Ralph Orchestrator is a framework that repeatedly runs AI-agent tasks until they finish or reach an iteration limit. Developers use it to coordinate autonomous coding work through command-line, web-dashboard, and MCP-server interfaces, with state managed per workspace. The catalogue entries provide agent skills, agents, instructions, and plugins for operating Ralph.
Borrowing it
Nothing to install: this file belongs to mikeyobrien/ralph-orchestrator. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/mikeyobrien/ralph-orchestrator/main/.claude/agents/code-assist.mdgit clone --depth 1 https://github.com/mikeyobrien/ralph-orchestratorWrote 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.
[](https://agentmods.dev/agents/mikeyobrien/ralph-orchestrator/code-assist)<a href="https://agentmods.dev/agents/mikeyobrien/ralph-orchestrator/code-assist"><img src="https://agentmods.dev/badge/agents/mikeyobrien/ralph-orchestrator/code-assist/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<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="Reviewed on agentmods" width="80" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00280 | $0.01045 |
| Opus 5.5 | $0.00112 | $0.00418 |
| Sonnet 5.5 | $0.00056 | $0.00209 |
| Haiku 4.5 | $0.00028 | $0.00104 |
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 1mo 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.
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.mdis your handoff mechanism.
Your Workflow
Phase 1: Orientation
- Read the task file completely (if provided)
- Read any referenced specs in
.ralph/specs/ - Read
IMPLEMENTATION_PLAN.mdif it exists - Explore the relevant codebase areas to understand existing patterns
- Identify acceptance criteria and success metrics
Phase 2: Planning
- If no
IMPLEMENTATION_PLAN.mdexists, create one with:- Clear scope boundaries
- Ordered implementation steps
- Dependencies between steps
- Validation criteria for each step
- If a plan exists, assess current progress and pick up where it left off
- Keep plans simple—they're disposable coordination artifacts
Phase 3: Implementation
- Work one logical chunk at a time
- After each chunk:
- Run
cargo buildto verify compilation - Run
cargo testto verify correctness - Fix any issues before proceeding
- Run
- Commit logically grouped changes with clear messages
- Update
IMPLEMENTATION_PLAN.mdto reflect progress
Phase 4: Validation
- Run the full test suite:
cargo test - Run smoke tests:
cargo test -p ralph-core smoke_runner - Verify all acceptance criteria from the task file are met
- 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)
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.
- 1mo ago First seen · 88 lines · 280 tokens per session scan A 4983e345d66e
code-assist is an agent published in the GitHub repository mikeyobrien/ralph-orchestrator (3,186 stars, last pushed 9d ago), licensed MIT. It adds 280 tokens to every session and 1,045 once invoked, about $0.0011 per session on Opus 5.5. 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.
Other agents, from other repositories
task-manager
Break down complex features into atomic, verifiable subtasks with dependency tracking and JSON-based progress management.
external-scout
Fetches external library and framework documentation from Context7 API and other sources, caching results for offline use.
Reviewer
Mandatory fast reviewer: validates every agent delegation output before acceptance. Checks acceptance criteria, file partitions, regressions, type safety, security basics.
Content Engineer
Content engineer: CMS schema design, content queries, content modeling, releases, studio customization.
ralph-agent
Autonomous development agent for Ralph loops with Hat-lite builder/verifier workflow. Use when running Ralph autonomous loops, mentions "ralph loop", "autonomous development", "hat-lite", "builder verifier", or needs fresh context iteration workflow.
perspective-generator
Use when detailed perspective analysis is needed after NCI scoring, or when high disagreement between interpretations requires synthesis. Generates balanced dual perspectives - both manipulative and legitimate.