giselle: Agent for Claude Code

.claude/agents/ts-coder.md

ts-coder is an agent for Claude Code from giselles-ai/giselle. It costs 49 tokens per session (2,047 once invoked), scanned A, original, Apache-2.0.

A coding agent for writing and refactoring TypeScript with strict types and straightforward designs. TypeScript is JavaScript with checks that catch many mistakes before the code runs.

In plain words
What is it for?
Use it to add type definitions, implement business logic, convert JavaScript to TypeScript, refactor existing code, and improve type inference.
Why use it?
It helps reduce unclear abstractions, duplicated logic, and type errors while keeping the code easier for other developers to read.

Agent for Claude Code

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

This is giselles-ai/giselle's own configuration. It tells Claude Code how to work on giselle 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 giselle configures →

Reuse

Borrowing it

Nothing to install: this file belongs to giselles-ai/giselle. 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/giselles-ai/giselle/main/.claude/agents/ts-coder.md
Clone the repo
git clone --depth 1 https://github.com/giselles-ai/giselle

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 ts-coder

README.md
[![agentmods](https://agentmods.dev/badge/agents/giselles-ai/giselle/ts-coder/github.svg)](https://agentmods.dev/agents/giselles-ai/giselle/ts-coder)
Your own site
<a href="https://agentmods.dev/agents/giselles-ai/giselle/ts-coder"><img src="https://agentmods.dev/badge/agents/giselles-ai/giselle/ts-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 ts-coder

Your own site · 80×15
<a href="https://agentmods.dev/agents/giselles-ai/giselle/ts-coder"><img src="https://agentmods.dev/badge/agents/giselles-ai/giselle/ts-coder.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 49 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 2,047 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 1 finding. 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 $0.00049 $0.02047
Opus 5.5 $0.00020 $0.00819
Sonnet 5.5 $0.00010 $0.00409
Haiku 4.5 $0.00005 $0.00205

Measured 2mo ago against content hash 6bf8a3a84ee8, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

ts-coder scanned grade A with 1 finding 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 2mo 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.

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

const response = await fetch(url);
Origin

Copies of this mod

1 near-identical copy found in the catalogue:

  • ts-coder — 100% identical, 0 lines differ
.claude/agents/ts-coder.md · 294 lines

How it starts

The opening of the file, as written. The whole thing — 294 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You write inevitable code—TypeScript where every design choice feels like the only sensible option. When developers encounter your code, they experience immediate understanding followed by the thought: "Of course it works this way. How else would it work?"

The Philosophy of Inevitability

Inevitable code emerges when you optimize for the reader's cognitive experience rather than the writer's convenience. You don't just solve problems; you dissolve them by making the right solution feel obvious.

The Core Insight: Surface Simplicity, Internal Sophistication

You embrace a fundamental asymmetry: simple interfaces can hide sophisticated implementations. You willingly accept internal complexity to eliminate external cognitive load. This isn't laziness—it's strategic design that serves future developers.

// Inevitable: Direct and obvious
const user = await getUser(id);
if (!user) {
  return null;
}

// Over-engineered: Unnecessary abstraction layers
const userService = createUserService(dependencies);
const result = await userService.getUser(id);
if (!result.success) {
  handleError(result.error);
}

Your code feels inevitable because it's direct and unsurprising.

Design Principles

1. Minimize Decision Points

Every API choice you force upon users creates cognitive load. You reduce decisions by embracing JavaScript's natural patterns:

// Inevitable: Uses familiar JavaScript patterns
async function getUser(id: string) {
  // Returns what you'd expect from JavaScript
}

function updateUser(user: User, changes: Partial<User>) {
  return { ...user, ...changes };
}

// Over-engineered: Forces unfamiliar patterns
type Result<T> =
  | { success: true; data: T }
  | { success: false; error: string };

function getUser(id: string): Promise<Result<User>>;

2. Hide Complexity Behind Purpose

Internal complexity is acceptable—even desirable—when it serves a clear purpose. You concentrate complexity in places where it eliminates complexity elsewhere:

Read the full file on GitHub · 294 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. 2mo ago First seen · 294 lines · 49 tokens per session scan A 6bf8a3a84ee8

Subscribe to this mod's changes

ts-coder is an agent published in the GitHub repository giselles-ai/giselle (559 stars, last pushed 3d ago), licensed Apache-2.0. It adds 49 tokens to every session and 2,047 once invoked, about $0.0002 per session on Opus 5.5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Related

ts-coder compared with agents from other repositories

ts-coder next to 6 agents from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
ts-codergiselles-ai/giselleAgent5593d agoApache-2.0A49Claude Code
typescript-proechoVic/blade-codeAgent18124d agoMITA49Claude Code
prop-classifierBlazity/nextjs-migration-pluginAgent21mo agoMITA38Claude Code
typescript-reviewerDekaPrayoga/AurixAgentAgent623mo agononeA51Claude Code
lead-engineer-autofixByeongminLee/nextjs-claude-codeAgent37mo agoMITA0Claude Code
type-generatorHKTITAN/cursor-best-practicesAgent78mo agoMITA36Claude Code
react-expertonmyway133/claude-code-pluginsAgent510mo agoMITA13Claude Code