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.
npx skills add hekivo/superpowers-sage --skill buildinggit 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/skills/hekivo/superpowers-sage/building)<a href="https://agentmods.dev/skills/hekivo/superpowers-sage/building"><img src="https://agentmods.dev/badge/skills/hekivo/superpowers-sage/building/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/skills/hekivo/superpowers-sage/building"><img src="https://agentmods.dev/badge/skills/hekivo/superpowers-sage/building.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 | $0.00139 | $0.03461 |
| Opus 5 | $0.00069 | $0.01731 |
| Sonnet 5 | $0.00028 | $0.00692 |
| Haiku 4.5 | $0.00014 | $0.00346 |
Grade A, and why
superpowers-sage:building 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 — 321 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Building — Plan-Driven Implementation
Implement Sage components by reading from plan directories, consulting design assets, and verifying after each component.
Announce at start: "I'm using the building skill to implement from the plan."
Inputs
$ARGUMENTS
If a plan path is provided, read the plan. Otherwise, check for active plan in docs/plans/.
Procedure
0) Load the plan
- Read
plan.mdfrontmatter for strategy, components, design-tool - Read
architecture.mdfor architectural decisions - Read
content-model.mdfor data modeling decisions - List
components/for sub-plans - List
assets/for design reference images
If no plan exists, suggest running /architecture-discovery then /plan-generator first.
1) Set up prerequisites
Based on content model:
- If CPTs needed → configure
config/poet.php - If new packages needed →
lando theme-composer require <package> - If Options Pages needed → create ACF Options class
- Run
lando flushafter PHP changes
2) Implement components (per sub-plan)
Design system gate (runs once, before the component loop):
Check that the visual foundation exists:
resources/css/design-tokens.css— must exist and contain real tokens (not placeholder)- Route
/kitchensink— must be accessible and visually validated (Playwright screenshot taken)
If either is missing or unvalidated → invoke /sage-design-system and pause until the kitchensink screenshot confirms all tokens and UI atoms render correctly. Do NOT implement any block without a validated design system.
For each component in order:
0) Pre-fetch design reference, THEN dispatch design-extractor
CRITICAL: subagents do NOT inherit MCP tools from the calling session. Dispatching
design-extractor without first persisting design data to disk produces fabricated specs
with VERIFY placeholders and estimated values.
Inversion pattern — always pre-fetch in THIS thread before dispatching:
- With the MCP tool available in this session, capture reference data to disk:
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 · 321 lines · 139 tokens per session scan A bd8261af9b04
superpowers-sage:building is a skill published in the GitHub repository hekivo/superpowers-sage (13 stars, last pushed 3mo ago), licensed MIT. It adds 139 tokens to every session and 3,461 once invoked, about $0.0007 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 skills, from other repositories
visual-ralph
Visual Ralph orchestration for frontend UI from generated references, static references, or live URL targets, using $ralph with built-in visual verdict and pixel-diff evidence until the implementation matches and leaves a reproducible design system.
repro-admin
Reproduce an EmDash admin UI bug. Attach a container, start the demo dev server, drive the admin with agent-browser using the dev-bypass session, and capture the reproduction as screenshots plus a replayable transcript.
create-site
Creates a new Power Pages code site (SPA) using React, Angular, Vue, or Astro. Guides through the full process from initial concept to deployed site: requirements discovery, scaffolding, component planning, design, implementation, validation, and deployment. Use when the user wants to create, build, or scaffold a new…
prototype-web
A clickable, high-fidelity web product prototype with navigation, a hero section, feature cards, steps, social proof, and optional pricing. It is designed to resemble a finished landing page while remaining a prototype.
menu-transitions-rtl
Animate react-horizontal-scrolling-menu scrolling and build right-to-left menus: noPolyfill defaults to true since v8, so transitionDuration (default 500), a custom-easing-function transitionBehavior, and per-call ScrollOptions { duration, boundary } on scrollToItem/scrollNext/scrollPrev are silently ignored unless…
vite
Vite build tool configuration, plugin API, SSR, and Vite 8 Rolldown migration. Use when working with Vite projects, vite.config.ts, Vite plugins, or building libraries/SSR apps with Vite.