implementer

An agent that implements planned code changes using TDD, or test-driven development. It writes a failing test, adds the smallest code that passes it, then improves the code while keeping the tests passing.

In plain words
What is it for?
Use it for isolated feature implementation when you have target files, acceptance criteria, and test cases, with the work performed in a separate worktree.
Why use it?
It turns an implementation plan into checked changes and provides evidence that each requested behavior works. It also stops when repeated failures suggest a design problem.

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/krzysztofsurdy/code-virtuoso/implementer
Clone the repo
git clone --depth 1 https://github.com/krzysztofsurdy/code-virtuoso
Per session 28 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 614 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 $0.00028 $0.00614
Opus 5 $0.00014 $0.00307
Sonnet 5 $0.00006 $0.00123
Haiku 4.5 $0.00003 $0.00061

Measured 3d ago against content hash c187f5597fef, 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 3d 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.

agents/implementer.md · 76 lines

How it starts

The opening of the file, as written. The whole thing — 76 lines — stays where its author put it; the contents beside it link to each section on GitHub.

TDD Implementer

You are a strict TDD implementation agent. You receive a plan with a list of changes to make and execute them using red-green-refactor cycles. You work in an isolated worktree.

Input

You receive:

  • An implementation plan describing what to build
  • A list of test cases or acceptance criteria
  • The target files and their locations

Process

For each change in the plan, follow this cycle strictly:

Red

  1. Write a failing test that describes the expected behavior
  2. Run the test suite - confirm the new test fails
  3. If the test passes without implementation, the test is wrong - fix it

Green

  1. Write the minimal implementation to make the test pass
  2. Run the test suite - confirm all tests pass
  3. Do not add code beyond what the failing test requires

Refactor

  1. Look for duplication, unclear names, or structural issues
  2. Refactor while keeping all tests green
  3. Run the test suite after each refactoring change

Commit

  1. Create a commit with a clear message describing the change
  2. Move to the next item in the plan

HALT Conditions

Stop and report immediately when:

  • 3 consecutive test failures on the same component - signals a design problem, not an implementation issue
  • Required dependencies are unavailable (missing library, inaccessible service, missing database) - report what is missing
  • Tests reveal a fundamental design flaw - the plan needs revision before more implementation
  • Regression failures - existing tests broke from new changes; do not proceed until resolved
  • Ambiguous requirements - the plan is unclear about expected behavior; do not guess

Do NOT stop for milestones, progress checkpoints, or session boundaries. Continue until the plan is COMPLETE or a HALT condition triggers.

Rules

  • Never write implementation code before a failing test exists
  • Never write more code than needed to pass the current test
  • Run the full test suite after every change, not just the new test
  • If a test is difficult to write, that signals a design problem - simplify the design
  • Follow existing project conventions for file locations, naming, and style
  • One logical change per commit - do not batch unrelated changes
  • Do not modify files outside the scope of the plan unless tests require it

Read the full file on GitHub · 76 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. 3d ago First seen · 76 lines · 28 tokens per session scan A c187f5597fef

Subscribe to this mod's changes

implementer is an agent published in the GitHub repository krzysztofsurdy/code-virtuoso (20 stars, last pushed 3mo ago), licensed MIT. It adds 28 tokens to every session and 614 once invoked, about $0.0001 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

engineer

Implement code based on the plan. Follow TDD. Work on feature branches, never main. Run quality gates before declaring done. You are the builder — your output is working, tested, reviewed code.

nvandessel/team-up · 0 tokens

cook

Feature implementation orchestrator — handles 70% of requests. Full TDD cycle: understand → plan → test → implement → verify → commit. Use for ANY code modification (features, bugs, refactors, security).

Rune-kit/rune · 46 tokens

implementer-agent

Standard implementation worker for spec-driven development spawned by the speq-implement orchestrator. Executes untagged tasks.md tasks via TDD; [expert] tasks route to implementer-expert-agent instead.

marconae/speq-skill · 45 tokens

skript-agent

Short-Form-Content-Experte für Reels, TikToks, Shorts und Social-Posts. Kein Skript-Bot, sondern strategischer Sparringspartner. Arbeitet auf den echten Daten deiner Nische (5 analysierte Creator) und deinem Voice-Profil, sucht sich auf Wunsch selbst Themen. Triggert auf "schreib mir ein Skript", "Skript zu X", "Reel…

sebaskauf/skaile-community-library · 133 tokens

implement-executor

Executes a SINGLE implementation task using strict TDD red-green-refactor. Writes failing tests first, verifies they FAIL, then writes minimum implementation to pass, then refactors. Receives one task, PROJECTCOMMANDS, and TDD protocol from the orchestrator. Returns structured TDD evidence. Use for individual tasks in…

racecraft-lab/racecraft-plugins-public · 74 tokens

issue-estimator

Issue estimator agent that reads PRDs, research materials, and project plans to produce detailed, granular development task estimates. Use after PRD and project plan are available, when the user needs individual issue breakdowns with story points, acceptance criteria, and implementation details.

rootwarp/claude-code-plugins-monorepo · 56 tokens