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 takaoumehara/superforge-skill --skill superforge-braingit clone --depth 1 https://github.com/takaoumehara/superforge-skillWrote 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/takaoumehara/superforge-skill/superforge-brain)<a href="https://agentmods.dev/skills/takaoumehara/superforge-skill/superforge-brain"><img src="https://agentmods.dev/badge/skills/takaoumehara/superforge-skill/superforge-brain.svg" alt="Measured on agentmods" 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 | $0.00259 | $0.04976 |
| Opus 5 | $0.00130 | $0.02488 |
| Sonnet 5 | $0.00052 | $0.00995 |
| Haiku 4.5 | $0.00026 | $0.00498 |
Grade A, and why
superforge-brain 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 8d 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 — 375 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Superforge Brain — the BreakBias engine
Most idea generation stops when something plausible arrives. BreakBias does not stop, because stopping is a decision made by whoever got tired first. Instead it enumerates every (element × technique × sub-method) combination as a cell, and a run is finished only when every cell has a terminal status.
Software can hold a 300-cell ledger and never lose its place. A person in a workshop cannot. That asymmetry is the reason to run this as a skill rather than as a meeting.
Lineage. The two floor constraints — Closed World and Function Follows Form — come from SIT (Systematic Inventive Thinking). BreakBias extends it: eight techniques instead of five, a named bias on every element, an explicit ban list that novelty is then scored against, the cell ledger, judgment in a separate context, and a market gate placed after judgment.
0. Iron rules (non-negotiable)
- Closed World — never import an element from outside the system and its immediate boundary. The moment you add something external it stops being non-obvious and becomes an addition anyone could have made.
- Form first — construct the impossible state, withhold judgment, and derive the value backwards. Never reason forward from a benefit.
- Ban the obvious three — list the three answers any model reaches for first and outlaw them before generating. They go into the artifact. The ban applies to generation only: §6 revisits all three once the sweep is done, because the most obvious answer to a problem is often the right one.
- No pruning mid-sweep — deduplication, killing, and scoring happen after generation, never during.
- Never skip a cell — no ellipsis, no "and so on". A cell you did not run is not a cell you decided against.
1. Choose the method — do not assume the full sweep
BreakBias is one way to generate ideas, not the only one this skill offers. Ask once, before generating anything:
What ships with it
11 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
- evals/evals.json 2.8 KB
- README.es.md 11 KB
- README.ja.md 12 KB
- README.ko.md 12 KB
- README.md 10 KB
- README.zh-CN.md 10 KB
- references/classic-methods.md 5.1 KB
- references/idea-map-output.md 11 KB
- references/ideation-tools.md 16 KB
- references/talk-to-users.md 8.0 KB
- references/value-classification.md 9.6 KB
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.
- 8d ago First seen · 375 lines · 259 tokens per session scan A 191b6374863e
superforge-brain is a skill published in the GitHub repository takaoumehara/superforge-skill (1 stars, last pushed 23d ago), licensed MIT. It adds 259 tokens to every session and 4,976 once invoked, about $0.0013 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 2026-08-31.
Other skills, from other repositories
slides
Create and edit presentation slide decks (.pptx) with PptxGenJS, bundled layout helpers, and render/validation utilities. Use when tasks involve building a new PowerPoint deck, recreating slides from screenshots/PDFs/reference decks, modifying slide content while preserving editable output, adding…
lov-media-publisher
A video publishing workflow for the WeChat Channels and Bilibili creator dashboards. It checks media and post fields, handles platform-specific limits and layouts, and reads the submitted details back from the platform.
lov-article-creator
A skill that turns source material or a draft into a complete, branded WeChat public-account article package.
lov-illustrate
A document-illustration workflow that examines a Markdown document, chooses suitable real images, charts, or generated visuals, and inserts them into an enhanced version. Markdown is a plain-text format that uses simple symbols for headings, links, and other document structure.
lov-any2deck
Generate professional slide deck images from content (Markdown, text, URLs). Creates outlines with style instructions, then generates individual slide images. Supports 16 visual styles, CJK/Latin mixed text, branding overlays, and PPTX/PDF export. Use when the user asks to "create slides", "make a presentation"…
lov-bp
Orchestrate a complete investor BP workflow or route to one focused module: source-backed outline, PPTX/PDF production, or evidence/content/visual polishing. Use when the user wants to create a business plan end to end, combine BP stages, continue from an existing BP workspace, or is unsure which BP skill to use.…