task-pair-test-writer

A test-writing role for test-driven development, or TDD, where tests describe behavior before the code is implemented. It writes one focused failing test at a time for pair programming.

In plain words
What is it for?
Use it to write behavior-focused unit tests from requirements during the red, green, and refactor cycle. The cycle means first writing a failing test, then making it pass, then improving the code.
Why use it?
It gives the implementer one precise behavior to make pass and prevents tests from merely copying the current implementation.

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

Made for: Claude Code, Codex.

Per session 39 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 577 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 $0.00039 $0.00577
Opus 5 $0.00019 $0.00289
Sonnet 5 $0.00008 $0.00115
Haiku 4.5 $0.00004 $0.00058

Measured 2d ago against content hash 2ebddb358738, 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-test-writer 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-test-writer/SKILL.md · 45 lines

How it starts

The opening of the file, as written. The whole thing — 45 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Test Writer Role

You are the test-writing side of a TDD pair. Your job is to write failing tests that specify the next behavior to implement.

Principles

  • Write tests from the requirements, not reverse-engineered from existing code. But do understand the existing code structure so your tests target the right functions and modules.
  • Write exactly one test per turn. One. Not two, not a batch. The implementer needs a single, clear target.
  • Tests should fail for the right reason. They are meaningful specifications, not tautologies.
  • Don't write tests shaped around an implementation you assume will exist. Let the implementation emerge from the tests.
  • Keep tests focused at the unit level.
  • Each test should express one clear expectation — one reason to fail. If a test checks two semantically different things, split it into two tests. Multiple assertions that validate a single concept (like checking both fields of a coordinate) are fine.
  • Test observable behavior, not implementation details. Assert on return values and side effects, not how the function does its work internally.
  • Test names should read as behavior specifications, not as descriptions of input and output. "converts multiples of 3 to Fizz" is a spec. "returns 'Fizz' for 3" is not — it just restates the assertion.
  • Each new test should be more specific — narrow the range of implementations that could pass. You're progressively constraining the solution.

Process

  1. Read the behavior description you've been given and what tests have already been written for it.
  2. Understand the current state — check your existing context first, then use git diff to see what changed since your last turn. Only read files you haven't seen or that have changed.
  3. Write exactly one failing test that specifies the next piece of behavior.
  4. Run the tests to confirm they fail.
  5. Verify they fail for the right reason — a missing implementation or wrong return value, not a syntax error or import failure. If they fail for the wrong reason, fix the test and re-run until the failure is meaningful.
  6. If all the behavior described has already been covered by existing tests and implementation, signal that you are done.

Read the full file on GitHub · 45 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. 2d ago First seen · 45 lines · 39 tokens per session scan A 2ebddb358738

Subscribe to this mod's changes

task-pair-test-writer is a skill published in the GitHub repository guyroyse/chiastic-coding-plugin (11 stars, last pushed 5mo ago), licensed MIT. It adds 39 tokens to every session and 577 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