authoring-pluginpack-config

A configuration guide for pluginpack, a tool that packages one set of agent skills or plugins for several AI coding apps.

In plain words
What is it for?
Use it to create or update pluginpack.config.ts, choose target apps, define plugin contents, configure MCP servers, and set generated output directories.
Why use it?
It removes the need to maintain separate source layouts and configuration by defining the source, supported targets, and output folders in one file.

Skill for Claude CodeCodex

Install

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.

agentmods
npx agentmods add skills/gleanwork/pluginpack/authoring-pluginpack-config
Any agent
npx skills add gleanwork/pluginpack --skill authoring-pluginpack-config
Clone the repo
git clone --depth 1 https://github.com/gleanwork/pluginpack

Made for: Claude Code, Codex.

Per session 74 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 754 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00074 $0.00754
Opus 5 $0.00037 $0.00377
Sonnet 5 $0.00015 $0.00151
Haiku 4.5 $0.00007 $0.00075

Measured yesterday against content hash 77d6662aa535, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

authoring-pluginpack-config 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 yesterday.

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.

skills/authoring-pluginpack-config/SKILL.md · 92 lines

How it starts

The opening of the file, as written. The whole thing — 92 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Authoring a pluginpack config

pluginpack compiles one portable source into each app's native plugin format. The config (pluginpack.config.ts) declares the source layout and the targets to emit.

Fastest start

npx @gleanwork/pluginpack init scaffolds a pluginpack.config.ts and an example source plugin. Then edit to taste.

Config shape

import { defineConfig } from "@gleanwork/pluginpack";

export default defineConfig({
  name: "acme-plugins",
  version: "0.1.0",
  source: {
    // Recommended: portable skills at the repo-level skills/ directory.
    skills: "skills",
    rootPlugin: { id: "core", description: "Acme portable skills." },
    // Alternatively, richer source plugins live under plugins/<id>/.
    // plugins: "plugins",
  },
  metadata: {
    description: "Acme agent plugins.",
    author: { name: "Acme" },
    owner: { name: "Acme", email: "[email protected]" },
    license: "MIT",
  },
  targets: {
    cursor: {
      outDir: ".",
      plugins: {
        acme: {
          from: ["core"],
          path: "plugins/cursor/acme",
          components: ["skills"],
        },
      },
    },
    claude: {
      outDir: ".",
      pluginRoot: "plugins/claude",
      plugins: { acme: { from: ["core"] } },
    },
    antigravity: {
      outDir: "plugins/antigravity",
      plugins: { acme: { from: ["core"] } },
    },
    copilot: {
      outDir: "plugins/copilot",
      plugins: { acme: { from: ["core"] } },
    },
    codex: {
      outDir: "plugins/codex",
      plugins: { acme: { from: ["core"] } },
    },
  },
});
  • source.skills is the portable surface; source.rootPlugin.id is the source plugin name targets reference via from.
  • Each emitted plugin's from lists the source plugin id(s) to include; multiple ids merge (a colliding file path is an error).
  • path / pluginRoot control where a target places the emitted plugin.

Critical: avoid output collisions

claude and copilot both write .claude-plugin/marketplace.json, so they cannot share an outDir. Give them distinct roots (e.g. claude at ., copilot at plugins/copilot). pluginpack build errors on overlapping output paths.

Read the full file on GitHub · 92 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. yesterday First seen · 92 lines · 74 tokens per session scan A 77d6662aa535

Subscribe to this mod's changes

authoring-pluginpack-config is a skill published in the GitHub repository gleanwork/pluginpack (5 stars, last pushed 21d ago), licensed MIT. It adds 74 tokens to every session and 754 once invoked, about $0.0004 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.

Related

Other skills, from other repositories

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

babysit-pr

Babysit a GitHub pull request after creation by continuously polling review comments, CI checks/workflow runs, and mergeability state until the PR is merged/closed or user help is required. Diagnose failures, retry likely flaky failures up to 3 times, auto-fix/push branch-related issues when appropriate, and keep…

openai/codex · 114 tokens

imagegen

Generate or edit raster images when the task benefits from AI-created bitmap visuals such as photos, illustrations, textures, sprites, mockups, or transparent-background cutouts. Use when Codex should create a brand-new image, transform an existing image, or derive visual variants from references, and the output…

openai/codex · 113 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

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…

vercel/next.js · 170 tokens