add-pluginpack-target

A contributor guide for adding support for a new AI coding app or plugin format to pluginpack.

In plain words
What is it for?
Use it when changing pluginpack itself to add a target adapter, native file layout, manifest generation, validation, installation instructions, and defaults.
Why use it?
It explains where to implement the new format and how to verify it against official documentation, schemas, validators, or published plugin repositories.

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

Made for: Claude Code, Codex.

Per session 53 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 510 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 $0.00053 $0.00510
Opus 5 $0.00026 $0.00255
Sonnet 5 $0.00011 $0.00102
Haiku 4.5 $0.00005 $0.00051

Measured yesterday against content hash b39385f55ca4, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

add-pluginpack-target 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/add-pluginpack-target/SKILL.md · 50 lines

What it actually says

Adding a pluginpack target

A target adapter owns one app's native layout, manifests, and validation.

First: get the real format, do not guess

Find the app's actual plugin format from official docs or a real published plugin repo (the way the existing adapters were derived from github/copilot-plugins, gleanwork/cursor-plugins, the Claude plugins reference, and the documented OpenAI Codex CLI plugin format). Capture an external oracle you can validate against — a published JSON Schema, the app's own validator CLI, or a real repo to diff against. Record it in CONFORMANCE.md.

Touch points

Adding a target means:

  1. src/types.ts — add the name to the TargetName union.
  2. src/targets/<name>.ts — implement PluginTargetDefinition (see src/targets/types.ts): emit logic, manifest/marketplace builder, validation, install snippet, and defaults.
  3. src/targets/registry.ts — add one entry mapping the name to that definition.

Everything else — the CLI's --target choices, build()'s target set, and emit/validate dispatch — derives from the registry automatically via the shared engine in src/targets/engine.ts. Reuse src/targets/validation-shared.ts for checks whose shape genuinely matches the other targets (hooks, frontmatter); write your own where the shape is genuinely different, the way codex's structured source object does.

Wire MCP

If the app supports MCP servers, decide whether it reads a .mcp.json file (reference it from the manifest, like cursor/copilot, or rely on auto-discovery, like claude), a target-specific config file (like Antigravity's mcp_config.json), or another native shape. resolveMcpServers already merges a plugin's servers; thread the result into your emitter.

Verify

Add conformance tests in tests/ against the external oracle, extend CONFORMANCE.md, then run npm run check.

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 · 50 lines · 53 tokens per session scan A b39385f55ca4

Subscribe to this mod's changes

add-pluginpack-target is a skill published in the GitHub repository gleanwork/pluginpack (5 stars, last pushed 21d ago), licensed MIT. It adds 53 tokens to every session and 510 once invoked, about $0.0003 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