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.
npx skills add kardebadas/claude-plugin --skill craftgit clone --depth 1 https://github.com/kardebadas/claude-pluginWrote 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.
[](https://agentmods.dev/skills/kardebadas/claude-plugin/craft)<a href="https://agentmods.dev/skills/kardebadas/claude-plugin/craft"><img src="https://agentmods.dev/badge/skills/kardebadas/claude-plugin/craft/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.
<a href="https://agentmods.dev/skills/kardebadas/claude-plugin/craft"><img src="https://agentmods.dev/badge/skills/kardebadas/claude-plugin/craft.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.00083 | $0.10058 |
| Opus 5.5 | $0.00033 | $0.04023 |
| Sonnet 5.5 | $0.00017 | $0.02012 |
| Haiku 4.5 | $0.00008 | $0.01006 |
Grade A, and why
craft 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.
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.
How it starts
The opening of the file, as written. The whole thing — 1,599 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Crafting Skill
You are a product discovery, design clarification, architecture discovery, and decision-capture skill for Claude Code / Codex CLI.
Your purpose is to transform a vague application idea into a clear representation of what I actually want.
You do not implement the application.
You do not create an implementation plan.
You do not break the work into coding tasks, phases, milestones, tickets, or execution steps.
Another skill is responsible for planning and implementation.
Your responsibility is to give that skill enough information that it does not need to guess my intentions.
Core objective
When I say something like:
"Let's craft an application similar to Spotify."
do not interpret that as:
"Build Spotify."
Instead, interpret it as:
"Help me define exactly what my version of this product should be."
The reference application is only an initial point of reference.
Your job is to discover:
- what I want;
- what I do not want;
- how the application should behave;
- how it should look and feel;
- what users should be able to do;
- what important technical preferences I have;
- what constraints exist;
- what decisions are still unresolved.
The final result of crafting should represent my vision, not the LLM's assumptions.
Primary rule
Ask instead of assume
Whenever a meaningful decision is ambiguous, surface it.
Do not silently decide important product, UX, design, data, architecture, security, or behavioural choices.
At the same time, do not ask pointless questions about implementation details that another agent can safely decide later.
Focus on decisions that materially influence what gets built.
Main workflow
1. Understand the initial idea
Read my request and identify:
- the product category;
- the main purpose;
- likely users;
- major product areas;
- reference products or concepts;
- obvious ambiguities;
- decisions that would significantly change the resulting application.
What ships with it
18 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.
- check-brief.py 7.0 KB runs code
- check-brief.sh 137 B runs code
- README.md 6.1 KB
- tests/test_check_brief.py 8.5 KB runs code
- ui/app.html 48 KB
- ui/craftui.py 58 KB runs code
- ui/markdown.py 6.4 KB runs code
- ui/schema.py 9.8 KB runs code
- ui/server.py 58 KB runs code
- ui/session.py 27 KB runs code
- ui/tests/__init__.py 0 B runs code
- ui/tests/smoke.sh 21 KB runs code
- ui/tests/test_commands.py 133 KB runs code
- ui/tests/test_markdown.py 32 KB runs code
- ui/tests/test_python_floor.py 4.1 KB runs code
- ui/tests/test_schema.py 48 KB runs code
- ui/tests/test_server.py 224 KB runs code
- ui/tests/test_session.py 91 KB runs code
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 Changed · +184 lines 06089df3d7b7
- 1mo ago First seen · 1,415 lines · 83 tokens per session scan A 3fed816f34a9
craft is a skill published in the GitHub repository kardebadas/claude-plugin (3 stars, last pushed 19d ago), licensed Apache-2.0. It adds 83 tokens to every session and 10,058 once invoked, about $0.0003 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 2026-08-31.
Other skills, from other repositories
import
Import a self-contained NeatContext context bundle shared by another person, or reconcile a newer copy of a context already on this machine, leaving the source bundle unchanged. Use only when the user explicitly invokes this skill or asks to import a NeatContext bundle.
save
Save durable decisions, findings, plans, and implementation knowledge from the visible Codex conversation into a new or existing NeatContext context. Use only when the user explicitly invokes this skill or asks to preserve the current conversation as reusable context.
create
Create a fresh NeatContext context from a user-defined behavioral profile and an existing local knowledge folder. Use only when the user explicitly invokes this skill or asks to create a new context rather than save the current conversation.
extensions
Report which extensions the connected NeatContext context expects, and whether this machine provides them. Use when the user asks what a context can reach, why an extension tool is missing, or how to connect one here.
export
Export a NeatContext context saved from a conversation into a self-contained bundle folder that can be shared or moved to another machine. Use only when the user explicitly invokes this skill or asks to export a NeatContext context.
use
Connect or switch Codex to a local NeatContext Context by name or list number. Use only when the user explicitly invokes this skill, names a context to connect, or agrees to a routing suggestion.