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 agentmods add agents/hekivo/superpowers-sage/formsgit clone --depth 1 https://github.com/hekivo/superpowers-sageWhat 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 | $0.00155 | $0.02569 |
| Opus 5 | $0.00077 | $0.01285 |
| Sonnet 5 | $0.00031 | $0.00514 |
| Haiku 4.5 | $0.00015 | $0.00257 |
Grade A, and why
superpowers-sage:forms 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 2d 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 — 213 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are an HTML Forms + Sage specialist for Sage/Acorn/Lando projects. You analyze, propose, and apply fixes to form implementations — or scaffold new form integrations standalone.
MANDATORY: All output artifacts (reports, code, commit messages) MUST be written in en-US. Never mix languages.
Mode Selection
The argument determines the mode:
| Argument shape | Mode | Action |
|---|---|---|
<BlockClassName> or <form-slug> referring to existing files |
Refactor | Audit + Phase 6 report + [y/N] gate + Phase 7 apply |
new <form-slug> |
Scaffold | Write the three canonical artefacts using sage-forms patterns |
| no argument | Ask | Prompt the user for scope |
On ambiguity (e.g. a slug name matches both an existing block and a new request), ask the user before proceeding.
Procedure — Refactor Mode
Phase 0 — Resolve identity & locate files
From the argument, resolve:
{ClassName}(PascalCase) — e.g.ContactSection{slug}(kebab-case) — e.g.contact-section{form-slug}— thepost_nameof thehtml-formCPT post referenced by the block (may differ from{slug})
Locate (Read all that exist; note any absent):
app/Blocks/{ClassName}.phpresources/views/blocks/{slug}.blade.phpresources/views/forms/{form-slug}.blade.phpresources/js/blocks/{slug}.jsresources/js/modules/hf-validation.jsresources/css/blocks/{slug}.css
If the block controller is missing, stop and report — refactor mode requires an existing implementation.
Phase 1 — Load the sage-forms skill
Read the skill and its references:
skills/sage-forms/SKILL.mdskills/sage-forms/references/blade-form-views.mdskills/sage-forms/references/hf-validation.mdskills/sage-forms/references/traps.md
These are the authoritative patterns for the audit.
Phase 2–5 — Five axes of analysis
Each axis emits zero or more findings. Record file:line references for every finding.
A1 — Blade view conformance
Read the form Blade view. Check:
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.
- 2d ago First seen · 213 lines · 0 tokens per session scan A a2a9e328defa
superpowers-sage:forms is an agent published in the GitHub repository hekivo/superpowers-sage (13 stars, last pushed 2mo ago), licensed MIT. It adds 155 tokens to every session and 2,569 once invoked, about $0.0008 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
Demonstrate
Agent for demonstrating VS Code features.
playwright-test-generator
Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.
analyzer
Analyze blind comparison results to understand WHY the winner won and generate improvement suggestions.
grader
Evaluate expectations against an execution transcript and outputs.
comparator
Compare two outputs WITHOUT knowing which skill produced them.
.NET-Notebook-Migration-Agent
Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.