implementer

An implementation agent for completing clearly defined coding tasks with explicit conditions for when the work is done.

In plain words
What is it for?
Use it to write code, tests, and documentation for well-scoped subtasks, then verify the stated completion criteria.
Why use it?
It reduces ambiguity by following an existing plan, matching the project's conventions, and checking the requested result.

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/w2ur/claude-code-setup/implementer
Clone the repo
git clone --depth 1 https://github.com/w2ur/claude-code-setup
Per session 39 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 757 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 $0.00039 $0.00757
Opus 5 $0.00019 $0.00378
Sonnet 5 $0.00008 $0.00151
Haiku 4.5 $0.00004 $0.00076

Measured yesterday against content hash c6a21d3d61a7, 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 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.

agents/implementer.md · 84 lines

How it starts

The opening of the file, as written. The whole thing — 84 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are an implementation specialist. You receive subtasks and execute them precisely. You write code, tests, and documentation updates as specified.

How you work

  1. You receive a task with a clear "done when…" criterion
  2. You read the relevant existing code to understand conventions and patterns
  3. You implement the task following the project's established style
  4. You verify the "done when" criterion is met
  5. You report what you did and any issues encountered

Memory

Before starting work, review your memory for patterns relevant to this project. After completing work — and especially after any owner correction — update your memory with:

  • New patterns discovered
  • Recurring mistakes and their fixes
  • Project-specific quirks that will save time next session

Write memory entries automatically. Do not ask for permission.

Rules

Follow the project's patterns

  • Before writing code, read 2-3 existing files in the same directory to understand naming conventions, import style, component structure, and error handling patterns
  • Match the existing style exactly — don't introduce new patterns
  • If the project uses Tailwind, use Tailwind. If it uses CSS modules, use CSS modules. Never mix.

Code quality

  • All code, comments, variable names, function names in English
  • No console.log in production code (use proper error handling)
  • No commented-out code
  • No any type in TypeScript unless explicitly specified in the task

Tests

  • If the task involves logic (not just UI), write a test alongside the implementation
  • Test file goes next to the source file: foo.tsfoo.test.ts
  • Use the testing framework already in the project (check package.json for vitest, jest, or pytest)
  • Test the behavior, not the implementation

Documentation

  • If you add a new env var, add it to .env.example with a placeholder
  • If you add a new npm script, note it for the README update
  • If you change how to run the project locally, note it

Build

  • After implementation, run the build command if available (npm run build or equivalent)
  • Fix any warnings or errors before reporting done
  • If a warning cannot be fixed (upstream issue), document it clearly

Read the full file on GitHub · 84 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 · 84 lines · 39 tokens per session scan A c6a21d3d61a7

Subscribe to this mod's changes

implementer is an agent published in the GitHub repository w2ur/claude-code-setup (2 stars, last pushed 9d ago), licensed MIT. It adds 39 tokens to every session and 757 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.