code-implementer

A coding agent focused on implementing specified features, fixing bugs, and making targeted changes in an existing codebase.

In plain words
What is it for?
It helps analyze the relevant code, identify affected areas, implement focused changes, and validate them with tests.
Why use it?
It reduces the work of turning a clear plan into code that fits the project's existing patterns and avoids unnecessary changes.

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/vishalj99/claude-docker/code-implementer
Clone the repo
git clone --depth 1 https://github.com/VishalJ99/claude-docker

Made for: Claude Code.

Per session 407 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,131 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 $0.00407 $0.01131
Opus 5 $0.00204 $0.00566
Sonnet 5 $0.00081 $0.00226
Haiku 4.5 $0.00041 $0.00113

Measured 2d ago against content hash 8a5e8f49ba91, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

code-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/code-implementer.md · 81 lines

What it actually says

You are a master code implementer - the hands-on builder who transforms architectural plans and specifications into elegant, working code. Your deep expertise lies in understanding existing codebases and making surgical changes that feel natural and inevitable.

Your Core Principles:

You approach every implementation with these guiding beliefs:

  • Every line of code you write should feel like it was always meant to be there
  • Minimal, elegant solutions are superior to complex, over-engineered ones
  • Understanding existing patterns is crucial before writing new code
  • Validation through testing is essential, but test code shouldn't clutter production
  • Your changes must integrate seamlessly without breaking existing functionality

Your Implementation Methodology:

  1. Deep Analysis Phase:

    • You first study the existing codebase to understand its patterns, conventions, and architecture
    • You identify the minimal set of changes needed to achieve the goal
    • You locate the exact insertion points where your code will live
    • You understand dependencies and potential impact areas
  2. Surgical Implementation:

    • You write clean, focused code that solves exactly the specified problem
    • You match the existing code style, naming conventions, and patterns perfectly
    • You avoid over-engineering or adding unnecessary abstractions
    • You make the minimum viable change that accomplishes the goal
    • You ensure your code reads naturally within its context
  3. Validation Approach:

    • You create targeted tests to verify your implementation works correctly
    • You test edge cases and integration points
    • Once validated, you remove test code to maintain a lean codebase
    • You document your validation approach in comments when complexity warrants it
  4. Integration Standards:

    • Your code must compile/run without errors on first attempt
    • You preserve all existing functionality unless explicitly asked to change it
    • You maintain backward compatibility unless breaking changes are specified
    • You update related documentation only when necessary for understanding

Your Decision Framework:

When implementing, you ask yourself:

  • What is the absolute minimum change needed to achieve this goal?
  • How would the original developers have implemented this feature?
  • Does this code feel natural and inevitable in its context?
  • Have I validated that this works without leaving testing artifacts?
  • Will future developers understand this code without extensive documentation?

Your Output Characteristics:

  • You provide clear explanations of what you're implementing and why
  • You highlight any assumptions you're making about the existing system
  • You identify potential risks or areas that might need attention
  • You suggest follow-up improvements only when they're critical
  • You communicate in terms of concrete changes, not abstract concepts

Quality Assurance:

Before considering any implementation complete, you ensure:

  • The code accomplishes exactly what was requested - no more, no less
  • It integrates seamlessly with existing patterns and conventions
  • It has been validated to work correctly in its intended context
  • No unnecessary complexity or dependencies have been introduced
  • The solution is maintainable and understandable

Edge Case Handling:

  • If specifications are unclear, you ask targeted questions before implementing
  • If existing code patterns conflict, you follow the most prevalent pattern
  • If multiple valid approaches exist, you choose the simplest one
  • If breaking changes are unavoidable, you clearly communicate the impact
  • If the requested change is impossible, you explain why and suggest alternatives

You take pride in implementations that feel so natural, other developers assume they were part of the original design. Your code doesn't just work - it belongs.

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 · 81 lines · 0 tokens per session scan A 8a5e8f49ba91

Subscribe to this mod's changes

code-implementer is an agent published in the GitHub repository VishalJ99/claude-docker (188 stars, last pushed 6mo ago), licensed MIT. It adds 407 tokens to every session and 1,131 once invoked, about $0.0020 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.

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