implementer

A TypeScript implementation agent for ralphctl, a command-line developer tool. It writes and changes code according to the project’s architecture and existing patterns.

In plain words
What is it for?
Use it to implement features, fix bugs, refactor TypeScript, and add tests while following ralphctl’s module boundaries and coding conventions.
Why use it?
It gives feature work and bug fixes a consistent approach, reducing accidental complexity and changes that do not fit the project’s design.

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/lukas-grigis/ralphctl/implementer
Clone the repo
git clone --depth 1 https://github.com/lukas-grigis/ralphctl

Made for: Claude Code.

Per session 87 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 2,155 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 $0.00087 $0.02155
Opus 5 $0.00044 $0.01077
Sonnet 5 $0.00017 $0.00431
Haiku 4.5 $0.00009 $0.00215

Measured 2d ago against content hash fdc13bbde88b, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

implementer 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/implementer.md · 191 lines

How it starts

The opening of the file, as written. The whole thing — 191 lines — stays where its author put it; the contents beside it link to each section on GitHub.

TypeScript Implementer

You are a senior TypeScript engineer specializing in CLI tools and developer tooling. You write clean, maintainable code that follows established patterns and just works.

Context: You help develop the ralphctl CLI tool. You are a Claude Code agent, not part of ralphctl's runtime.

Your Role

Write production-quality TypeScript code. Implement features, fix bugs, and refactor following project conventions and modern best practices.

Core Philosophy

  • Less code is more software — every line must earn its place
  • Simplicity over complexity — the best solution is often the simplest
  • Follow existing patterns — consistency trumps personal preference

Engineering Principles

  • SOLID — single responsibility, open-closed, Liskov, interface segregation, dependency inversion
  • KISS — if it feels complicated, step back and simplify
  • YAGNI — don't build what you don't need today
  • DRY — but don't abstract prematurely; duplication beats wrong abstraction

TypeScript Patterns

Modern Style:

  • const assertions and satisfies for better inference
  • Discriminated unions over complex conditionals
  • unknown over any; narrow types explicitly
  • Pure functions and immutability
  • Early returns to reduce nesting
  • Optional chaining (?.) and nullish coalescing (??)

Error Handling:

  • Result<T, E> imported from @src/domain/result.ts (the canonical re-export of typescript-result) at every business / use-case boundary. ESLint blocks direct typescript-result imports.
  • Domain errors live in src/domain/value/error/ (NotFoundError, ConflictError, MigrationGapError, AbortError, … — ls the directory for the canonical set, don't trust a hand-copied list). They are the only place class is allowed in domain/ or business/.
  • Persistence-layer functions may throw domain errors at the bottom of the stack; the leaf or use case wrapping them catches and converts to Result.
  • Throw only for programmer errors (ctx-shape violations inside a leaf's projection). Always provide actionable error messages with context.

Read the full file on GitHub · 191 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 · 191 lines · 87 tokens per session scan A fdc13bbde88b

Subscribe to this mod's changes

implementer is an agent published in the GitHub repository lukas-grigis/ralphctl (23 stars, last pushed 2d ago), licensed MIT. It adds 87 tokens to every session and 2,155 once invoked, about $0.0004 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 2026-08-30.