How do I install the Relay skill?

Run npx skillmds@latest add oleg-koval/relay-2 in your terminal (requires Node.js), paste this page's agent-chat prompt into Claude, Cursor, or any MCP-connected agent, or download the SKILL.md file and copy it into your agent's skills directory.

Is Relay safe to use?

This skill has not completed SkillMD's automated safety review yet. SkillMD never runs a skill's scripts for you; review the SKILL.md before installing.

Which AI agents work with Relay?

This skill is tagged as working with Claude Code, Claude.ai, OpenAI Codex. SKILL.md is an open format, so most agents that read a skills directory can load it too.

Is Relay free to use?

Yes. Installing skills from SkillMD is free. This skill is licensed under MIT.

oleg-koval (@oleg-koval) published this skill. Their other Agent Skills are listed on their SkillMD profile.

Relay by oleg-koval — Agent Skill

Name: Relay
Author: oleg-koval

Relay

Use claude-relay to run a long or rate-limit-prone task autonomously across subscription accounts. Invoke this skill whenever the user says "use relay", "run this with relay", "do this overnight", "run this autonomously", "use relay for X", or has a multi-hour / multi-step task they want to hand off completely. Also use proactively when a task looks like it will take many turns and the user hasn't thought about rate limits yet. Guides goal writing, picks the right flags, and starts the run.

oleg-koval 34d1af1 3.4 KB Updated Sep 17, 2026

File contents

relay

Runs a task unattended using claude-relay: drives claude -p in a headless loop, writes a handoff summary when one account's limit approaches, and switches to the next account automatically. You watch logs; relay handles the rest.

Binary: claude-relay (alias relay if added to shell). Config: ~/.claude-relay/relay.config.json.

Step 1: Decide: relay or inline?

Use relay when:

Task will take many turns or hours (big refactor, migration, research + implementation)
The user wants to hand it off and walk away
Rate limits are a real concern (long-running or token-heavy)

Stay inline when:

Task is quick (< ~10 turns)
User wants to review each step
Task needs interactive input that relay can't provide

Step 2: Write the goal

A relay goal is a self-contained spec a fresh Claude agent can execute cold. Write it to /tmp/relay-goal-<short-name>.md. It must include:

What to do: concrete deliverables, not vague intent
How to verify: the exact command proving success (npm test, curl /api/health, etc.)
Scope: explicit list of what NOT to do (no commits, no PRs, no migrations, unless stated)
Key files: paths the agent should read first if the context isn't obvious

Template:

## Goal
<1-3 sentences: the deliverable>

## Success criteria
Run `<command>` and confirm it exits 0 / returns the expected result.

## Scope
- DO: <explicit list>
- DO NOT: open PRs / push commits / run migrations / touch unrelated files

## Key files
- <path>: <why it matters>

Good goals are specific. "Add input validation to all POST routes in app/api/" beats "improve the API".

Step 3: Pick flags

Situation	Flag
Task needs uncommitted changes, local `.env`, or a local database	`--in-place`
Everything is committed; task is self-contained	(default, isolated git worktree)

When in doubt: if the repo has a .env or node_modules the task depends on, use --in-place.

Step 4: Run

claude-relay run /tmp/relay-goal-<name>.md <absolute-path-to-repo> [--in-place]

Relay logs stream to stderr. The run ends when the agent outputs RELAY_TASK_COMPLETE on its own line, or hits a hard cap (400 turns / 48h wall clock).

Step 5: Tell the user

After starting, report:

The exact command you ran
What to watch for: RELAY_TASK_COMPLETE in logs, or claude-relay status --config ~/.claude-relay/relay.config.json
The flag you picked and why (especially if you chose --in-place)

Health check

If anything seems misconfigured:

claude-relay doctor --config ~/.claude-relay/relay.config.json

Should show ✓ for both account slots. If a slot shows ✗, tell the user to run:

claude-relay login <email>  # must have claude.ai open in browser as that account first

---name: relay-2description: Use claude-relay to run a long or rate-limit-prone task autonomously across subscription accounts. Invoke this skill whenever the user says "use relay", "run this with relay", "do this overnight", "run this autonomously", "use relay for X", or has a multi-hour / multi-step task they want to hand off completely. Also use proactively when a task looks like it will take many turns and the user hasn't thought about rate limits yet. Guides goal writing, picks the right flags, and starts the run.license: MIT---# relayRuns a task **unattended** using `claude-relay`: drives `claude -p` in a headless loop, writes ahandoff summary when one account's limit approaches, and switches to the next account automatically.You watch logs; relay handles the rest.Binary: `claude-relay` (alias `relay` if added to shell). Config: `~/.claude-relay/relay.config.json`.---## Step 1: Decide: relay or inline?**Use relay when:**- Task will take many turns or hours (big refactor, migration, research + implementation)- The user wants to hand it off and walk away- Rate limits are a real concern (long-running or token-heavy)**Stay inline when:**- Task is quick (< ~10 turns)- User wants to review each step- Task needs interactive input that relay can't provide---## Step 2: Write the goalA relay goal is a self-contained spec a fresh Claude agent can execute cold. Write it to`/tmp/relay-goal-<short-name>.md`. It must include:- **What to do**: concrete deliverables, not vague intent- **How to verify**: the exact command proving success (`npm test`, `curl /api/health`, etc.)- **Scope**: explicit list of what NOT to do (no commits, no PRs, no migrations, unless stated)- **Key files**: paths the agent should read first if the context isn't obvious**Template:**```markdown## Goal<1-3 sentences: the deliverable>## Success criteriaRun `<command>` and confirm it exits 0 / returns the expected result.## Scope- DO: <explicit list>- DO NOT: open PRs / push commits / run migrations / touch unrelated files## Key files- <path>: <why it matters>```Good goals are specific. "Add input validation to all POST routes in `app/api/`" beats "improve the API".---## Step 3: Pick flags| Situation | Flag ||-----------|------|| Task needs uncommitted changes, local `.env`, or a local database | `--in-place` || Everything is committed; task is self-contained | *(default, isolated git worktree)* |When in doubt: if the repo has a `.env` or `node_modules` the task depends on, use `--in-place`.---## Step 4: Run```bashclaude-relay run /tmp/relay-goal-<name>.md <absolute-path-to-repo> [--in-place]```Relay logs stream to stderr. The run ends when the agent outputs `RELAY_TASK_COMPLETE` on its ownline, or hits a hard cap (400 turns / 48h wall clock).---## Step 5: Tell the userAfter starting, report:- The exact command you ran- What to watch for: `RELAY_TASK_COMPLETE` in logs, or `claude-relay status --config ~/.claude-relay/relay.config.json`- The flag you picked and why (especially if you chose `--in-place`)---## Health checkIf anything seems misconfigured:```bashclaude-relay doctor --config ~/.claude-relay/relay.config.json```Should show ✓ for both account slots. If a slot shows ✗, tell the user to run:```bashclaude-relay login <email> # must have claude.ai open in browser as that account first```

Frequently asked questions