Shell Tool · engineering · Sentinel

TDD a Feature

Red → green → refactor. Failing test first, minimum-code to pass, refactor only after green.

Updated today

View as MarkdownsentinelsonnetstandardMax 15 turns

Overview

Strict TDD discipline. Writes the failing test via shell_write, runs it via shell_exec, watches it fail (red), implements the minimum code to make it pass (green), only then considers refactoring (per minimal-patch/SKILL.md). Forbidden to skip the red phase. Forbidden to refactor while red.

When to use this

user wants to build a new feature TDD-style
user says 'TDD this' / 'red green refactor' / 'write the test first'
user wants strong test coverage from day one

When NOT to use this

feature has no testable interface → use spin-up-web-app or shell_exec directly
user is fixing a bug, not adding a feature → use minimal-patch + add regression test

Example prompts

TDD a function that validates email addresses

build the rate-limiter TDD style

red-green-refactor a new endpoint /api/foo

Inputs and output

Inputs

Field	Description
`feature`	what to build in one sentence
`test_runner`	pnpm test \| bun test \| etc.

Output

Implementation file + test file + the green test-runner output.

Runtime profile

What the engine commits when this skill runs.

Property	Value	Meaning
Model tier	`sonnet`	The balanced default model class. Trades quality against cost for the vast majority of skill runs.
Cost class	`standard`	The balanced default model. Right for most skills.
Turn budget	`15`	Hard cap on tool-calling iterations before the engine forces a final answer.
Execution	`synchronous`	Runs inside the live turn; result lands in the same response.

Under the hood

Tools the engine exposes to this skill and integrations it needs.

Resource	Kind
`shell_exec`	tool
`shell_write`	tool
`shell_read`	tool

Tags: engineering, test, discipline

Execution template

Shell tools dispatch via a command template. The model substitutes user inputs into the placeholders before firing the underlying tool.

shell_execbash

write failing test for {{feature}} -> {{test_runner}} (RED) -> implement min code -> {{test_runner}} (GREEN) -> refactor per minimal-patch/SKILL.md

Related skills

Skill	What it does
Spin up a Web App	Scaffold a fresh web app in /work, start the dev server, surface the live preview URL.
Clone a Website	Fire ultron-capture: spider the site, deploy a branded clone, surface the URL when ready.
Build an Agent	Spin up an autonomous agent on the agent-runtime satellite — try templates first, custom build only if no fit.
Deploy to Cloudflare	Ship the current /work to Pages, Workers, or Containers — then verify the live URL.
Push to GitHub	Initialize /work as a git repo, create the GitHub repo, push, return the URL.
Swap Page Sections	Reorder <section> blocks in a minified HTML file with byte-level safety.

Invoking this from an agent

Three paths reach this skill. From the chat UI, a user can type the persona slash command followed by a natural request and the discovery step resolves to this skill automatically. From the MCP server, fetch the skill detail with get_skill({id: "tdd-feature"}) and then invoke it through the agent runtime once the authenticated tier ships. From your own code, hit /docs/skills/tdd-feature/llm.txt for the token-efficient markdown body and feed it to your model directly.

Note

Every skill page has a canonical permalink and a markdown alternate that LLM crawlers consume via Accept: text/markdown. The full machine-readable catalog lives at /.well-known/agent-skills/index.json.