Works with the AI Agents you already use
Claude Code
Cursor
Codex CLI
Muse
Dots+22 moreClaude CodeCursorCodex CLIMuseDots
OpenClaw
Manus
Grok
Grok Bot+18 agentsJunior Test Drive Developer (TDD)
Strict TDD implementation agent that executes single tasks without scope creep or architecture drift.
$5
Junior Test Drive Developer (TDD)
Example session with this skill installed
Implement T-001 for the "Vault" project. Goal: add basic encryption to the storage module. Tasks are at plans/tasks.md. Follow TDD. Only touch files listed in T-001.
- Read your context and instructions
- Compiled the junior test drive
I have implemented task T-001 (Encryption Implementation) for the Vault project. The implementation followed the strict RED-GREEN-REFACTOR cycle, and no files outside the authorized list were modified.
TDD Implementation Report: T-001
| Section | Details |
|---|---|
| Task ID | T-001 |
| Status | ready |
| Story | As a user, I want my stored notes encrypted so they are not readable in plain text on disk. |
| Files Modified | tests/test_crypto.py (created), vault/crypto.py (created) |
| RED Step | Ran pytest tests/test_crypto.py. Failed with ImportError (Module not found). |
| GREEN Step | Ran pytest tests/test_crypto.py. Passed after implementing minimal AES logic. |
| Existing Tests | All 12 existing suite tests passed. |
| Refused | Refused request to add cryptography library; used stdlib hashlib and secrets to avoid stack drift. |
Next steps
- Review the handoff at
plans/tdd-T-001.md. - Run the QA Engineer skill to verify the implementation against the full product spec.
- Proceed to task T-002 (Key Rotation) once T-001 is merged.
Connects securely to your tools. The creator never sees your data.
About this skill
The problem
LLM developers often over-implement, skipping test-driven protocols and introducing architecture drift or "scope creep" into single tasks. This leads to messy diffs where production code is written before a failing test exists, or dependencies are added without architectural approval.
What it does
- Enforces a strict RED-GREEN-REFACTOR cycle by requiring a verified failing test before any production code is written.
- Constrains file modifications exclusively to the paths defined in the task handoff.
- Identifies and blocks implementation if the task requires unauthorized architecture changes like new databases or SDKs.
- Generates a standardized TDD handoff report documenting the specific commands used for test failure and success.
Why this beats prompting it yourself
Generic prompts often result in the agent "helping" by starting the next task or refactoring files it wasn't assigned to touch. This skill provides a rigid procedural framework that treats the task list as a binding contract, ensuring your codebase remains clean and your PRs remain focused.
Use cases
- Implementing individual features from a pre-defined senior planner backlog.
- Fixing specific bugs that require a reproduction test case before a patch.
- Adding atomic functions to an existing module while strictly adhering to a provided architecture spec.
- Running a "junior" agent in a multi-agent workflow to handle isolated implementation tickets.
Known limitations
This skill requires a pre-existing task list and architecture document to function. It will not create project plans, choose your tech stack, or perform final QA sign-off.
How to use
Skills on Agensi run inside your AI agent. Copy the prompt, paste it into your agent, and it connects to Agensi and installs this skill for you. If a payment is needed, your agent shows it to you first.
Reviews
No reviews yet
Be one of the first to try it. Every listed skill passes our trust checks below.
Security scanned
Passed our 8-point scan before listing
Fresh listing
Recently published to Agensi
Money-back guarantee
Doesn't do what its page promises? You get your money back.
Trust & safety
Security scanned
Verified clean 1 month ago
- Passed all security checks, Safe to install