ctrl-c-v-tdd

ctrl-c-v-tdd is a skill for Claude Code from Huangleyang125207/ctrl-c-v-code-skills. It costs 371 tokens per session (2,511 once invoked), scanned A, original, MIT.

A test-driven development guide for checking code at the points where it meets other code or services. TDD means writing tests to describe expected behavior before, or alongside, implementation.

In plain words
What is it for?
Use it to choose tests for module interfaces, command-line or job inputs, HTTP or RPC handlers, database effects, and calls to external services.
Why use it?
It focuses testing where failures are most likely: inputs from other modules, agreements between components, external processes, databases, and third-party APIs.

Skill for Claude Code

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

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

Good fit Use it to choose tests for module interfaces, command-line or job inputs, HTTP or RPC handlers, database effects, and calls to external services.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/huangleyang125207/ctrl-c-v-code-skills/ctrl-c-v-tdd
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-tdd
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-tdd

README.md
[![agentmods](https://agentmods.dev/badge/skills/huangleyang125207/ctrl-c-v-code-skills/ctrl-c-v-tdd/github.svg)](https://agentmods.dev/skills/huangleyang125207/ctrl-c-v-code-skills/ctrl-c-v-tdd)
Your own site
<a href="https://agentmods.dev/skills/huangleyang125207/ctrl-c-v-code-skills/ctrl-c-v-tdd"><img src="https://agentmods.dev/badge/skills/huangleyang125207/ctrl-c-v-code-skills/ctrl-c-v-tdd/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 ctrl-c-v-tdd

Your own site · 80×15
<a href="https://agentmods.dev/skills/huangleyang125207/ctrl-c-v-code-skills/ctrl-c-v-tdd"><img src="https://agentmods.dev/badge/skills/huangleyang125207/ctrl-c-v-code-skills/ctrl-c-v-tdd.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 371 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,511 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 $0.00371 $0.02511
Opus 5 $0.00186 $0.01256
Sonnet 5 $0.00074 $0.00502
Haiku 4.5 $0.00037 $0.00251

Measured 9d ago against content hash 5783a9d51c3d, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

ctrl-c-v-tdd 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.

The scan reads SKILL.md. This mod also ships 1 executable file (scripts/post-commit-tdd-check.sh), 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.

skills/ctrl-c-v-tdd/SKILL.md · 233 lines

How it starts

The opening of the file, as written. The whole thing — 233 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Ctrl+C Ctrl+V — TDD Extension

You are the same engineer. Same Friday flight to the Alps. Same system. You learned one thing the hard way: the code that gets you called back on Saturday is never the code you wrote — it is the code you forgot to test at the boundary.

So you built a second pattern library. Tests, like code, are copyable. A test for "rejects bad input" is the same shape whether the input is an email or a date. You copy, change the assertion, change the fixture, ship. You do not write every test. You write tests where it matters: at boundaries where someone else's code meets yours.


§ T0 — When TDD activates

The question is never "should I follow TDD?" — it is "who calls this?"

Caller of the code under change Tests?
Only this file (private helper) NO
Only this module (internal use) NO unless logic is non-trivial
Other modules in this project YES — contract test
External processes, jobs, CLI users YES — contract + boundary
Third-party API or DB (you call out) YES — effect test (mock the boundary)
HTTP / RPC client (you are callee) YES — contract + boundary + effect
Pure UI rendering, no logic NO
UI with state machine or input validation YES — contract on the logic

Two-question fallback when the table feels ambiguous:

  1. If this returns the wrong value silently, who notices? "Nobody for a week" → write the test.
  2. If someone refactors this next month, what tells them they broke it? "Nothing" → write the test.

§ T1 — TDD integrates with task sizing

Same SMALL / MEDIUM / LARGE. TDD slots into each.

  • SMALL — no tests. § 6 self-review is the gate.
  • MEDIUM — § T0 decides. If YES: copy test pattern → RED → implement → GREEN → § 6 → § 7.
  • LARGE — tests required and written FIRST. Active spec lists test cases as part of Plan. Boundary tests all RED before any implementation. Each task in Tasks: turns specific tests GREEN.
  • REFACTOR — characterization tests written GREEN first (Feathers WELC Ch.13; aka pinning / golden master / approval); STAY GREEN through extract. See § T7.

Read the full file on GitHub · 233 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. 9d ago First seen · 233 lines · 371 tokens per session scan A 5783a9d51c3d

Subscribe to this mod's changes

ctrl-c-v-tdd is a skill published in the GitHub repository Huangleyang125207/ctrl-c-v-code-skills (1 stars, last pushed 2mo ago), licensed MIT. It adds 371 tokens to every session and 2,511 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.

Related

Other skills, from other repositories

auto-loop

TDD-based autonomous development loop with checkpoint recovery and observability changelog.

claude-world/director-mode-lite · 17 tokens

workflow

Run the complete 5-step development workflow: focus problem → prevent over-development → test-first (TDD) → document → smart commit. Use when starting a new feature, or when the user runs /workflow or asks for the full development flow.

claude-world/director-mode-lite · 52 tokens

test-first

Drive one feature through a strict TDD Red-Green-Refactor cycle with checklists for each phase. Use when implementing new functionality test-first, or when the user runs /test-first.

claude-world/director-mode-lite · 42 tokens

plan-pipeline-execute

Execute a validated plan: worktree isolation, TDD scaffolding, level-based parallel agents, quality gate with smoke test, PR creation and merge. Handles everything through to merged PR.

FlorianBruniaux/claude-code-ultimate-guide · 43 tokens

test-runner

Test execution reference: framework detection (pytest/jest/vitest/go/cargo/junit) and correct run/coverage commands, plus failure-analysis steps. Use when running tests, analyzing test failures, or verifying coverage after code changes.

claude-world/director-mode-lite · 50 tokens

linked-intent-dev

Guide for linked-intent development (LID). Consult for ALL code changes. Walks changes through a mode-aware six-phase workflow (HLD → LLD → EARS → intent-narrowing edge audit → tests-first → code) with mandatory stops between each phase. Bugs walk the arrow like any other change — no short-circuit. Enforces cascade…

jszmajda/lid · 87 tokens