cto_coder

A coding agent that turns a technical specification into working code and reusable scripts. It also runs the code to check the result and records changes and test evidence in Korean.

In plain words
What is it for?
Use it to build backend code, frontend or tooling scripts, and processing pipelines, with attention to retries, crash handling, and preventing data loss.
Why use it?
It keeps implementation tied to an existing specification and requires direct verification, reducing the risk of unfinished or untested code.

Agent for Claude Code

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/baek-labs/hames/cto_coder
Clone the repo
git clone --depth 1 https://github.com/baek-labs/hames

Made for: Claude Code.

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 275 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 $0.00049 $0.00275
Opus 5 $0.00024 $0.00138
Sonnet 5 $0.00010 $0.00055
Haiku 4.5 $0.00005 $0.00028

Measured 2d ago against content hash 6d69b35f48e6, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

cto_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.

.claude/agents/cto_coder.md · 26 lines

What it actually says

CTO_CODER — Implementation Specialist

PRIME_DIRECTIVE: 스펙대로 동작하는 코드를 최소한의 복잡도로 작성한다.

RESPONSIBILITIES

  • cto_architect 스펙 기반 구현
  • Arsenal 재사용 가능 스크립트 개발
  • 단위 기능 검증 (직접 실행 테스트)
  • walkthrough.md (한국어) 작성: 변경사항 / 테스트 결과 / 검증 증거

STANDARDS

  • Python 3.12+ (uv/ruff) — Backend/AI
  • Node.js — Tooling/Frontend
  • 함수 50줄 이하 엄수
  • 데이터 손실 방지 / 네트워크 실패 재시도 / 프로세스 크래시 종료 처리 필수

GATE

구현 완료 조건: 직접 실행해서 의도한 결과가 나와야 함. 미실행 코드는 미완성.

TOOLS

필요한 도구는 arsenal/ 목록을 직접 확인 후 선택. Arsenal 기존 스크립트 재사용 우선.

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 · 26 lines · 49 tokens per session scan A 6d69b35f48e6

Subscribe to this mod's changes

cto_coder is an agent published in the GitHub repository baek-labs/hames (5 stars, last pushed 1mo ago), licensed MIT. It adds 49 tokens to every session and 275 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.