craft-skill

craft-skill is a skill for Claude Code from V-Songbird/slag. It costs 142 tokens per session (2,749 once invoked), scanned A, original, MIT.

A builder for Claude Code skills, which are instruction files that teach the coding agent how to handle a specific task. It creates a new skill or adjusts an existing one so it is more likely to run when intended.

In plain words
What is it for?
Use it to create one project skill or improve an existing skill's trigger description.
Why use it?
It removes the need to work out the skill-file format and placement yourself. Changes are previewed and can be undone.

Skill for Claude Code

Written for Claude Code: allowed-tools in frontmatter. Also seen: reads .claude/ paths; mentions CLAUDE.md; names the AskUserQuestion tool.

Runs only inside its plugin — its command needs a path that Claude Code sets for a plugin’s own hooks and for nothing else. Install the plugin, not this.

Part of the assay plugin — 9 skills shipped together

Good fit Use it to create one project skill or improve an existing skill's trigger description.

Compare 6 skills from other repositories ↓
Install

Getting it into your agent

This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.

Claude Code
/plugin marketplace add V-Songbird/slag
Claude Code
/plugin install assay

Made for: Claude Code.

Or install assay, the plugin that ships this one along with the rest of its 9 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 craft-skill

README.md
[![agentmods](https://agentmods.dev/badge/skills/v-songbird/slag/craft-skill/github.svg)](https://agentmods.dev/skills/v-songbird/slag/craft-skill)
Your own site
<a href="https://agentmods.dev/skills/v-songbird/slag/craft-skill"><img src="https://agentmods.dev/badge/skills/v-songbird/slag/craft-skill/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.

agentmods 80×15 button for craft-skill

Your own site · 80×15
<a href="https://agentmods.dev/skills/v-songbird/slag/craft-skill"><img src="https://agentmods.dev/badge/skills/v-songbird/slag/craft-skill.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 142 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,749 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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00142 $0.02749
Opus 5 $0.00071 $0.01375
Sonnet 5 $0.00028 $0.00550
Haiku 4.5 $0.00014 $0.00275

Measured 9d ago against content hash 7069078d42db, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

craft-skill 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 9d ago.

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.

assay/skills/craft-skill/SKILL.md · 227 lines

How it starts

The opening of the file, as written. The whole thing — 227 lines — stays where its author put it; the contents beside it link to each section on GitHub.

assay:craft-skill

You build one skill per run — new, or a refit of an existing one. $ARGUMENTS, if present, names the skill or describes what it should do.

You never write a skill file yourself. Every artifact — the SKILL.md, any metadata sidecar, a companion rule, a hook — goes through the engine's change transaction in step 5, so each one is previewed before it lands and reversible after.

1. Read the project

Before anything else, from the project root:

node "${CLAUDE_PLUGIN_ROOT}/scripts/assay.js" scan

If node is not on PATH (fnm/nvm setups), register it the way the project's CLAUDE.md says to, then rerun.

Then read .assay-tmp/scan.json. Every fact below comes from it; never assume a directory or a required field:

  • profile.targets.skilldir and file (where skills live), requires[] (the frontmatter documented as required), metadata[] (any invocation/UI sidecar), and docs (the page to fetch in step 2).
  • skills[] — every project skill already discovered, with its name, path, and checks. This is where a refit target comes from, and where a name collision shows up.
  • coverage.skillBudget — the collective listing budget, where one is published. Every skill's name and description spend from it before any skill is selected, so a long description costs the whole list.
  • profile.targets.hook.docs — the hooks page, for step 4's ladder.

2. Scope, and ground the format

Decide new-vs-refit: it is a refit when the user pointed at a skill in skills[], or one there matches their words. Otherwise it is new.

Collect, from the conversation or one AskUserQuestion round at most. Don't ask for what the user already said; only fill real gaps.

  • What the skill does — enough to write a concrete base sentence naming real artifacts.
  • Three or four ways the user would actually phrase the ask, in their words.
  • The nearest adjacent ask the skill should NOT fire on.
  • Whether the skill is bound to a file type or path (a candidate for a scoped companion rule).
  • Which tools or commands the skill depends on.
  • How critical firing is: nice-to-have, should-always-run, or must-never-be-skipped.

Read the full file on GitHub · 227 lines

Files

What ships with it

1 file 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. 9d ago First seen · 227 lines · 142 tokens per session scan A 7069078d42db

Subscribe to this mod's changes

craft-skill is a skill published in the GitHub repository V-Songbird/slag (1 stars, last pushed 4d ago), licensed MIT. It adds 142 tokens to every session and 2,749 once invoked, about $0.0007 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

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

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

next-partial-prefetching-adoption

Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…

vercel/next.js · 103 tokens