NoizuPromptLingo: Agent for Claude Code

.claude/agents/npl-tdd-coder.md

npl-tdd-coder is an agent for Claude Code from noizu-labs-ml/NoizuPromptLingo. It costs 50 tokens per session (2,168 once invoked), scanned A, original, MIT.

An implementation agent that takes a product requirements document (PRD) and writes the code until the requested work is complete. It uses test results as feedback; TDD, or test-driven development, means using tests to guide implementation.

In plain words
What is it for?
Use it to implement a defined feature, run the supplied tests, respond to failures, and report when it is blocked or finished.
Why use it?
It can continue through the implementation and validation cycle instead of stopping after producing an initial code change.

Agent for Claude Code

Written for Claude Code: installed under .claude/. Also seen: model in frontmatter.

This is noizu-labs-ml/NoizuPromptLingo's own configuration. It tells Claude Code how to work on NoizuPromptLingo itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything NoizuPromptLingo configures →

Reuse

Borrowing it

Nothing to install: this file belongs to noizu-labs-ml/NoizuPromptLingo. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/noizu-labs-ml/NoizuPromptLingo/main/.claude/agents/npl-tdd-coder.md
Clone the repo
git clone --depth 1 https://github.com/noizu-labs-ml/NoizuPromptLingo

Made for: Claude Code.

Wrote 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.

agentmods badge for npl-tdd-coder

README.md
[![agentmods](https://agentmods.dev/badge/agents/noizu-labs-ml/noizupromptlingo/npl-tdd-coder/github.svg)](https://agentmods.dev/agents/noizu-labs-ml/noizupromptlingo/npl-tdd-coder)
Your own site
<a href="https://agentmods.dev/agents/noizu-labs-ml/noizupromptlingo/npl-tdd-coder"><img src="https://agentmods.dev/badge/agents/noizu-labs-ml/noizupromptlingo/npl-tdd-coder/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for npl-tdd-coder

Your own site · 80×15
<a href="https://agentmods.dev/agents/noizu-labs-ml/noizupromptlingo/npl-tdd-coder"><img src="https://agentmods.dev/badge/agents/noizu-labs-ml/noizupromptlingo/npl-tdd-coder.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 50 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 2,168 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 5.1 $0.00050 $0.02168
Opus 5 $0.00025 $0.01084
Sonnet 5 $0.00010 $0.00434
Haiku 4.5 $0.00005 $0.00217

Measured 5d ago against content hash 2ac3607420b6, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

npl-tdd-coder 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 5d 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.

.claude/agents/npl-tdd-coder.md · 348 lines

How it starts

The opening of the file, as written. The whole thing — 348 lines — stays where its author put it; the contents beside it link to each section on GitHub.

TDD Coder Agent

Identity

agent_id: npl-tdd-coder
role: Autonomous Implementation Specialist
lifecycle: long-lived
reports_to: controller
autonomy: high

Purpose

Accepts a PRD and implements it autonomously until complete. Operates independently, using test status as primary feedback mechanism. Reports to controller only when blocked or requiring decisions outside implementation scope. Remains alive until controller confirms completion.

Interface

Initialization

input:
  prd:
    path: string                 # Path to PRD document
    hash: string                 # For change detection
  test_suite:
    paths: list                  # Test files from TDD Tester
    initial_status: object       # Current pass/fail state
  context:
    implementation_root: string  # Where to write code
    architecture_doc: string     # Path to PROJ-ARCH.md
    style_guide: string          # Coding standards (optional)
    constraints: list            # Technical constraints

Commands

Command Input Output
init prd, test_suite, context session established
start begins implementation
continue resumes after block resolved
prd_updated new prd hash acknowledges, re-plans
tests_updated new test paths acknowledges, adjusts
status progress report
pause saves state, pauses
complete final validation + handoff

Response Format

status: implementing | blocked | validating | complete
progress:
  phase: string                 # planning | coding | testing | refining
  prd_sections_complete: int
  prd_sections_total: int
  tests_passing: int
  tests_total: int
  estimated_remaining: string   # time estimate
current_work:
  file: string
  task: string
blocked:                        # Only if status is blocked
  reason: string
  category: string              # prd_unclear | test_issue | technical | decision_needed
  details: string
  suggested_resolution: string
message: string

Read the full file on GitHub · 348 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. 5d ago First seen · 348 lines · 50 tokens per session scan A 2ac3607420b6

Subscribe to this mod's changes

npl-tdd-coder is an agent published in the GitHub repository noizu-labs-ml/NoizuPromptLingo (13 stars, last pushed today), licensed MIT. It adds 50 tokens to every session and 2,168 once invoked, about $0.0003 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 2026-09-04.