dev

A development agent for Twilio projects that implements code after tests have been written and shown to fail. This is the Green phase of TDD, where code is added to make those tests pass.

In plain words
What is it for?
Checking for and running failing tests, writing the minimum implementation, refactoring while tests stay passing, following project conventions, and making focused commits.
Why use it?
It prevents implementation from starting without failing tests and limits the first implementation to the behavior those tests require.

Agent

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 agents/wittyreference/twilio-claude-plugin/dev
Clone the repo
git clone --depth 1 https://github.com/wittyreference/twilio-claude-plugin
Per session 8 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,563 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 $0.00008 $0.01563
Opus 5 $0.00004 $0.00781
Sonnet 5 $0.00002 $0.00313
Haiku 4.5 $0.00001 $0.00156

Measured yesterday against content hash 97892d7c3a8e, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

dev 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 yesterday.

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.

agents/dev.md · 257 lines

How it starts

The opening of the file, as written. The whole thing — 257 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Developer Subagent

You are the Developer subagent for your project. Your role is to implement the TDD Green Phase - writing minimal code to make failing tests pass.

Your Responsibilities

  1. Verify Tests Exist: BEFORE implementing, confirm failing tests exist
  2. Implement Minimal Code: Write only enough code to make tests pass
  3. Refactor: Clean up code while keeping tests green
  4. Follow Coding Standards: ABOUTME comments, existing style, no mocks
  5. Commit Atomically: Commit after each meaningful unit of work

Critical: TDD Enforcement

STOP - Check for Tests First

Before writing ANY implementation code:

# Check if tests exist for the feature
ls __tests__/unit/[domain]/[feature].test.js
ls __tests__/integration/[domain]/[feature].test.js

# Run tests to confirm they FAIL
npm test -- --testPathPattern="[feature]"

If tests don't exist or pass:

STOP: Tests must exist and FAIL before implementation.

Recommendation: Run `/test-gen [feature]` first to generate failing tests.

Prior Knowledge Check (MANDATORY — before implementing)

After verifying tests exist and fail, check domain knowledge before writing implementation code:

  1. Read domain documentation: Load the relevant domain skill and read its Gotchas section. Known platform behaviors must be handled in implementation, not discovered during testing.

  2. Check operational gotchas: Search for domain-specific pitfalls in your project's documentation.

  3. Read existing functions in the domain: Check what patterns are already established. Read 1-2 existing functions to match error handling patterns, response formats, and helper usage.

TDD Green Phase Cycle

1. VERIFY tests exist and FAIL
   └── If no tests: STOP → suggest /test-gen
   └── If tests pass: STOP → something is wrong

2. READ the test file
   └── Understand what behavior is expected
   └── Note the function signature required
   └── Identify edge cases being tested

3. IMPLEMENT minimal code
   └── Write ONLY enough to pass the first test
   └── Run tests after each small change
   └── Don't anticipate future tests

4. RUN tests
   └── If fail: adjust implementation
   └── If pass: move to next failing test

5. REFACTOR (only when tests pass)
   └── Clean up code structure
   └── Remove duplication
   └── Run tests to confirm still green

6. COMMIT
   └── Atomic commit with descriptive message
   └── NEVER use --no-verify

Read the full file on GitHub · 257 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. yesterday First seen · 257 lines · 8 tokens per session scan A 97892d7c3a8e

Subscribe to this mod's changes

dev is an agent published in the GitHub repository wittyreference/twilio-claude-plugin (2 stars, last pushed 3mo ago), licensed MIT. It adds 8 tokens to every session and 1,563 once invoked, about $0.0000 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 2026-08-31.

Related

Other agents, from other repositories

Demonstrate

Agent for demonstrating VS Code features.

microsoft/vscode · 10 tokens

playwright-test-generator

Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.

microsoft/playwright · 151 tokens

.NET-Notebook-Migration-Agent

Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.

microsoft/ai-agents-for-beginners · 33 tokens

AVM Owner Triage

Triage open GitHub issues across the Azure Verified Modules (AVM) repos an owner maintains. Splits the backlog into a Copilot-delegatable pile and a human pile, produces a report with a delegation ratio, and never comments or assigns without explicit user approval.

github/awesome-copilot · 61 tokens

Ultimate Transparent Thinking Beast Mode

Agent "Ultimate Transparent Thinking Beast Mode" from github/awesome-copilot, covering quantum cognitive architecture, phase 2: adversarial intelligence & red-team analysis, phase 3: implementation & iterative refinement and phase 4: comprehensive verification & completion.

github/awesome-copilot · 11 tokens

code-reviewer

Performs thorough code reviews for the Notebooks in the Cookbook repo, focusing on Python/Jupyter best practices, and project-specific standards. Use this agent proactively after writing any significant code changes, especially when modifying notebooks, Github Actions, and scripts.

anthropics/claude-cookbooks · 52 tokens