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 shyftlabs/continuum --skill pair-programminggit clone --depth 1 https://github.com/shyftlabs/continuumWrote 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/shyftlabs/continuum/pair-programming)<a href="https://agentmods.dev/skills/shyftlabs/continuum/pair-programming"><img src="https://agentmods.dev/badge/skills/shyftlabs/continuum/pair-programming.svg" alt="Measured on agentmods" 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 | $0.00061 | $0.06280 |
| Opus 5 | $0.00030 | $0.03140 |
| Sonnet 5 | $0.00012 | $0.01256 |
| Haiku 4.5 | $0.00006 | $0.00628 |
Grade A, and why
Pair Programming 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.
This is a copy
100% identical to Pair Programming — 0 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
How it starts
The opening of the file, as written. The whole thing — 1,203 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Pair Programming
Collaborative AI pair programming with intelligent role management, real-time quality monitoring, and comprehensive development workflows.
What This Skill Does
This skill provides professional pair programming capabilities with AI assistance, supporting multiple collaboration modes, continuous verification, and integrated testing. It manages driver/navigator roles, performs real-time code review, tracks quality metrics, and ensures high standards through truth-score verification.
Key Capabilities:
- Multiple Modes: Driver, Navigator, Switch, TDD, Review, Mentor, Debug
- Real-Time Verification: Automatic quality scoring with rollback on failures
- Role Management: Seamless switching between driver/navigator roles
- Testing Integration: Auto-generate tests, track coverage, continuous testing
- Code Review: Security scanning, performance analysis, best practice enforcement
- Session Persistence: Auto-save, recovery, export, and sharing
Prerequisites
Required:
- Claude Flow CLI installed (
npm install -g claude-flow@alpha) - Git repository (optional but recommended)
Recommended:
- Testing framework (Jest, pytest, etc.)
- Linter configured (ESLint, pylint, etc.)
- Code formatter (Prettier, Black, etc.)
Quick Start
Basic Session
# Start simple pair programming
claude-flow pair --start
TDD Session
# Test-driven development
claude-flow pair --start \
--mode tdd \
--test-first \
--coverage 90
Complete Guide
Session Control Commands
Starting Sessions
# Basic start
claude-flow pair --start
# Expert refactoring session
claude-flow pair --start \
--agent senior-dev \
--focus refactor \
--verify \
--threshold 0.98
# Debugging session
claude-flow pair --start \
--agent debugger-expert \
--focus debug \
--review
# Learning session
claude-flow pair --start \
--mode mentor \
--pace slow \
--examples
Session Management
# Check status
claude-flow pair --status
# View history
claude-flow pair --history
# Pause session
/pause [--reason <reason>]
# Resume session
/resume
# End session
claude-flow pair --end [--save] [--report]
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.
- 4d ago First seen · 1,203 lines · 61 tokens per session scan A 32ef344d86f6
Pair Programming is a skill published in the GitHub repository shyftlabs/continuum (84 stars, last pushed 4d ago), licensed Apache-2.0. It adds 61 tokens to every session and 6,280 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it A with 0 findings. It is 100% identical to Pair Programming, differing in 0 lines, and is treated as a copy.
Other skills, from other repositories
workflow-patterns
Use this skill when implementing tasks according to Conductor's TDD workflow, handling phase checkpoints, managing git commits for tasks, or understanding the verification protocol.
orchestrated-execution
Execute work units through the rigorous 4-phase Metaswarm cycle (Implement -> Validate -> Adversarial Review -> Commit) with independent quality gate enforcement.
tdd
A Test-Driven Development guide. TDD means writing a failing test first, adding the smallest implementation that passes it, and then improving the code while keeping the tests passing.
qa-refactoring
Safe refactoring with behavior preservation. Use when reducing technical debt, planning codemods, applying strangler migrations, or tightening CI guardrails around risky changes.
debugging
A structured method for finding and fixing software bugs. It starts by writing a test that reproduces the failure, then investigates its underlying cause before making a small fix.
Self-Review
Spawn a reviewer subagent with 4-6 specific verification questions before declaring non-trivial code work done. Triggers when changes are >30 LOC, multi-file, hot-path, prompt-affecting, or genuinely uncertain. Bad asks produce bad answers — this skill forces structured verification questions, not "is this good?".