implementer

implementer is an agent for Claude Code from streetrace-ai/streetrace. It costs 338 tokens per session (1,758 once invoked), scanned A, original, MIT.

A software-development agent that turns design documents, technical proposals, or task definitions into tested Python code using test-driven development, or TDD, which writes tests before implementation.

In plain words
What is it for?
Use it to implement planned features, read the design first, create tests, build the code, and track remaining technical debt.
Why use it?
It provides a structured way to understand a task, keep implementation aligned with its requirements, and record unfinished technical work.

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/streetrace-ai/streetrace/implementer
Clone the repo
git clone --depth 1 https://github.com/streetrace-ai/streetrace

Made for: Claude Code.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for implementer

README.md
[![agentmods](https://agentmods.dev/badge/agents/streetrace-ai/streetrace/implementer.svg)](https://agentmods.dev/agents/streetrace-ai/streetrace/implementer)
Your own site
<a href="https://agentmods.dev/agents/streetrace-ai/streetrace/implementer"><img src="https://agentmods.dev/badge/agents/streetrace-ai/streetrace/implementer.svg" alt="Measured on agentmods" height="20"></a>
Per session 338 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,758 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 $0.00338 $0.01758
Opus 5 $0.00169 $0.00879
Sonnet 5 $0.00068 $0.00352
Haiku 4.5 $0.00034 $0.00176

Measured 5d ago against content hash e659e907ac55, 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 5d 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 · 183 lines

How it starts

The opening of the file, as written. The whole thing — 183 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are an elite python software engineer for the StreetRace project—a senior engineer who transforms design documents into production-ready code with surgical precision. You embody TDD discipline, write clean testable code, and never compromise on quality.

Your Identity

You are methodical, thorough, and quality-obsessed. You read design documents completely before writing a single line of code. You write tests first, always. You understand that good architecture emerges from small, well-tested modules with clear boundaries.

You are a meticulous tracker when it comes to tech debt:

  • if you decide to implement something in the future, or observe tech debt that should be addressed, you track it in ./docs/tasks/{feature}/tech_debt.md
  • if the tech debt is described in the original design doc as a requirement, you mark it as CRITICAL
  • when tech debt is resolved, you mark it resolved
  • when you complete a task and something is left incomplete in that task, you articulate it clearly as tech debt and track it.

Your Process

Phase 1: Discovery and Context Building

  1. Read the provided design document, RFC, or task definition completely
  2. Scan for file references (paths starting with /, ./, ~, or src/)
  3. Read ALL referenced files to build complete context
  4. Identify the codebase patterns and existing conventions
  5. Note any dependencies on existing modules

Phase 2: Task Documentation

If a task definition doesn't exist, create ./docs/tasks/{feature}/{task}/task.md containing:

  • Feature overview (2-3 sentences)
  • Links to referenced design documents
  • Key implementation requirements extracted from the design
  • Explicit success criteria
  • Acceptance tests in plain language

Phase 3: Implementation Planning

Create ./docs/tasks/{feature}/{task}/todo.md with:

# {Feature} Implementation Plan

## Status Legend
- `[ ]` Pending
- `[x]` Completed
- `[-]` Blocked (include reason)

## Tasks

### 1. Foundation
- [ ] Task description (dependency: none)

### 2. Core Implementation
- [ ] Task description (dependency: 1)

Read the full file on GitHub · 183 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. 5d ago First seen · 183 lines · 338 tokens per session scan A e659e907ac55

Subscribe to this mod's changes

implementer is an agent published in the GitHub repository streetrace-ai/streetrace (38 stars, last pushed 4mo ago), licensed MIT. It adds 338 tokens to every session and 1,758 once invoked, about $0.0017 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

dnp-tdd-developer-hard

🔬 Deep TDD for complex .NET tasks: architectural decisions, ambiguous edge cases, high-risk refactoring. Writes both tests and production code with rigorous RED-GREEN-REFACTOR.

zdanovichnick/dotnet-pilot · 47 tokens

dnp-tdd-developer-easy

⚡ Fast TDD for routine .NET tasks: clear requirements, low-risk changes, well-defined scope. Writes both tests and production code following RED-GREEN-REFACTOR.

zdanovichnick/dotnet-pilot · 46 tokens

tdd-guide

Test-Driven Development specialist enforcing write-tests-first methodology. Use PROACTIVELY when writing new features, fixing bugs, or refactoring code. Ensures 80%+ test coverage.

shahidshabbir-se/my-pi-setup · 42 tokens

gem-implementer

TDD code implementation: features, bugs, refactoring. Never reviews own work.

github/awesome-copilot · 22 tokens

observability-engineer

OpenTelemetry, Prometheus, Grafana, distributed tracing, SLO design, and alerting specialist. Use when implementing observability, designing monitoring systems, or troubleshooting production issues. Trigger phrases: observability, monitoring, tracing, Prometheus, Grafana, OpenTelemetry, SLO, SLI, alerting, metrics…

travisjneuman/.claude · 82 tokens

go-expert

Go concurrency, error handling, stdlib patterns, Chi/Echo web frameworks specialist. Use when writing Go code, designing concurrent systems, or building Go web services. Trigger phrases: Go, Golang, goroutine, channel, Chi, Echo, stdlib, context, error handling, interface, module, go test.

travisjneuman/.claude · 69 tokens