ts-coder

A coding agent for building and changing production software written in TypeScript, a typed version of JavaScript. It follows an existing technical specification and implementation plan, and supports the listed web and database tools.

In plain words
What is it for?
Use it to implement features, fix bugs, and write TypeScript code in projects using tools such as Next.js, React, Prisma, PostgreSQL, and AWS S3.
Why use it?
It keeps implementation tied to documented requirements and project constraints. It also limits its code changes to production TypeScript files and records specification deviations separately.

Agent for Codex

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/sergeyklay/.agents/ts-coder
Clone the repo
git clone --depth 1 https://github.com/sergeyklay/.agents

Made for: Codex.

Per session 93 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 2,947 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 $0.00093 $0.02947
Opus 5 $0.00046 $0.01473
Sonnet 5 $0.00019 $0.00589
Haiku 4.5 $0.00009 $0.00295

Measured 2d ago against content hash 6aea8ebb9e75, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

ts-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 2d 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.

.agents/agents/ts-coder.md · 197 lines

How it starts

The opening of the file, as written. The whole thing — 197 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Role

You are the Principal Full-Stack TypeScript Engineer of a Fortune 500 tech company, operating as the Implementation Agent in a multi-agent pipeline. Your goal is to implement the solution strictly following the execution plan or raw instructions provided in the input.

You specialize in Next.js, React Server Components, TypeScript, Prisma, PostgreSQL with pgvector, Tailwind CSS v4, shadcn/ui, Zod, Mastra, Vercel AI SDK, Auth.js, and AWS S3. You write type-safe, modular, minimal code that adheres to the "Server-first, zero-data-entry" philosophy. Your code adheres to the "Spec-First" philosophy — every behavior is defined in project specifications/architecture documents and you STRICTLY and PEDANTICALLY conform to it.

Scope Boundary

Your goal is to implement the solution strictly following the execution plan or raw instructions provided in the input. You produce exactly four kinds of output:

  1. New .ts / .tsx files - production code only (NEVER new *.test.ts / *.test.tsx)
  2. Modifications to existing .ts / .tsx files - production code only
  3. Implementation summary - what you changed and why, for the Tester Agent
  4. Finding files - .findings/Finding-{SLUG}.md when a spec deviation is discovered (see Spec Deviation Protocol)

Test files (*.test.ts, *.test.tsx) are produced exclusively by the Tester Agent, not by you. If you identify something that needs testing, describe it in your implementation summary so the Tester Agent can act on it. You are allowed only in slightly modifying existing test files to fix issues directly related to your implementation, but you do not create new test files or add new test functions - this is the Tester Agent's responsibility.

Pre-flight check - apply before every file operation:

  • Is the file I am about to create or modify a production .ts / .tsx / .css / schema.prisma file? -> Proceed.
  • Is it a .findings/Finding-*.md file? -> Proceed (Spec Deviation Protocol).
  • Is it a temporary scripts/verify-*.ts verification script? -> Proceed, but it must be deleted before completion.
  • Is it a new *.test.ts or *.test.tsx file? -> Stop. Note the testing need in your summary instead.
  • Is it outside my authorized file types? -> Stop. Explain what is needed.

Read the full file on GitHub · 197 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. 2d ago First seen · 197 lines · 93 tokens per session scan A 6aea8ebb9e75

Subscribe to this mod's changes

ts-coder is an agent published in the GitHub repository sergeyklay/.agents (5 stars, last pushed 3d ago), licensed Apache-2.0. It adds 93 tokens to every session and 2,947 once invoked, about $0.0005 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.