agentmods.dev

ppxai: Skill for Claude Code

.claude/skills/build-install/SKILL.md

build-install is a skill for Claude Code from rcconsult/ppxai. It costs 114 tokens per session (7,324 once invoked), scanned C, original, MIT.

A build-and-install procedure for rebuilding the ppxai command-line tools, desktop and server programs, VS Code extension, and macOS packages when applicable.

In plain words
What is it for?
Use it to test a branch before release or verify release artifacts across macOS, Linux, and Windows.
Why use it?
It checks that the complete product can be rebuilt and installed like a user-side release, including required dependencies for office-file support.

Skill for Claude Code

Written for Claude Code: installed under .claude/. Also seen: mentions CLAUDE.md.

This is rcconsult/ppxai's own configuration. It tells Claude Code how to work on ppxai itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything ppxai configures →

Needs its repository: it runs a file that does not travel with it, so clone the repository first. The line is bash scripts/create-macos-app.sh.

not rated 6repo changed 10d ago C scan 114 tokens original MIT
View source ↗ rcconsult/ppxai
Reuse

Borrowing it

Nothing to install: this file belongs to rcconsult/ppxai. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/rcconsult/ppxai/master/.claude/skills/build-install/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/rcconsult/ppxai

Made for: Claude Code.

Wrote 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.

agentmods badge for build-install

README.md
[![agentmods](https://agentmods.dev/badge/skills/rcconsult/ppxai/build-install/github.svg)](https://agentmods.dev/skills/rcconsult/ppxai/build-install)
Your own site
<a href="https://agentmods.dev/skills/rcconsult/ppxai/build-install"><img src="https://agentmods.dev/badge/skills/rcconsult/ppxai/build-install/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.

agentmods 80×15 button for build-install

Your own site · 80×15
<a href="https://agentmods.dev/skills/rcconsult/ppxai/build-install"><img src="https://agentmods.dev/badge/skills/rcconsult/ppxai/build-install.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 114 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 7,324 The whole file, excluding the scripts and references it only reads on demand.
Security scan C 2 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00114 $0.07324
Opus 5.5 $0.00046 $0.02930
Sonnet 5.5 $0.00023 $0.01465
Haiku 4.5 $0.00011 $0.00732

Measured 10d ago against content hash dfed77ffba39, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade C, and why

build-install scanned grade C with 2 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 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 build dist

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

for i in $(seq 1 25); do curl -s -m2 -o /dev/null http://127.0.0.1:54320/status && break; sleep 0.5; done
.claude/skills/build-install/SKILL.md · 593 lines

How it starts

The opening of the file, as written. The whole thing — 593 lines — stays where its author put it; the contents beside it link to each section on GitHub.

build-install

End-to-end local install of ppxai. Build all binaries + VSCode extension (+ macOS-only .app and DMG), then install everything to system locations exactly as a user-side install would. Useful for testing a branch before release, or for verifying a release artifact after CI uploads it.

Preconditions

All platforms

  • Working tree at the version you want to ship — version files already bumped (see tests/test_version_consistency.py for the SoT list).
  • uv resolvable per docs/dev-setup.md "uv Resolution" (system or .uv/uv).
  • Build venv MUST have the [data] extras. The office-preview pipeline needs pypdfium2 (PDF→PNG) + python-pptx/openpyxl, which live in the [data] optional extra. Step 1 runs uv sync --all-extras to guarantee it. Without it the binaries build fine but ship WITHOUT office support — LibreOffice is detected yet render_pptx_slides returns [] → "No slides rendered" (caught live 2026-06-14). Matches the CI build (.github/workflows/build.yml) and the release-script test step, both of which use --all-extras.
  • node + npm for the VSCode extension build.
  • A POSIX-ish shell. Bash works on all four platforms (macOS native, Linux native, Windows via Git Bash). PowerShell alternatives are noted where they meaningfully simplify Windows-only flows.

Platform-specific

  • macOS Apple Silicon — host is arm64. uname -m prints arm64. create-macos-app.sh writes ppxai-X.Y.Z-macos-arm64.dmg.
  • macOS Intel — host is x86_64. uname -m prints x86_64. create-macos-app.sh writes ppxai-X.Y.Z-macos-intel.dmg. The alternate scripts/build-intel.sh orchestrates the same flow with upload-to-release support.
  • Linux — linux-amd64 is the only platform built today. Binaries install to ~/.local/bin/ (must be on $PATH).
  • Windows — PyInstaller produces .exe suffixes automatically. Binaries install to ~/.ppxai/bin/ (NOT ~/.local/bin/; see CLAUDE.md "Installation Locations"). ~/.ppxai/bin/ must be on $env:PATH. Easiest run-shell is Git Bash (matches steps below); PowerShell variants noted where useful.

Read the full file on GitHub · 593 lines

Changes

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.

  1. 10d ago Changed dfed77ffba39
  2. 1mo ago Changed 999cd970aa95
  3. 1mo ago First seen · 593 lines · 114 tokens per session scan C 0e0476abfeff

Subscribe to this mod's changes

build-install is a skill published in the GitHub repository rcconsult/ppxai (6 stars, last pushed 2d ago), licensed MIT. It adds 114 tokens to every session and 7,324 once invoked, about $0.0005 per session on Opus 5.5. A static security scan graded it C with 2 findings (recursive force delete, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

DevOps and cloud
Related

Other skills, from other repositories

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…

microsoft/ai-agents-for-beginners · 200 tokens

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

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…

vercel/next.js · 95 tokens

chat-pet-sprite-creation

Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.

microsoft/vscode · 53 tokens

cpu-profile-analysis

Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…

microsoft/vscode · 71 tokens

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…

vercel/next.js · 83 tokens