kc-plugin-forge

kc-plugin-forge is a skill for Claude Code, Codex from iamcxa/kc-claude-plugins. It costs 34 tokens per session (11,086 once invoked), scanned A, original, MIT.

A development and quality workflow for Claude Code plugins. It can coordinate plugin scaffolding, validation, skill testing, cleanup, and agent-configuration checks when its required supporting plugins are installed.

In plain words
What is it for?
Use it when creating a new Claude Code plugin, reviewing an existing one, improving its skills with test-driven development, or verifying its agents.
Why use it?
It provides an organised path for checking whether a plugin is complete and usable. This helps expose missing files, quality problems, and configuration issues during development.

Skill for Claude CodeCodex

Installs and runs on its own, but its text points at files inside its plugin — anything it tells you to read at a ${CLAUDE_PLUGIN_ROOT} path is only there once the plugin is installed. Installing the plugin gets both.

Part of the kc-plugin-forge plugin — 5 skills shipped together

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/iamcxa/kc-claude-plugins/kc-plugin-forge
Any agent
npx skills add iamcxa/kc-claude-plugins --skill kc-plugin-forge
Clone the repo
git clone --depth 1 https://github.com/iamcxa/kc-claude-plugins

Made for: Claude Code, Codex.

Or install kc-plugin-forge, the plugin that ships this one along with the rest of its 5 skills.

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 kc-plugin-forge

README.md
[![agentmods](https://agentmods.dev/badge/skills/iamcxa/kc-claude-plugins/kc-plugin-forge.svg)](https://agentmods.dev/skills/iamcxa/kc-claude-plugins/kc-plugin-forge)
Your own site
<a href="https://agentmods.dev/skills/iamcxa/kc-claude-plugins/kc-plugin-forge"><img src="https://agentmods.dev/badge/skills/iamcxa/kc-claude-plugins/kc-plugin-forge.svg" alt="Measured on agentmods" height="20"></a>
Per session 34 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 11,086 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 $0.00034 $0.11086
Opus 5 $0.00017 $0.05543
Sonnet 5 $0.00007 $0.02217
Haiku 4.5 $0.00003 $0.01109

Measured today against content hash 895566c08a08, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

kc-plugin-forge 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 today.

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.

kc-plugin-forge/skills/kc-plugin-forge/SKILL.md · 720 lines

How it starts

The opening of the file, as written. The whole thing — 720 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Plugin Forge

One-command plugin development and quality pipeline. Orchestrates marketplace skills to scaffold, test, validate, and improve Claude Code plugins.

Prerequisites: superpowers + plugin-dev marketplace plugins must be installed. Optional: claude-md-management for self-improvement loop.

Read references before starting any phase:

Read → ${CLAUDE_PLUGIN_ROOT}/reference/quality-pipeline.md
Read → ${CLAUDE_PLUGIN_ROOT}/reference/learned-patterns.md

Routing

digraph forge {
  rankdir=TB;
  node [shape=diamond];
  input [label="Input?"];
  disambig [label="Ambiguous?\n(no path, multi-plugin)"];

  node [shape=box];
  ask [label="List plugins\nConfirm target + scope"];
  create [label="Phase 1: Scaffold\nInvoke plugin-dev:create-plugin"];
  audit [label="Phase 1: Validate\nDispatch plugin-dev:plugin-validator agent"];
  fix [label="Fix FAIL items\n(reference: quality-pipeline.md Phase 1)"];
  tdd [label="Phase 2: Skill TDD\nInvoke superpowers:writing-skills\nper skill in plugin"];
  dreaming [label="Phase 2.7: Dreaming\nPattern Promotion"];
  clean [label="Phase 2.5: Clean Profile\nSmoke Test"];
  agents [label="Phase 3: Agent Verify\nInvoke plugin-dev:agent-development\nper agent in plugin"];
  revalidate [label="Phase 4: Re-validate\nDispatch plugin-dev:plugin-validator agent"];
  report [label="Summary Report\n+ Learning + Doc-sync offer"];
  selfforge [label="self-forge\nPhase 2 TDD + Phase 2.7 Dreaming\n+ Phase 4 Learning"];

  input -> create [label="new <name>"];
  input -> disambig [label="bare / vague"];
  input -> dreaming [label="dreaming <path>\ndreaming --all\ndreaming --dry-run"];
  disambig -> ask [label="yes"];
  ask -> audit [label="full pipeline"];
  ask -> audit [label="validate-only\n(skip Phase 2-3)"];
  ask -> tdd [label="skill-tdd-only"];
  ask -> agents [label="agent-verify-only"];
  input -> audit [label="<path>"];
  input -> tdd [label="skill-tdd-only"];
  input -> agents [label="agent-verify-only"];
  input -> selfforge [label="self-forge"];
  selfforge -> tdd;
  create -> tdd;
  tdd -> dreaming;
  dreaming -> report [label="self-forge\n(skip clean + agents + revalidate)"];
  dreaming -> clean [label="full pipeline / skill-tdd-only / new"];
  dreaming -> report [label="standalone dreaming route"];
  reaudit [label="Re-validate FAIL items\nDispatch plugin-dev:plugin-validator agent"];
  audit -> fix [label="FAIL"];
  audit -> tdd [label="PASS\n(full pipeline)"];
  audit -> report [label="PASS\n(validate-only)"];
  fix -> reaudit;
  reaudit -> tdd [label="PASS"];
  reaudit -> fix [label="still FAIL"];
  clean -> agents;
  agents -> revalidate;
  revalidate -> report [label="PASS"];
  revalidate -> fix [label="FAIL"];
}

Read the full file on GitHub · 720 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. today Changed · +6 lines 895566c08a08
  2. 5d ago First seen · 714 lines · 34 tokens per session scan A a3309fda08bb

Subscribe to this mod's changes

kc-plugin-forge is a skill published in the GitHub repository iamcxa/kc-claude-plugins (3 stars, last pushed today), licensed MIT. It adds 34 tokens to every session and 11,086 once invoked, about $0.0002 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

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

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