plugin-authoring

A guide for creating and checking Claude Code plugins, which are add-ons that extend the coding assistant with commands, agents, skills, or event hooks.

In plain words
What is it for?
Use it to start, review, validate, or debug plugin files such as plugin.json, marketplace.json, commands/, agents/, skills/, and hooks/.
Why use it?
It helps you follow the required file formats and structure, and diagnose common plugin problems before changing files.

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/kossakovsky/cc-plugins/plugin-authoring
Any agent
npx skills add kossakovsky/cc-plugins --skill plugin-authoring
Clone the repo
git clone --depth 1 https://github.com/kossakovsky/cc-plugins

Made for: Claude Code, Codex.

Per session 51 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,589 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin 98% copy Near-identical to another mod 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 $0.00051 $0.01589
Opus 5 $0.00026 $0.00794
Sonnet 5 $0.00010 $0.00318
Haiku 4.5 $0.00005 $0.00159

Measured yesterday against content hash 89596157f200, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

plugin-authoring 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.

Origin

This is a copy

98% identical to plugin-authoring — 4 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.

plugins/plugin-development/skills/plugin-authoring/SKILL.md · 137 lines

How it starts

The opening of the file, as written. The whole thing — 137 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Plugin Authoring (Skill)

You are the canonical guide for Claude Code plugin development. Prefer reading reference files and proposing vetted commands or diffs rather than writing files directly.

Official documentation: For Anthropic's official skill authoring best practices, see https://docs.anthropic.com/en/docs/agents-and-tools/agent-skills/skill-authoring-best-practices

Triggers & Scope

Activate whenever context includes .claude-plugin/, plugin.json, marketplace.json, commands/, agents/, skills/, or hooks/.

Flow of Operation

  1. Diagnose current repo layout (read-only)
  2. Propose the minimal safe action (scaffold, validate, or review)
  3. Execute via /plugin-development:... commands when the user agrees
  4. Escalate to the plugin-reviewer agent for deep audits
  5. Guardrails: default to read-only; ask before edits

Checklists

Component Checklist

□ .claude-plugin/plugin.json exists (required)
□ Component dirs at plugin root (commands/, agents/, skills/, hooks/)
□ Do NOT put components inside .claude-plugin/ directory
□ Commands use kebab-case naming
□ Skills have valid frontmatter (name + description required, optional: model, allowed-tools)
□ Skills name validation:
  - Matches directory name
  - Lowercase letters, numbers, hyphens only
  - Max 64 characters
  - No reserved words ('anthropic', 'claude')
  - No XML tags
□ Hooks use ${CLAUDE_PLUGIN_ROOT} for paths (not relative paths)
□ All scripts are executable (chmod +x)

Read the full file on GitHub · 137 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 · 137 lines · 51 tokens per session scan A 89596157f200

Subscribe to this mod's changes

plugin-authoring is a skill published in the GitHub repository kossakovsky/cc-plugins (3 stars, last pushed 5mo ago), licensed MIT. It adds 51 tokens to every session and 1,589 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it A with 0 findings. It is 98% identical to plugin-authoring, differing in 4 lines, and is treated as a copy.

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