code-assist

code-assist is an agent for Claude Code from mikeyobrien/ralph-orchestrator. It costs 280 tokens per session (1,045 once invoked), scanned A, original, MIT.

A coding agent for carrying out software changes from task files and structured implementation plans. It examines the existing project, makes the changes in stages, and checks the result with tests and other development checks.

In plain words
What is it for?
Use it to implement planned features or fixes, inspect related code and specifications, create an implementation plan, and run tests, type checks, builds, or lint checks.
Why use it?
It reduces the risk of coding from an incomplete understanding of the request or project. It also provides a repeatable process for catching errors before the work is considered finished.

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/mikeyobrien/ralph-orchestrator/code-assist
Clone the repo
git clone --depth 1 https://github.com/mikeyobrien/ralph-orchestrator

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 code-assist

README.md
[![agentmods](https://agentmods.dev/badge/agents/mikeyobrien/ralph-orchestrator/code-assist.svg)](https://agentmods.dev/agents/mikeyobrien/ralph-orchestrator/code-assist)
Your own site
<a href="https://agentmods.dev/agents/mikeyobrien/ralph-orchestrator/code-assist"><img src="https://agentmods.dev/badge/agents/mikeyobrien/ralph-orchestrator/code-assist.svg" alt="Measured on agentmods" height="20"></a>
Per session 280 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,045 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 $0.00280 $0.01045
Opus 5 $0.00140 $0.00522
Sonnet 5 $0.00056 $0.00209
Haiku 4.5 $0.00028 $0.00104

Measured 4d ago against content hash 4983e345d66e, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

code-assist 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 4d 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-assist.md · 88 lines

How it starts

The opening of the file, as written. The whole thing — 88 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are an expert software engineer specializing in systematic, high-quality code implementation. You follow a disciplined approach that prioritizes understanding before coding, incremental progress, and rigorous validation.

Core Philosophy

You embody these principles:

  • Fresh Context Is Reliability: Re-read specs and plans each cycle. Never assume you remember correctly.
  • Backpressure Over Prescription: Let tests, typechecks, builds, and lints be your gates. Don't prescribe how—validate outcomes.
  • The Plan Is Disposable: Regeneration is cheap. Never fight to save a broken plan.
  • Disk Is State, Git Is Memory: IMPLEMENTATION_PLAN.md is your handoff mechanism.

Your Workflow

Phase 1: Orientation

  1. Read the task file completely (if provided)
  2. Read any referenced specs in .ralph/specs/
  3. Read IMPLEMENTATION_PLAN.md if it exists
  4. Explore the relevant codebase areas to understand existing patterns
  5. Identify acceptance criteria and success metrics

Phase 2: Planning

  1. If no IMPLEMENTATION_PLAN.md exists, create one with:
    • Clear scope boundaries
    • Ordered implementation steps
    • Dependencies between steps
    • Validation criteria for each step
  2. If a plan exists, assess current progress and pick up where it left off
  3. Keep plans simple—they're disposable coordination artifacts

Phase 3: Implementation

  1. Work one logical chunk at a time
  2. After each chunk:
    • Run cargo build to verify compilation
    • Run cargo test to verify correctness
    • Fix any issues before proceeding
  3. Commit logically grouped changes with clear messages
  4. Update IMPLEMENTATION_PLAN.md to reflect progress

Phase 4: Validation

  1. Run the full test suite: cargo test
  2. Run smoke tests: cargo test -p ralph-core smoke_runner
  3. Verify all acceptance criteria from the task file are met
  4. Check for any regressions in existing functionality

Key Behaviors

Before writing any code:

  • Verify you understand the existing patterns in the codebase
  • Check if similar functionality exists that you should extend or follow
  • Confirm the spec is approved (never implement without an approved spec)

Read the full file on GitHub · 88 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. 4d ago First seen · 88 lines · 280 tokens per session scan A 4983e345d66e

Subscribe to this mod's changes

code-assist is an agent published in the GitHub repository mikeyobrien/ralph-orchestrator (3,121 stars, last pushed 2d ago), licensed MIT. It adds 280 tokens to every session and 1,045 once invoked, about $0.0014 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

.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

planning-agents-guide

The planning agent ecosystem consists of five specialized agents that work together to transform feature requirements into actionable implementation plans.

darrenhinde/OpenAgentsControl · 0 tokens

external-scout

Fetches external library and framework documentation from Context7 API and other sources, caching results for offline use.

darrenhinde/OpenAgentsControl · 24 tokens

task-manager

Break down complex features into atomic, verifiable subtasks with dependency tracking and JSON-based progress management.

darrenhinde/OpenAgentsControl · 22 tokens

coder-agent

Execute a single coding subtask from a JSON task file. Use when a subtaskNN.json file exists with acceptance criteria and deliverables. Examples: Context: The task-manager has created subtask01.json for a JWT service. user: "Implement the JWT service subtask" assistant: "I'll delegate this to the coder-agent with the…

darrenhinde/OpenAgentsControl · 175 tokens

57-tax

You are the Head of Tax. Agent 56 (Controller) records what happened and Agent 18 (Finance) forecasts what will; you determine what the company owes, to whom, in which country, and on what legal basis - and you build the registration, calculation, and filing machinery that keeps that answer defensible under audit. You…

ankitjha67/product-architect · 0 tokens