to 2B, or/refine//alternative." - If pattern accepted but components_overview not accepted: "You're in Phase 2B (Component Map). Review the component overview.
/acceptto proceed to 2C, or/refine." - If components_overview accepted but cross_cutting not accepted: "You're in Phase 2C (Cross-Cutting). Review the cross-cutting decisions.
/acceptto proceed to Phase 3, or/refine."
If components: "You're in Phase 3, designing components one at a time. Use /design-component, /review-component, /accept, or /refine. Use /reopen if a late discovery requires changing an accepted component."
If finalization: "You're in Phase 4. Review the generated document. /accept to complete, or request revisions."
$ARGUMENTS
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 · 45 lines · 0 tokens per session scan A e0c51b00e1f3
help 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 565 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.
help compared with commands from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| helpAhmedHabiba/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 |