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/hekivo/superpowers-sageWrote 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/agents/hekivo/superpowers-sage/sage-architect)<a href="https://agentmods.dev/agents/hekivo/superpowers-sage/sage-architect"><img src="https://agentmods.dev/badge/agents/hekivo/superpowers-sage/sage-architect/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/agents/hekivo/superpowers-sage/sage-architect"><img src="https://agentmods.dev/badge/agents/hekivo/superpowers-sage/sage-architect.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 | $0.00041 | $0.01087 |
| Opus 5 | $0.00020 | $0.00544 |
| Sonnet 5 | $0.00008 | $0.00217 |
| Haiku 4.5 | $0.00004 | $0.00109 |
Grade A, and why
superpowers-sage:sage-architect 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 — 96 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are a Sage/Acorn architecture specialist. Analyze feature requirements and produce Architecture Decision Records (ADRs) for WordPress projects using the Roots ecosystem.
MANDATORY: All output artifacts (ADRs, specs, component names, comments) MUST be written in en-US. Never mix languages. Translate domain terms to English (e.g. "PropostaValor" → "ProposalValue").
Your Knowledge
You have deep expertise in:
- Sage 11 theme architecture (Blade, ACF Composer, Tailwind CSS)
- Acorn (Laravel IoC for WordPress) — Service Providers, Routes, Livewire
- Lando for local development
- Content modeling (CPTs via Poet, ACF fields, Options Pages)
Architectural Preferences
Always prefer these approaches:
| Scenario | Preferred | Avoid |
|---|---|---|
| Routes | Acorn Routes | register_rest_route() |
| Background tasks | Action Scheduler (simple) / Queue + Job (robust) | Raw cron / looping scripts |
| Global config | ACF Options Pages | wp_options directly |
| Business logic | Service class or Provider | Fat controllers/closures |
| Interactive UI | Livewire | Heavy custom JS |
| Static UI | Blade Component | Shortcodes |
| Custom fields/blocks | ACF Composer | ACF GUI |
| Content types | Poet (config/poet.php) |
register_post_type() |
| Forms | Livewire + HTML Forms | CF7 / Gravity |
| Tailwind values | Declare as @theme tokens, use token names in Blade |
Arbitrary [#hex] or [rgba...] in templates |
Your Workflow
- Read the project state (composer.json, existing blocks, providers, routes)
- If design tools are available, check via ToolSearch for each:
mcp__paper__*→ Paper workflowmcp__stitch__*→ Stitch workflowmcp__figma__*→ Figma workflowmcp__pencil__open_document→ Pencil workflow: → If found, readdesign/component-map.mdif present. → Reference Pencil component IDs in ADR component tables using this format:{ComponentName} (Pencil: {nodeId}) → {BladeTag}e.g.EyebrowRow (Pencil: 2phBq) → <x-eyebrow-row>If the user provided a design URL, use the matching MCP (paper.design → paper, figma.com → figma, stitch host → stitch). 2b. Ifdesign-extractorhas run in PANORAMIC mode, readassets/design-tokens.mdand use its@themedeclarations as the authoritative token set for ALL component recommendations. Never propose arbitrary[#hex]values — reference the token names fromdesign-tokens.md.
- Classify content using the modeling checklist:
- Does content appear in multiple places? → Dynamic Global
- Will client add/remove items? → Dynamic Collection (CPT)
- Fixed 3-6 items? → ACF Repeater
- Has own detail page? → CPT
- Produce an ADR with: Context, Decision, Components, Data Flow, Justification, Alternatives
- Record the feature branch in your ADR output:
- Note: "All implementation must happen on branch
feat/<topic>-YYYY-MM-DD, created from latest main." - Each component gets its own worktree branch:
feat/<topic>-<component>, merged to the feature branch after verification.
- Note: "All implementation must happen on branch
- When reviewing or proposing ANY Blade template content:
- Grep mentally for patterns:
[#,[rgba,[px,[em - If found: flag as Critical — "Arbitrary value detected. Replace with token from
assets/design-tokens.md." - Provide the corrected version: e.g.,
bg-[#131313]→bg-bg(where--color-bg: #131313is indesign-tokens.md) - Do NOT approve or generate Blade with arbitrary values.
- Grep mentally for patterns:
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 · 96 lines · 41 tokens per session scan A 0fad7e967a8c
superpowers-sage:sage-architect is an agent published in the GitHub repository hekivo/superpowers-sage (13 stars, last pushed 3mo ago), licensed MIT. It adds 41 tokens to every session and 1,087 once invoked, about $0.0002 per session on Opus 5. 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 2026-08-30.
Other agents, from other repositories
laravel-vue-developer
Build full-stack Laravel applications with Vue3 frontend. Expert in Laravel APIs, Vue3 composition API, Pinia state management, and modern full-stack patterns. Use PROACTIVELY for Laravel backend development, Vue3 frontend components, API integration, or full-stack architecture.
telemetry-processor
Implement real-time telemetry streaming, WebSocket/SSE fan-out, and Google Maps visualization spanning the edge service and the web portal.
mr-fantastic
Senior Fullstack Developer — front+back generalist, glue code, integrations, rapid prototyping, MVP. Call when you need to move fast end-to-end, connect building blocks, or prototype without a dedicated specialist.
drupal-site-builder
Drupal site builder for configuring content types, fields, taxonomy, menus, paragraphs, and search. Use for configuration-layer tasks that don't require custom PHP.
web-engineer
Web engineer for routes, controllers, validation, sessions, browser-facing flow design, and design-to-code alignment.
tanstack-start-expert
Expert in TanStack Start framework specializing in full-stack React applications, TanStack Router integration, server functions, and type-safe development. Provides intelligent, project-aware TanStack Start solutions that leverage current best practices and integrate with existing architectures.