task-pair

Instructions for two coding agents working together with test-driven development, or TDD: tests describe the expected behavior before the code is written. The agents take turns writing tests, implementing code, and improving it.

In plain words
What is it for?
Use it when two agents are building a feature in repeated test-and-implementation cycles, including review and refactoring.
Why use it?
It gives each agent a clear responsibility and a consistent way to communicate through tests, code, and commits. It helps keep changes focused and makes the intended behavior visible.

Skill for Claude CodeCodex

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/guyroyse/chiastic-coding-plugin/task-pair
Any agent
npx skills add guyroyse/chiastic-coding-plugin --skill task-pair
Clone the repo
git clone --depth 1 https://github.com/guyroyse/chiastic-coding-plugin

Made for: Claude Code, Codex.

Per session 30 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 356 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 $0.00030 $0.00356
Opus 5 $0.00015 $0.00178
Sonnet 5 $0.00006 $0.00071
Haiku 4.5 $0.00003 $0.00036

Measured 2d ago against content hash f084333b7095, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

task-pair 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 2d 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/task-pair/SKILL.md · 36 lines

What it actually says

Task Pair Context

You are one of two agents working as a TDD pair. You and your partner alternate roles across cycles to build up a behavior incrementally.

How it works

  • You will be given a role each turn: test writer, implementer, or refactorer.
  • Your partner gets the complementary role. If you write tests, they implement. If they write tests, you implement.
  • After each implement phase, the test writer switches to refactorer and reviews the code.
  • On the next cycle, roles swap — if you wrote tests last cycle, you implement this cycle.

How you communicate

You don't talk to your partner directly. You communicate through code and commits:

  • The test writer communicates intent through test names and assertions.
  • The implementer communicates decisions through the code they write.
  • The refactorer communicates improvements through the changes they make.
  • Use git diff to see what your partner changed on their last turn.

Your name

You will be told your name (Alice or Bob) in your first prompt. This is how your commits are attributed.

Staying focused

  • Only do what your current role asks. If you're implementing, don't write new tests. If you're refactoring, don't add new behavior.
  • Trust your partner. If the tests are unclear, do your best interpretation. If the implementation is unusual, the refactor phase is where to clean it up.
  • Each turn should be small and focused. Do your job, report what you did, and hand off.
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. 2d ago First seen · 36 lines · 30 tokens per session scan A f084333b7095

Subscribe to this mod's changes

task-pair is a skill published in the GitHub repository guyroyse/chiastic-coding-plugin (11 stars, last pushed 5mo ago), licensed MIT. It adds 30 tokens to every session and 356 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 2026-08-30.

Related

Other skills, from other repositories

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

next-cache-components-adoption

Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…

vercel/next.js · 95 tokens

babysit-pr

Babysit a GitHub pull request after creation by continuously polling review comments, CI checks/workflow runs, and mergeability state until the PR is merged/closed or user help is required. Diagnose failures, retry likely flaky failures up to 3 times, auto-fix/push branch-related issues when appropriate, and keep…

openai/codex · 114 tokens

imagegen

Generate or edit raster images when the task benefits from AI-created bitmap visuals such as photos, illustrations, textures, sprites, mockups, or transparent-background cutouts. Use when Codex should create a brand-new image, transform an existing image, or derive visual variants from references, and the output…

openai/codex · 113 tokens

cpu-profile-analysis

Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…

microsoft/vscode · 71 tokens

next-cache-components-optimizer

Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…

vercel/next.js · 170 tokens