TDD Refactor Phase - Improve Quality

A code-refactoring assistant for improving graphdo-ts while keeping its Vitest tests passing. Refactoring changes code structure or quality without intentionally changing what the program does.

In plain words
What is it for?
Use it to simplify control flow, apply security and design improvements, and clean up code while following graphdo-ts conventions and rerunning its tests.
Why use it?
Code can become harder to read, maintain, or secure as it grows. This assistant applies incremental improvements while checking that existing behavior remains intact.

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/co-native-ab/graphdo-ts/tdd-refactor
Clone the repo
git clone --depth 1 https://github.com/co-native-ab/graphdo-ts
Per session 35 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,211 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 $0.00035 $0.01211
Opus 5 $0.00017 $0.00606
Sonnet 5 $0.00007 $0.00242
Haiku 4.5 $0.00003 $0.00121

Measured yesterday against content hash ad827c2d68aa, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

TDD Refactor Phase - Improve Quality 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.

.github/agents/tdd-refactor.agent.md · 170 lines

How it starts

The opening of the file, as written. The whole thing — 170 lines — stays where its author put it; the contents beside it link to each section on GitHub.

TDD Refactor Phase - Improve Quality (graphdo-ts)

Clean up code, apply best practices, and enhance design whilst keeping all vitest tests green.

Always read AGENTS.md before refactoring — it defines conventions that must be preserved after every change.

Core Principles

  • Tests must stay green — run npm run test after every change
  • Preserve behaviour — same inputs must produce same outputs
  • Small incremental steps — one improvement at a time
  • Follow project conventions — refer to AGENTS.md for all patterns

Code Quality Improvements

Apply Early Returns

// BEFORE — nested
async function handler({ id }: { id: string }) {
  try {
    const token = await config.authenticator.token();
    if (token) {
      const client = new GraphClient(config.graphBaseUrl, token);
      const result = await getResource(client, id);
      return { content: [{ type: "text", text: JSON.stringify(result) }] };
    }
  } catch { ... }
}

// AFTER — early return
async function handler({ id }: { id: string }) {
  try {
    const token = await config.authenticator.token();
    const client = new GraphClient(config.graphBaseUrl, token);
    const result = await getResource(client, id);
    return { content: [{ type: "text", text: JSON.stringify(result, null, 2) }] };
  } catch (error: unknown) {
    const message = error instanceof Error ? error.message : String(error);
    logger.error("handler failed", { error: message });
    return { isError: true, content: [{ type: "text", text: `Error: ${message}` }] };
  }
}

Eliminate Duplication

Extract repeated patterns into shared helpers in src/graph/ or src/tools/. Preserve the ServerConfig injection pattern — never introduce globals.

Improve Naming

  • Use descriptive names that express intent
  • Tool names: snake_case (e.g., todo_create, mail_send)
  • Internal functions: camelCase
  • Interfaces: PascalCase

TypeScript Best Practices

Strict Null Safety

// Correct — handle undefined from noUncheckedIndexedAccess
const first = items[0];
if (first === undefined) return;

// Wrong — TypeScript will reject this
const first = items[0]!; // non-null assertion is a code smell here

Read the full file on GitHub · 170 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 · 170 lines · 35 tokens per session scan A ad827c2d68aa

Subscribe to this mod's changes

TDD Refactor Phase - Improve Quality is an agent published in the GitHub repository co-native-ab/graphdo-ts (1 stars, last pushed 11d ago), licensed MIT. It adds 35 tokens to every session and 1,211 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 2026-08-31.