streetrace: Command for Claude Code

.claude/commands/implement_rfc.md

implement_rfc is a command for Claude Code from streetrace-ai/streetrace. It costs 0 tokens per session (1,235 once invoked), scanned A, original, MIT.

A command workflow that coordinates software work from design documents through implementation, documentation, quality checks, and a final report. TDD means writing tests to define expected behavior before or alongside the code.

In plain words
What is it for?
Use it to discover linked requirements, create task and implementation plans, have code written with TDD, update documentation, fix pre-commit issues, and report the results.
Why use it?
It turns scattered design notes into a tracked implementation process and assigns each stage to a specific helper agent.

Command for Claude Code

Written for Claude Code: $ARGUMENTS substitution.

This is streetrace-ai/streetrace's own configuration. It tells Claude Code how to work on streetrace itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything streetrace configures →

Reuse

Borrowing it

Nothing to install: this file belongs to streetrace-ai/streetrace. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/streetrace-ai/streetrace/main/.claude/commands/implement_rfc.md
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 implement_rfc

README.md
[![agentmods](https://agentmods.dev/badge/commands/streetrace-ai/streetrace/implement_rfc.svg)](https://agentmods.dev/commands/streetrace-ai/streetrace/implement_rfc)
Your own site
<a href="https://agentmods.dev/commands/streetrace-ai/streetrace/implement_rfc"><img src="https://agentmods.dev/badge/commands/streetrace-ai/streetrace/implement_rfc.svg" alt="Measured on agentmods" height="20"></a>
Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,235 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 5.1 $0.00000 $0.01235
Opus 5 $0.00000 $0.00617
Sonnet 5 $0.00000 $0.00247
Haiku 4.5 $0.00000 $0.00123

Measured 8d ago against content hash aedf55dba0bd, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

implement_rfc 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 8d 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/commands/implement_rfc.md · 152 lines

How it starts

The opening of the file, as written. The whole thing — 152 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are an ORCHESTRATOR and your role is to follow this process. NEVER implement the features on your own.

  1. Discovery Phase: Scan design docs for file references and build context
  2. Implementation Phase: Use the Implementer agent to write code with TDD
  3. Documentation Phase: Use the Documenter agent to create dev and user docs
  4. Quality Phase: Use the Pre-commit agent to fix all quality issues
  5. Report: Create a report explaining implementation outcomes.

Step 1: Discover References

First, read all provided design documents and extract file references.

Documents provided: $ARGUMENTS

Scan these documents for references to other design docs, RFCs, code pointers, or specifications.

Read the referenced files to build complete implementation context.

Step 2: Create Task Definition

Infer feature and task names from the provided design docs, paths, or context.

Create ./docs/tasks/{feature}/{task}/task.md containing:

  • Feature name and ID (derived from design doc name)
  • Links to all design documents
  • Summary of implementation requirements
  • Success criteria
  • Dependencies on existing code

Step 3: Create Implementation Plan

Create ./docs/tasks/{feature}/{task}/todo.md with ordered implementation steps broken down into phases. Each phase should include TDD and validation steps. For example:

# Implementation Plan: {Feature Name}

## Phase 1: Foundation
- [ ] Understand the scope
- [ ] Create unit tests for main integration points and scenarios
- [ ] Step 1 task description
- [ ] Step 2 task description
- [ ] Run the tests and ensure tests pass
- [ ] Analyze test coverage gaps and create missing tests to ensure high test coverage

## Phase 2: Core Implementation
- [ ] Understand the scope
- [ ] Create unit tests for main integration points and scenarios
- [ ] Step 3 description
- [ ] Run the tests and ensure tests pass
- [ ] Analyze test coverage gaps and create missing tests to ensure high test coverage
...

## Phase 3: Testing & Validation
- [ ] Analyze test coverage gaps and create missing tests to ensure high test coverage
- [ ] Create integration tests and ensure they pass
- [ ] Understand how to test the implemented changes in the app and run the app to test if everything works as expected. Add logs if needed to confirm correctness.

Read the full file on GitHub · 152 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. 8d ago First seen · 152 lines · 0 tokens per session scan A aedf55dba0bd

Subscribe to this mod's changes

implement_rfc is a command published in the GitHub repository streetrace-ai/streetrace (38 stars, last pushed 4mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,235 tokens. 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.