What is plugin-creator?

A guide for creating and reviewing reusable instructions for coding agents, called skills. It also covers the extra files used to package those skills as Claude Code plugins.

Use it to create, refactor, review, or validate a skill for Claude Code, Codex, or another agent host, including plugin components such as hooks, commands, subagents, and integrations when relevant.

It helps turn one-off scripts or procedures into portable, maintainable agent tools instead of leaving them as undocumented instructions. It also marks which steps apply only to Claude Code.

plugin-creator — Skill for Claude Code and Codex by 85danf

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.

Any agent

npx skills add 85danf/agent-skills --skill plugin-creator

Clone the repo

git clone --depth 1 https://github.com/85danf/agent-skills

Made for: Claude Code, Codex.

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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/85danf/agent-skills/plugin-creator/github.svg)](https://agentmods.dev/skills/85danf/agent-skills/plugin-creator)

Your own site

<a href="https://agentmods.dev/skills/85danf/agent-skills/plugin-creator"><img src="https://agentmods.dev/badge/skills/85danf/agent-skills/plugin-creator/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.

Your own site · 80×15

<a href="https://agentmods.dev/skills/85danf/agent-skills/plugin-creator"><img src="https://agentmods.dev/badge/skills/85danf/agent-skills/plugin-creator.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 202 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 6,167 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 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.

Model	Per session	Once invoked
Fable 5.1	$0.00202	$0.06167
Opus 5.5	$0.00081	$0.02467
Sonnet 5.5	$0.00040	$0.01233
Haiku 4.5	$0.00020	$0.00617

Measured 1mo ago against content hash 5170a586319a, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

plugin-creator 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 1mo ago.

The scan reads SKILL.md. This mod also ships 10 executable files (scripts/classify_change.py, scripts/generate_openai_yaml.py, scripts/generate_quality_artifacts.py, …), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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.

plugin-creator/SKILL.md · 461 lines

How it starts

The opening of the file, as written. The whole thing — 461 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Plugin Creator

Create, update, review, and validate Agent Skills for any host — Claude Code, Codex, or elsewhere. Stronger requirements apply to skills touching APIs, credentials, customer/ production data, or destructive operations.

Portability note. Originally written for authoring Claude Code plugins inside the "am-pm" plugin monorepo. Its core methodology — creation-cost/proof-cost, when a skill is the right tool at all, the 10-section SKILL.md body, context engineering, script-first authoring — is platform-agnostic. Genuinely Claude Code plugin-specific steps (optional plugin components: hooks, commands, subagents, MCP, LSP, monitors; the am-pm placement/duplication-check step; .claude-plugin/plugin.json authoring) are marked "Claude Code plugin-specific — skip for a portable/Codex-only skill". Never skip a step without that marking; always skip one that carries it when not authoring a Claude Code plugin (or not inside am-pm, for the monorepo-only step).

Principles

These bind on every skill creation, any host. Doctrine for a single Claude Code plugin component lives under references/components/ (Claude Code-specific throughout).

Approval boundary. Scope approval authorizes one target-aware plan artifact; target skill source stays gated until the saved plan reaches plan-approved at the second gate.

The core trade — creation cost against proof cost

A skill is cheap to build and expensive to trust on any host: a description and some markdown — almost nothing constrains it, which is why it works immediately and why you can never prove it fires. Claude Code-specific: every other plugin component (hook, subagent, MCP, LSP, monitor, command) earns its reliability by restricting itself to what a machine can decide, so the question there is never which component is best, but is what I am encoding genuinely expressible deterministically? Yes and it matters → pay the creation cost, buying provability. No → do not force it. On a portable/Codex-only skill this collapses to: the skill is what you have, so write its trigger and behavior as unambiguous as prose can make them.

Read the full file on GitHub · 461 lines

Files

What ships with it

60 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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.

1mo ago First seen · 461 lines · 202 tokens per session scan A 5170a586319a

Subscribe to this mod's changes

plugin-creator is a skill published in the GitHub repository 85danf/agent-skills (2 stars, last pushed 1mo ago), licensed MIT. It adds 202 tokens to every session and 6,167 once invoked, about $0.0008 per session on Opus 5.5. 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 2026-09-26.

Building agents

plugin-creator next to 6 skills from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
plugin-creator85danf/agent-skills	Skill	2	1mo ago	MIT	A	202	Claude Code, Codex
imagegenopenai/codex	Skill	134k	today	Apache-2.0	A	113	Codex
local-ai-agentsmicrosoft/ai-agents-for-beginners	Skill	79k	today	MIT	A	200	Claude Code, Codex
playwright-climicrosoft/playwright	Skill	99k	today	Apache-2.0	A	19	Claude Code
systematic-debuggingobra/superpowers	Skill	314k	3d ago	MIT	A	21	Claude Code
next-cache-components-adoptionvercel/next.js	Skill	143k	today	MIT	A	95	Claude Code
chat-pet-sprite-creationmicrosoft/vscode	Skill	195k	today	MIT	A	53	Claude Code, Codex