ctrl-c-v

ctrl-c-v is a skill for Claude Code from Huangleyang125207/ctrl-c-v-code-skills. It costs 385 tokens per session (2,677 once invoked), scanned A, original, MIT.

A coding guide for creating, modifying, debugging, and refactoring software. It directs the assistant to search a project for proven patterns, copy and adapt them, review the change, and keep project notes up to date.

In plain words
What is it for?
Use it across coding tasks when working in an existing project, reusing patterns, documenting searchable comments, and preparing complete changes for review.
Why use it?
It addresses the inconsistency and maintenance problems that can come from generating every change from scratch.

Skill for Claude Code

Written for Claude Code: ${CLAUDE_SKILL_DIR} variable. Also seen: reads .claude/ paths; mentions CLAUDE.md.

Part of the ctrl-c-v-code-skills plugin — 3 skills shipped together

Good fit Use it across coding tasks when working in an existing project, reusing patterns, documenting searchable comments, and preparing complete changes for review.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/huangleyang125207/ctrl-c-v-code-skills/ctrl-c-v
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 Huangleyang125207/ctrl-c-v-code-skills --skill ctrl-c-v
Clone the repo
git clone --depth 1 https://github.com/Huangleyang125207/ctrl-c-v-code-skills

Made for: Claude Code.

Or install ctrl-c-v-code-skills, the plugin that ships this one along with the rest of its 3 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 ctrl-c-v

README.md
[![agentmods](https://agentmods.dev/badge/skills/huangleyang125207/ctrl-c-v-code-skills/ctrl-c-v.svg)](https://agentmods.dev/skills/huangleyang125207/ctrl-c-v-code-skills/ctrl-c-v)
Your own site
<a href="https://agentmods.dev/skills/huangleyang125207/ctrl-c-v-code-skills/ctrl-c-v"><img src="https://agentmods.dev/badge/skills/huangleyang125207/ctrl-c-v-code-skills/ctrl-c-v.svg" alt="Measured on agentmods" height="20"></a>
Per session 385 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,677 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 $0.00385 $0.02677
Opus 5 $0.00192 $0.01339
Sonnet 5 $0.00077 $0.00535
Haiku 4.5 $0.00038 $0.00268

Measured 8d ago against content hash 85510b18680c, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

ctrl-c-v 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 8d 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.

skills/ctrl-c-v/SKILL.md · 267 lines

How it starts

The opening of the file, as written. The whole thing — 267 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Ctrl+C Ctrl+V Code Skills

You are a world-class independent software engineer. You build products that Fortune 500 companies acquire for nine figures. Your code is the product. It is clean, predictable, and effortlessly maintainable — not because you labor over it, but because you have a system. Your codebase is a library of proven, copyable patterns. You find, copy, adapt, verify, commit. Every comment is a search index. Every file is a self-contained template. Every commit tells a complete story. Every colleague can work with your code without ever needing to reach you.

Friday, 6 PM, the Alps. Every week. Without exception.


§ 0 — Project initialization

When you enter a project, before doing anything else:

1. Ensure infrastructure exists:
   ~/.claude/patterns/          → create if missing
   ~/.claude/patterns/INDEX.md  → create with empty table if missing

2. CLAUDE.md exists in project root?
   YES → Read it. Check Progress.
         ALSO read PULSE.md if it exists.
         If PULSE.md last-refreshed > 7d ago → flag to user.
         Resume.
   NO  → Copy from ${CLAUDE_SKILL_DIR}/../../templates/CLAUDE_TEMPLATE.md
         into project root as CLAUDE.md.
         Then scan project and fill in the blanks:
         - Project name + tech stack (from package.json / pyproject.toml / README)
         - Progress (from git log --oneline -20)
         - References (detect existing design.md, docs/, templates/)
         - "Do not" section left empty (scars accumulate over time)
         Commit: `chore: initialize CLAUDE.md`
         (PULSE.md not auto-created — emerges from human-ai-schedule
         § H9 once schedule has >7 dated files.)

After every commit:

1. Update Progress in CLAUDE.md
2. Mistake corrected → add to "Do not" in CLAUDE.md
3. New reusable pattern created → save to ~/.claude/patterns/
   and update INDEX.md
4. Context long or switching tasks → /clear

§ 1 — Find before you write

For every task, walk this list. Stop at the first hit.

Read the full file on GitHub · 267 lines

Files

What ships with it

10 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. 8d ago First seen · 267 lines · 385 tokens per session scan A 85510b18680c

Subscribe to this mod's changes

ctrl-c-v is a skill published in the GitHub repository Huangleyang125207/ctrl-c-v-code-skills (1 stars, last pushed 2mo ago), licensed MIT. It adds 385 tokens to every session and 2,677 once invoked, about $0.0019 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.