skill-forge

skill-forge is a skill for Claude Code, Codex from YoungjaeDev/my-claude-plugins. It costs 189 tokens per session (2,247 once invoked), scanned A, original, MIT.

A guide for writing and packaging Claude Code skills so they work in both Claude Code and Codex. It covers activation rules, file structure, metadata, and release details.

In plain words
What is it for?
Use it to create or revise a skill, choose between references and scripts, update frontmatter and descriptions, resolve plugin paths, and bump versions.
Why use it?
It helps avoid skills that fail to load, do not activate for the right requests, or are packaged incorrectly.

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 docs-forge plugin — 11 skills, 3 commands 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/youngjaedev/my-claude-plugins/skill-forge
Any agent
npx skills add YoungjaeDev/my-claude-plugins --skill skill-forge
Clone the repo
git clone --depth 1 https://github.com/YoungjaeDev/my-claude-plugins

Made for: Claude Code, Codex.

Or install docs-forge, the plugin that ships this one along with the rest of its 11 skills, 3 commands.

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 skill-forge

README.md
[![agentmods](https://agentmods.dev/badge/skills/youngjaedev/my-claude-plugins/skill-forge.svg)](https://agentmods.dev/skills/youngjaedev/my-claude-plugins/skill-forge)
Your own site
<a href="https://agentmods.dev/skills/youngjaedev/my-claude-plugins/skill-forge"><img src="https://agentmods.dev/badge/skills/youngjaedev/my-claude-plugins/skill-forge.svg" alt="Measured on agentmods" height="20"></a>
Per session 189 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,247 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 $0.00189 $0.02247
Opus 5 $0.00095 $0.01123
Sonnet 5 $0.00038 $0.00449
Haiku 4.5 $0.00019 $0.00225

Measured 4d ago against content hash 355aa29eaabf, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

skill-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 4d ago.

The scan reads SKILL.md. This mod also ships 1 executable file (scripts/measure-skills.mjs), 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.

plugins/docs-forge/skills/skill-forge/SKILL.md · 182 lines

How it starts

The opening of the file, as written. The whole thing — 182 lines — stays where its author put it; the contents beside it link to each section on GitHub.

skill-forge

Write a skill that actually loads, actually triggers, and actually reaches the person who needs it.

Overview

A skill fails in three separable ways, and they need different fixes:

  • It never loads. A frontmatter violation. Silent on Claude Code, fatal on Codex.
  • It loads but never triggers. A description that describes the subject instead of encoding the reaching conditions.
  • It triggers but the run goes wrong. Structure: vague completion criteria, material at the wrong rung of the information hierarchy, prose that changes nothing.

This skill carries the rules for all three, plus the packaging obligations that decide whether a change reaches users at all. Everything needed is bundled — no external skill is read at any point.

When to use

Use it when creating a new skill, rewriting a body, splitting one skill into two, renaming a skill, deciding between references/ and scripts/, or judging whether a proposed skill should exist.

Do not use it to:

  • diagnose one existing skill and get a graded fix list — that is docs-forge:skill-audit
  • sweep every skill in the repository — that is docs-forge:skill-fleet-review
  • write a slash command, a subagent, or a plugin manifest — those are different surfaces with different contracts

Quick reference

Question Read
which frontmatter fields, and what each runtime does with them references/frontmatter.md
why a line stays or goes; how to phrase triggers and completion criteria references/writing-levers.md
section order, length targets, scripts vs references vs assets, naming references/structure.md
the silent failures, the resolver block, version bumps, manifest regeneration references/runtime-contract.md

Read a reference when you reach the step that needs it, not up front.

Procedure

1. Establish that the skill should exist

Answer before writing anything:

  • What is the invocation moment? If two procedures are called at different times, they are two skills regardless of shared subject matter. If a procedure is called at the same moment as an existing skill, it is a section of that skill.
  • Does it change behavior? A skill restating what the model already does by default is a no-op that costs description tokens on every turn forever.
  • Is a script enough? Deterministic logic belongs in a script the caller runs. A skill wrapping one command is a menu entry, not a capability.

Read the full file on GitHub · 182 lines

Files

What ships with it

6 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.

  1. 4d ago First seen · 182 lines · 189 tokens per session scan A 355aa29eaabf

Subscribe to this mod's changes

skill-forge is a skill published in the GitHub repository YoungjaeDev/my-claude-plugins (2 stars, last pushed 9d ago), licensed MIT. It adds 189 tokens to every session and 2,247 once invoked, about $0.0009 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

chronicle

Analyze Copilot session history for standup reports, usage tips, session search, and session reindexing. Use when the user asks for a standup, daily summary, usage tips, workflow recommendations, wants to search or find past sessions by keyword/file/PR, wants to reindex their session store, or asks about deleting…

microsoft/vscode · 72 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

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