neuron-explorer
Qwen3.5‑4B 전용 조향형 뉴런 탐색기, 모든 MLP 뉴런을 밀어 결과를 보관·탐색
구축 전에 판매: CLI와 에이전트 기능으로 코딩 에이전트가 실제 구매자를 조사하고 검증된 랜딩 페이지를 제공합니다
Sell before you build: a CLI and agent skills that make your coding agent research real buyers and ship one checked landing page. Looking for more. Looking for money.
개발 도구Go · JavaScriptGitHub @Anonyfox온라인운영자 미확인
써 보셨어요? 한 번만 눌러 주세요. 로그인은 필요 없어요.
메이커가 쓴 소개는 위의 한 줄이 전부입니다. 더 자세한 내용은 저장소 README에서 읽을 수 있습니다. 저장소 README ↗
README 전체를 불러오는 중입니다.
README 전문 보기 ↗Sell before you build: one binary and a skill that make your coding agent research real buyers and ship one checked, fast landing page with a payment link.
curl -fsSL https://lfm.cash/install.sh | sh
lfm is an agent-first page compiler. Your coding agent researches real buyers, writes a design
concept from what they say, and builds one HTML template with its config and assets. lfm compiles that into a
standalone static folder and refuses to ship a page that is broken, slow, inaccessible, invisible to
search or full of generic AI design defaults. Every finding says how to fix it.
No framework, no platform, no runtime: one binary, one page, one folder you upload anywhere. No MCP
server either: a CLI with --json plus one SKILL.md is the whole agent interface.
Give any coding agent (Claude Code, Codex, Cursor, OpenCode, Gemini CLI and others) this request:
Make a landing page for my sourdough course with lfm: https://lfm.cash/SKILL.md
SKILL.md tells the agent how to install lfm, set up a project and follow the process.
To have every agent session pick it up by itself for requests like "generate me a landing page", install
it once as a user skill:
for d in ~/.agents/skills/lfm ~/.claude/skills/lfm; do mkdir -p "$d" && curl -fsSL https://lfm.cash/SKILL.md -o "$d/SKILL.md"; done
~/.agents/skills is read by Codex, Cursor, OpenCode, Gemini CLI and GitHub Copilot; ~/.claude/skills
by Claude Code. Keep only the one your agents need.
On Grok Bot, add the lfm.cash bot: it installs lfm on its own computer and runs the same process, asking you only what you decide. Its setup is in docs/grok-bot.md.
The script at the top downloads the release for macOS or Linux (amd64
or arm64), checks it against the release checksums and puts lfm in ~/.local/bin, without sudo.
LFM_VERSION=v0.0.2 pins a release and LFM_INSTALL_DIR changes the folder. With Homebrew:
brew install anonyfox/tap/lfm
With Go 1.26 or newer:
go install github.com/Anonyfox/lfm/cmd/lfm@latest
Optional: Chrome or Chromium for lfm compile --release, and Lighthouse for its scores. Missing tools
are reported and skipped, never installed.
lfm init sourdough-course # a starter project that compiles cleanly
cd sourdough-course
lfm skills install # the process skills, where your agent loads them
lfm compile # findings, output/ and the next step
Then ask your agent for the page. It works in three phases, each with its own skill:
research/.concept.md from the research: buyer, mechanism, direction, palette, type, imagery,
motion and copy, every decision cited to a source.concept.md, until lfm compile --release is clean and every
saved frame holds up on phone and desktop.The compiler checks each handover: missing research, an uncited concept or a page that ignores the
concept's palette, type and imagery show up as findings. Every report ends with the next step, such as
Next (design): write concept.md from the research., and names the skill for it, so an agent working
unattended stays on the path. When it says deploy, upload output/ to the URL in lfm.json.
| Command | Use |
|---|---|
lfm | What lfm is, how to start, every command |
lfm <command> -h | Usage, flags and behaviour of one command |
lfm skills | The process skills in the order a page needs them |
lfm skills <topic> | One SKILL.md, rendered for the installed version |
lfm skills install | All skills into the project's .agents/skills or .claude/skills |
lfm compile [--release] [--json] | Check and build; the last line is the next step |
lfm check <url|folder|file> [--release] [--json] | Check any built page from a URL or disk |
lfm serve --open | Live preview that recompiles on every save |
lfm rules [id] | Every check, or what one means and how to fix it |
lfm skills install updates the folders that already hold lfm skills. Otherwise it writes to
.claude/skills when Claude Code runs it or the project has only a .claude folder, and to
.agents/skills in every other case; --agents, --claude and --global choose explicitly. Each
installed SKILL.md records the lfm version and a digest of its text, so running it again after an
update replaces untouched copies and keeps copies the project changed (--force replaces them too).
lfm compile never writes skill files. After an upgrade, run the printed lfm skills install
command to update each folder with older copies.
lfm compile --json prints the result as one object with errors, warnings, the findings under
validation, next (phase, do, skill) and the installed skills. Exit status is 0 when
output/ was written, 1 when errors kept it unchanged or there is no project, and 2 for a mistake in the
command line.
lfm.cash is an lfm project in site/, built by an agent through the same three phases: 120 buyer posts and 20 competitor pages, a concept that chose one of ten directions with every decision cited, and a page that compiles with 0 errors and 0 warnings. Its proof section compiles the page an agent wrote from one sentence without lfm; that page and its report are there too.
concept.md decided.--release scrolls the page at phone and desktop sizes, saves every frame and reports
empty stretches, sideways scrolling, covered or unreadable text, split values and missing glyphs.lfm.json, templates, assets, research and concept.lfm compile does: lifecycle, packing, output, release, preview.