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 gethouston/houston --skill build-app-localgit clone --depth 1 https://github.com/gethouston/houstonWrote 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/gethouston/houston/build-app-local)<a href="https://agentmods.dev/skills/gethouston/houston/build-app-local"><img src="https://agentmods.dev/badge/skills/gethouston/houston/build-app-local/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/gethouston/houston/build-app-local"><img src="https://agentmods.dev/badge/skills/gethouston/houston/build-app-local.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 | $0.00055 | $0.01091 |
| Opus 5 | $0.00028 | $0.00545 |
| Sonnet 5 | $0.00011 | $0.00218 |
| Haiku 4.5 | $0.00006 | $0.00109 |
Grade C, and why
build-app-local scanned grade C with 1 finding 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 10d 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.
Recursive force deletehighDestructive command
rm -rf with a variable or a broad path is one typo away from removing the wrong tree.
rm -rf app/src-tauri/target/universal-apple-darwin/release/bundle Copies of this mod
1 near-identical copy found in the catalogue:
- build-app-local — 92% identical, 27 lines differ
How it starts
The opening of the file, as written. The whole thing — 101 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/build-app-local
Manual macOS build. CI broken? Use this. Normal path = /release.
Pre-reqs
Env vars set in shell:
APPLE_SIGNING_IDENTITY— Developer ID stringAPPLE_API_KEY— App Store Connect key IDAPPLE_API_KEY_PATH— path to.p8APPLE_API_ISSUER— issuer UUIDTAURI_SIGNING_PRIVATE_KEY+TAURI_SIGNING_PRIVATE_KEY_PASSWORDPOSTHOG_KEY·POSTHOG_HOST·SUPABASE_URL·SUPABASE_ANON_KEY·SENTRY_DSN
Flow
# 0. One-time: ensure both macOS rustup targets installed
rustup target add aarch64-apple-darwin x86_64-apple-darwin
# 1. Clean stale
cd .. # workspace root
rm -rf app/src-tauri/target/universal-apple-darwin/release/bundle
rm -rf app/dist
# 2. Bun-compile the host sidecar for BOTH arches (required for universal).
# This produces target/host-sidecar/houston-host-<triple> (+ stamps it with
# HEAD and stages the sibling `claude` binary); build.rs stages both into the
# bundle and, for a --release build, FAILS if the sidecar's inputs changed
# since it was compiled (staleness guard). --verify boots the native slice and
# curls /v1/capabilities + /v1/catalog, so run it on the host-native arch only.
#
# Cross-arch note: the non-native slice needs its Claude SDK platform package
# force-installed first (the pnpm store only has the host-matching one). On an
# Apple Silicon Mac the x86_64 slice needs the darwin-x64 package — match the
# @anthropic-ai/claude-agent-sdk version in packages/runtime/package.json:
# pnpm add -w @anthropic-ai/claude-agent-sdk-darwin-x64@<version> --force
scripts/build-host-sidecar.sh aarch64-apple-darwin --verify # native on Apple Silicon
scripts/build-host-sidecar.sh x86_64-apple-darwin # cross-arch slice
# 3. Build + auto-sign the app (universal fat binary)
cd app
pnpm tauri build --target universal-apple-darwin
Tauri signs .app. Does NOT notarize DMG. Must do manually:
# 4. Submit DMG to Apple for notarization (note universal path)
DMG="src-tauri/target/universal-apple-darwin/release/bundle/dmg/Houston_${VERSION}_universal.dmg"
xcrun notarytool submit "$DMG" \
--key "$APPLE_API_KEY_PATH" \
--key-id "$APPLE_API_KEY" \
--issuer "$APPLE_API_ISSUER" \
--wait
# 5. Staple ticket to DMG
xcrun stapler staple "$DMG"
# 6. Verify
xcrun stapler validate "$DMG"
spctl -a -vvv -t install "$DMG"
lipo -info "$(hdiutil attach "$DMG" -nobrowse -mountpoint /tmp/hmnt -quiet && echo /tmp/hmnt/*.app/Contents/MacOS/houston-engine)"
# → expect: "Architectures in the fat file: ... x86_64 arm64"
hdiutil detach /tmp/hmnt -quiet
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.
- 10d ago First seen · 101 lines · 55 tokens per session scan C fb6475ae7c8c
build-app-local is a skill published in the GitHub repository gethouston/houston (112 stars, last pushed today), licensed MIT. It adds 55 tokens to every session and 1,091 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it C with 1 finding (recursive force delete). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…
next-partial-prefetching-adoption
Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…