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.
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.
npx skills add mikeyobrien/ralph-orchestrator --skill ralph-hatsgit 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/skills/mikeyobrien/ralph-orchestrator/ralph-hats)<a href="https://agentmods.dev/skills/mikeyobrien/ralph-orchestrator/ralph-hats"><img src="https://agentmods.dev/badge/skills/mikeyobrien/ralph-orchestrator/ralph-hats/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/skills/mikeyobrien/ralph-orchestrator/ralph-hats"><img src="https://agentmods.dev/badge/skills/mikeyobrien/ralph-orchestrator/ralph-hats.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00059 | $0.00631 |
| Opus 5 | $0.00030 | $0.00316 |
| Sonnet 5 | $0.00012 | $0.00126 |
| Haiku 4.5 | $0.00006 | $0.00063 |
Grade A, and why
ralph-hats 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 13d 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 — 66 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Ralph Hats
Use this skill to operate the full Ralph hat lifecycle for user-authored hat collections.
Use This Skill For
- Creating a new hat collection in
.ralph/hats/ - Inspecting an existing hat collection and explaining its topology
- Validating trigger routing, event flow, and completion behavior
- Improving or refactoring hats for clearer roles and safer routing
- Recommending better orchestration patterns for a Ralph workflow
Core Assumptions
- Core runtime config already lives in
ralph.ymlor another-csource. - User-authored hats are stored separately and passed with
-H. - This skill operates public hat collections, not Ralph built-in presets.
Workflow
- If a hats file already exists, read it first and explain the current topology before proposing changes.
- If creating a new workflow, write it to
.ralph/hats/<name>.yml. - Keep the hats file focused on hats-only data. Leave runtime limits and other core config in the main config file.
- Validate with
ralph hats validate. - Visualize topology with
ralph hats graphwhen the event flow is not trivial. - Use
ralph hats show <hat>when you need to inspect one hat's effective configuration. - When the user wants stronger confidence, run a targeted
ralph run -c ... -H ... -p "..."exercise or provide the exact test command.
Guardrails
- Only use hats-file top-level keys that Ralph accepts today:
name,description,events,event_loop,hats. - In a hats file,
event_loopis only for hats overlay keys such asstarting_eventandcompletion_promise. - Never use
task.startortask.resumeas hat triggers. Ralph reserves those for coordination. Use semantic delegated events likework.start,review.start, orresearch.start. - Each trigger must route to exactly one hat.
- Keep
descriptionpopulated on every hat. - Prefer
events:metadata when custom event names would otherwise be opaque. - Do not write user workflows into
presets/from this skill.
What ships with it
4 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 13d ago First seen · 66 lines · 59 tokens per session scan A ee0e58d59ab0
ralph-hats is a skill published in the GitHub repository mikeyobrien/ralph-orchestrator (3,133 stars, last pushed 2d ago), licensed MIT. It adds 59 tokens to every session and 631 once invoked, about $0.0003 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.
Other skills, from other repositories
chart
Use when the user asks to visualize data with charts, graphs, or plots using the chart tool (bar, line, scatter, pie, time series, etc.).
writing-tests
Write unit tests, component tests, and integration tests for AiderDesk using Vitest and React Testing Library. Use when creating new tests, adding test coverage, configuring mocks, setting up test files, or debugging failing tests.
playwright-testing
Playwright E2E testing patterns, cross-browser configuration, page objects, and CI setup. Use when creating E2E specs, visual regression suites, or configuring Playwright in CI. Trigger terms: playwright, e2e, trace, page object, cross-browser.
agent-memory
Creates, queries agent expertise profiles in AGENT-EXPERTISE.md; increments file-familiarity counters after each task; ranks candidate agents by recency, task-area match. Use when deciding which agent should handle a file, checking who last worked on a module, recording task outcomes, or assigning work based on past…
data-engineering
Transforms, validates, loads data in ETL pipelines. Use when building scrapers, validating NDJSON feeds, or importing data into CMS/DB targets.
ralph-linear
Fetch Linear tickets and build them with ralph-starter.