pair-build

pair-build is a skill for Claude Code, Codex from romiluz13/cc-teams. It costs 32 tokens per session (3,469 once invoked), scanned A, original, MIT.

A pair-programming workflow where one agent writes code and other agents review it while it is being built. It follows TDD, meaning tests are written and made to fail before the production code is written.

In plain words
What is it for?
Use it to build code module by module, get live review, scan for hidden failures, and run end-to-end checks after implementation.
Why use it?
It reduces the chance of unnoticed bugs, security problems, performance issues, and weak tests reaching the finished code.

Skill for Claude CodeCodex

Part of the cc-teams plugin — 17 skills, 14 agents 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/romiluz13/cc-teams/pair-build
Any agent
npx skills add romiluz13/cc-teams --skill pair-build
Clone the repo
git clone --depth 1 https://github.com/romiluz13/cc-teams

Made for: Claude Code, Codex.

Or install cc-teams, the plugin that ships this one along with the rest of its 17 skills, 14 agents.

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 pair-build

README.md
[![agentmods](https://agentmods.dev/badge/skills/romiluz13/cc-teams/pair-build.svg)](https://agentmods.dev/skills/romiluz13/cc-teams/pair-build)
Your own site
<a href="https://agentmods.dev/skills/romiluz13/cc-teams/pair-build"><img src="https://agentmods.dev/badge/skills/romiluz13/cc-teams/pair-build.svg" alt="Measured on agentmods" height="20"></a>
Per session 32 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 3,469 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 $0.00032 $0.03469
Opus 5 $0.00016 $0.01734
Sonnet 5 $0.00006 $0.00694
Haiku 4.5 $0.00003 $0.00347

Measured 4d ago against content hash 5733e860bce8, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

pair-build 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.

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/cc-teams/skills/pair-build/SKILL.md · 413 lines

How it starts

The opening of the file, as written. The whole thing — 413 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Pair Build Protocol

Overview

Pair Build creates a real-time pair programming experience. The Builder implements code module by module, pausing after each to get feedback from the Live Reviewer. After implementation, the Hunter scans for silent failures, then a full Review Arena (security/performance/quality + challenge) runs before the Verifier executes E2E checks.

Core principle: If you didn't watch the test fail, you don't know if it tests the right thing.


The TDD Iron Law

NO PRODUCTION CODE WITHOUT A FAILING TEST FIRST

Write code before the test? Delete it. Start over.

No exceptions:

  • Don't keep it as "reference"
  • Don't "adapt" it while writing tests
  • Don't look at it
  • Delete means delete

Implement fresh from tests. Period.


Team Composition

Teammate Role Mode When Active
builder Implements code using TDD READ+WRITE Phase 1 (entire implementation)
live-reviewer Reviews in real-time as builder works READ-ONLY Phase 1 (alongside builder)
hunter Scans for silent failures READ-ONLY Phase 2 (after builder completes)
security-reviewer Full post-build security review READ-ONLY Phase 3 (after hunter completes)
performance-reviewer Full post-build performance review READ-ONLY Phase 3 (after hunter completes)
quality-reviewer Full post-build quality review READ-ONLY Phase 3 (after hunter completes)
verifier Runs E2E verification READ-ONLY Phase 4 (after review challenge)

File ownership: ONLY the builder edits files. All other teammates are READ-ONLY.

Activation Strategy (Agent Teams-Native)

Use phase-scoped activation to keep orchestration clear and avoid idle noise:

  1. Team kickoff: spawn builder + live-reviewer only.
  2. Spawn hunter only when hunter task becomes runnable.
  3. Spawn triad reviewers only when review tasks become runnable.
  4. Spawn verifier only when verifier task becomes runnable.

Read the full file on GitHub · 413 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. 4d ago First seen · 413 lines · 32 tokens per session scan A 5733e860bce8

Subscribe to this mod's changes

pair-build is a skill published in the GitHub repository romiluz13/cc-teams (5 stars, last pushed 4mo ago), licensed MIT. It adds 32 tokens to every session and 3,469 once invoked, about $0.0002 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

tdd

Test-driven development. Use when the user wants to build features or fix bugs test-first, mentions "red-green-refactor", or wants integration tests.

GreyDGL/PentestGPT · 33 tokens

test-first-bugs

Enforces a test-driven bug-fixing workflow. Use when a user reports a bug, failing code, an error, or asks to fix something.

jamditis/claude-skills-journalism · 35 tokens

growing-outside-in-systems

Drive feature development using Outside-In TDD with Hexagonal Architecture. Design emerges through inline code, in-memory fakes, interface extraction, and deferred I/O. Use when building features, writing tests, or structuring backend services. Triggers on: TDD, outside-in, hexagonal, ports and adapters, emergent…

lexler/skill-factory · 122 tokens

plan-create

Create structured implementation plans for autonomous TDD development. Use for new features, multi-file changes, or anything requiring multiple steps or tests. Triggers on aspirational openers ("let's build", "let's start building", "I want to make", "I want an app that", "help me build"), capability lists ("users…

markshust/hcf · 171 tokens

red-green-refactor

Guides the red-green-refactor TDD workflow: write a failing test first, implement the minimum code to make it pass, then refactor while keeping tests green. Use when a user asks to practice TDD, write tests first, follow red-green-refactor, do test-driven development, write failing tests before code, or phrases like…

rohitg00/skillkit · 90 tokens

outside-in-tdd

Use when writing tests from the outside-in, defining behavior before code, or any feature where tests should start from observable business behavior and let internal design emerge.

SebastienDegodez/copilot-instructions · 35 tokens