Borrowing it
Nothing to install: this file belongs to geleynse/gantry. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/geleynse/gantry/main/.claude/skills/build-and-dev/SKILL.mdgit clone --depth 1 https://github.com/geleynse/gantryWrote 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/geleynse/gantry/build-and-dev)<a href="https://agentmods.dev/skills/geleynse/gantry/build-and-dev"><img src="https://agentmods.dev/badge/skills/geleynse/gantry/build-and-dev/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/geleynse/gantry/build-and-dev"><img src="https://agentmods.dev/badge/skills/geleynse/gantry/build-and-dev.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 | $0.00051 | $0.01879 |
| Opus 5.5 | $0.00020 | $0.00752 |
| Sonnet 5.5 | $0.00010 | $0.00376 |
| Haiku 4.5 | $0.00005 | $0.00188 |
Grade A, and why
build-and-dev 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 2mo 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 — 106 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Build and Dev — Gantry Server
Gantry is a Bun project (not Node). All commands below run from server/ unless noted.
Setup
cd server
bun install
Build Commands
| Command | What it does |
|---|---|
bun run build:server |
Runs bun run build.ts — esbuild bundles src/index.ts → dist/index.js (ESM, node22 target, sourcemaps on) |
bun run build:client |
Runs bun run next build — Next.js 15 static export → dist/public/ |
bun run build |
build:server then build:client — full build |
bun run build:binary |
build:client then bun run build.ts --binary — standalone binary, see below |
bun run dev |
bun run build.ts --watch — esbuild watch mode, server only |
bun run dev:client |
bun run next dev --port 3001 — Next.js dev server on a separate port |
bun run start |
bun dist/index.js — run the already-built server |
build.ts reads package.json version and git rev-parse HEAD (short hash) at build time and bakes them in via esbuild define as process.env.BUILD_VERSION / process.env.GIT_COMMIT, so the compiled bundle has real values even with no .git or package.json on the deploy target.
build:server esbuild config (server/build.ts)
| Option | Value |
|---|---|
entryPoints |
src/index.ts |
bundle |
true |
platform / target |
node / node22 |
format |
esm |
outfile |
dist/index.js |
sourcemap |
true |
external |
node:*, bun:sqlite, ws, socks — left unbundled, resolved at runtime by Bun/Node |
In --watch mode (bun run dev), the same config runs via esbuild.context(...).watch() instead of a one-shot esbuild.build(...).
CRITICAL: bun run dev does not rebuild the dashboard
bun run dev only watches and rebuilds the server bundle (build.ts in --watch mode, esbuild). It does not touch dist/public/.
If you edit a .tsx file under src/app/ or src/components/ and need to see it in a browser:
bun run build:client # or bun run build for server+client
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.
- 2mo ago First seen · 106 lines · 51 tokens per session scan A f665a921fde5
build-and-dev is a skill published in the GitHub repository geleynse/gantry (4 stars, last pushed 2mo ago), licensed MIT. It adds 51 tokens to every session and 1,879 once invoked, about $0.0002 per session on Opus 5.5. 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.
build-and-dev compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| build-and-devgeleynse/gantry | Skill | 4 | 2mo ago | MIT | A | 51 | Claude Code |
| imagegenopenai/codex | Skill | 133k | yesterday | Apache-2.0 | A | 113 | Codex |
| playwright-climicrosoft/playwright | Skill | 99k | yesterday | Apache-2.0 | A | 19 | Claude Code |
| local-ai-agentsmicrosoft/ai-agents-for-beginners | Skill | 79k | 4d ago | MIT | A | 200 | Claude Code, Codex |
| systematic-debuggingobra/superpowers | Skill | 313k | 3d ago | MIT | A | 21 | Claude Code |
| next-cache-components-adoptionvercel/next.js | Skill | 143k | yesterday | MIT | A | 95 | Claude Code |
| next-partial-prefetching-adoptionvercel/next.js | Skill | 143k | yesterday | MIT | A | 103 | Claude Code |