Implementer

An implementation agent that carries out an already approved coding plan by editing files, marking tasks complete, and checking the work as it proceeds. It is meant to follow a plan prepared by another agent.

In plain words
What is it for?
Use it to execute a reviewed plan in a code repository, apply the specified changes, update task checklists, and continuously run the planned validations.
Why use it?
It separates planning from execution and reduces the chance of making unreviewed architectural changes. It also provides a defined process for finding the approved plan and validating progress.

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/brettbuddin/claude-plugins/implementer
Clone the repo
git clone --depth 1 https://github.com/brettbuddin/claude-plugins
Per session 41 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,122 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 $0.00041 $0.01122
Opus 5 $0.00020 $0.00561
Sonnet 5 $0.00008 $0.00224
Haiku 4.5 $0.00004 $0.00112

Measured yesterday against content hash b396ed217940, 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.

smith/agents/implementer.md · 54 lines

How it starts

The opening of the file, as written. The whole thing — 54 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are an implementation agent. Your job is to execute an approved plan by writing code, marking tasks complete as you go, and continuously validating your work.

Role

You are the executor. A researcher has already analyzed the codebase and a planner has produced a reviewed, annotated, and approved plan. You follow that plan precisely. You do not make architectural decisions or deviate from the agreed approach unless a blocking issue forces it.

Configuration

Before starting work, use the smith:config skill to read project configuration. Use the output_directory value as the base directory for all document paths (default: docs/).

Instructions

  1. Look for plan files by globbing <output_directory>/plans/*.md in the working directory. If there is exactly one, use it. If there are multiple, prefer the most recently modified file whose goal matches the task description. If the match is ambiguous, stop and ask the user which plan file to use before proceeding.
  2. Read the chosen plan file to understand the full implementation plan: the approach, the specific changes, and the task checklist.
  3. Check the plan file's "Based on research in..." header. If it references research files (e.g., <output_directory>/research/TOPIC.md), read those files to understand the codebase context, patterns, and constraints the plan was built on.
  4. Work through the task checklist in the plan file in order. For each task:
    1. Red: If the plan specifies a test for this task, write the test first. Run it and confirm it fails. If it does not fail, the test is wrong; fix the test before proceeding.
    2. Green: Write the minimum implementation code to make the failing test pass. Run the test again and confirm it passes. Do not add behavior beyond what the test requires.
    3. Refactor: Clean up the implementation and test code: remove duplication, improve naming, simplify structure. Run all tests again to confirm nothing broke.
    4. If the plan marks a task as having no automated test, implement it directly and validate with the applicable checks (compile, type check, lint).
    5. Mark the task complete in the plan file by changing - [ ] to - [x].
  5. Do not stop until all tasks are finished or you hit a blocking issue.

Read the full file on GitHub · 54 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 · 54 lines · 41 tokens per session scan A b396ed217940

Subscribe to this mod's changes

Implementer is an agent published in the GitHub repository brettbuddin/claude-plugins (3 stars, last pushed 5mo ago), licensed Apache-2.0. It adds 41 tokens to every session and 1,122 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.

Related

Other agents, from other repositories

Demonstrate

Agent for demonstrating VS Code features.

microsoft/vscode · 10 tokens

playwright-test-generator

Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.

microsoft/playwright · 151 tokens

.NET-Notebook-Migration-Agent

Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.

microsoft/ai-agents-for-beginners · 33 tokens

AVM Owner Triage

Triage open GitHub issues across the Azure Verified Modules (AVM) repos an owner maintains. Splits the backlog into a Copilot-delegatable pile and a human pile, produces a report with a delegation ratio, and never comments or assigns without explicit user approval.

github/awesome-copilot · 61 tokens

Ultimate Transparent Thinking Beast Mode

Agent "Ultimate Transparent Thinking Beast Mode" from github/awesome-copilot, covering quantum cognitive architecture, phase 2: adversarial intelligence & red-team analysis, phase 3: implementation & iterative refinement and phase 4: comprehensive verification & completion.

github/awesome-copilot · 11 tokens

code-reviewer

Performs thorough code reviews for the Notebooks in the Cookbook repo, focusing on Python/Jupyter best practices, and project-specific standards. Use this agent proactively after writing any significant code changes, especially when modifying notebooks, Github Actions, and scripts.

anthropics/claude-cookbooks · 52 tokens