setup
Skill1 starsChanged 34 days agoMITView on GitHub
Configure the failover plugin - choose the fallback agent command and turn on Claude Code's built-in recovery settings. Runs only when the user invokes it.
- Installs packages
191 other projects use a version of this.
Adopted by
Most recently taken up by
- hydra-db/hydradb-claude-codetheir own version, first seen Nov 8, 2026
- WALKERKILLER/Look-Tongji-Notestheir own version, first seen Nov 8, 2026
- steerlabs/opensteertheir own version, first seen Nov 8, 2026
- ansvisor/ansvisortheir own version, first seen Nov 8, 2026
- dsifry/metaswarmtheir own version, first seen Nov 8, 2026
- anombyte93/prd-taskmastertheir own version, first seen Nov 8, 2026
Used with
Projects with it also use add-voice-transcription, add-discord and 10 more.
Other files people use alongside this one.
Files found in the same public projects as a version of this one, more often than they turn up anywhere else. Each project counts once, large collections count for less, and this file's own repository is left out.
juancruzmunozalbeloSkilladd-voice-transcription
Add voice message transcription to NanoClaw using OpenAI's Whisper API. Automatically transcribes WhatsApp voice notes so the agent can read and respond to them.
Also in 5 projects that use this
MicrosoftSkilladd-discord
Add Discord bot channel integration via Chat SDK.
Also in 11 projects that use this
MicrosoftSkilladd-slack
Add Slack channel integration via Chat SDK.
Also in 11 projects that use this
juancruzmunozalbeloSkilladd-telegram-swarm
Add Agent Swarm (Teams) support to Telegram. Each subagent gets its own bot identity in the group. Requires Telegram channel to be set up first (use /add-telegram). Triggers on "agent swarm", "agent teams telegram", "telegram swarm", "bot pool".
Also in 7 projects that use this
- +8 more from microsoft
Other versions191 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 191
- anthropics/knowledge-work-plugins★ 35ksame name
- garrytan/gbrain★ 32ksame name
- gavrielc/nanoclaw★ 31ksame name
- nanocoai/nanoclaw★ 31ksame name
- qwibitai/nanoclaw★ 31ksame name
- Q00/ouroboros★ 6.3ksame name
- pytorch/executorch★ 5.2ksame name
- agenticnotetaking/arscontexta★ 3.5ksame name
- aws/agent-toolkit-for-aws★ 3.4ksame name
- spotify/portal-ai-plugins★ 2.8ksame name
181 more not listed
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
The file
We split this skill into the rules it gives an agent
4 rules. 0 are common, 1 is distinctive, and 3 are very specific to this project.
0
Common
Most of the 171 edited versions we read keep these.
1
Distinctive
This author's own choices. Worth a look.
3
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Very specific: line 13
Run command -v jq. If jq is missing, tell the user how to install it (brew install jq, apt install jq) and stop: every script in this …
- Very specific: line 31
Ask whether the handoff should start automatically when a turn dies ("auto": true), or only when the user runs /failover:handoff.
- Very specific: line 33
Write ~/.claude/failover.json (use $CLAUDE_CONFIG_DIR instead of ~/.claude if it is set):
- Distinctive: line 53
Run a dry check and show the user the output:
“Common” is measured: kept by at least 6 in 10 of the 171 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
Set up failover
Walk the user through the steps below. Ask before writing each file, and merge into existing files instead of replacing them.
1. Check the requirement
Run command -v jq. If jq is missing, tell the user how to install it (brew install jq, apt install jq) and stop: every script in this plugin needs it.
2. Choose the fallback agent
Check which agent CLIs are installed (command -v codex gemini aider opencode claude) and ask the user which one should take over a stopped task. The command must run without prompting, read the task brief from stdin (or from the file named by $FAILOVER_BRIEF_FILE), and be allowed to edit files in the working directory. Starting points, which the user should confirm against --help for their installed version:
| Agent | Command |
| Codex CLI | codex exec --sandbox workspace-write - |
| Claude Code on another model | claude -p --model sonnet --permission-mode acceptEdits |
| Gemini CLI | gemini --yolo -p "$(cat)" |
| Aider | aider --yes-always --message-file "$FAILOVER_BRIEF_FILE" |
| opencode | opencode run "$(cat)" |
Any other command works too, including a wrapper script of the user's own.
3. Write the config
Ask whether the handoff should start automatically when a turn dies ("auto": true), or only when the user runs /failover:handoff. Make clear that automatic mode sends the recent conversation to the chosen agent without asking each time, on that agent's account and cost.
Write ~/.claude/failover.json (use $CLAUDE_CONFIG_DIR instead of ~/.claude if it is set):
{
"command": "<the chosen command>",
"auto": true,
"on": ["policy", "rate_limit", "overloaded", "server_error"]
}4. Offer the built-in recovery settings
These are Claude Code settings, not part of this plugin, and they recover without leaving the session. Offer to merge them into the user's ~/.claude/settings.json, explaining each one, and only add the ones the user agrees to:
"switchModelsOnFlag": true- when a safety classifier flags a request, re-run it on the fallback Claude model instead of pausing to ask."fallbackModel": ["sonnet"]- when the primary model is overloaded or unavailable, serve the turn from another model."autoContinueAtUsageLimit": true- when a usage limit stops the session, wait for the reset and continue.
5. Confirm
Run a dry check and show the user the output:
echo "Reply with the single word OK. Do not create or modify any files." | "${CLAUDE_PLUGIN_ROOT}/scripts/handoff.sh" --reason setup-checkTell the user that events are logged to ~/.claude/failover/events.jsonl.
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

