weellioweellio/gander/skills/agent-ops/SKILL.md

agent-ops

Skill10 starsChanged 5 months agoMITView on GitHub

Control the Gander dashboard — open/show it, restart the bridge, reset the agent tiles, or check status. Use when the user asks to open/show the agent dashboard, start or stop the visualizer, or clear the agents.

Sends data out

4 other projects use a version of this.

Adopted by

Most recently taken up by

Ormus-Solutions/ormus-agent-opstheir own version, first seen Nov 8, 2026
LuisSambrano/antigravity-configtheir own version, first seen Nov 8, 2026
Vann-Dev/AgentBridgetheir own version, first seen May 15, 2026
HermeticOrmus/ormus-agent-opstheir own version, first seen Apr 25, 2026

Other versions4 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 4
LuisSambrano/antigravity-config★ 8same name
Vann-Dev/AgentBridge★ 2same name
HermeticOrmus/ormus-agent-ops★ 0same name
Ormus-Solutions/ormus-agent-ops★ 0same name
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.
In this repository4 other files it gives its agents.
- CLAUDE.mdCLAUDE.md
- autopilotSkill
- component-builderSkill
- context-auditSkill

The file

We split this skill into the rules it gives an agent

4 rules. 0 are common, 2 are distinctive, and 2 are very specific to this project.

0
Common
Most of the 4 edited versions we read keep these.
2
Distinctive
This author's own choices. Worth a look.
2
Very specific
Tied to their project's names, files or tools. Probably skip.

Common
Distinctive
Very specific

Distinctive:
Run the launcher. It starts the bridge if it isn't already running and opens the dashboard once:
line 13
Very specific:
If the browser tab doesn't open, navigate to http://localhost:3131/ manually.
line 19
Distinctive:
Stop the Node process serving port 3131:
line 34
Very specific:
Default port is 3131; override with the AOC_PORT environment variable (and update the hook URLs in hooks/hooks.json to match).
line 47

“Common” is measured: kept by at least 6 in 10 of the 4 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.

Keep what fits and drop the rest. Your version, ready for your agents.

Files

SKILL.md

Gander — control

Gander is a live dashboard that visualizes this session's Claude Code agents and sub-agents as animated avatar tiles. A small local bridge server holds the agent registry and serves the dashboard at http://localhost:3131/. Claude Code hooks push real tool activity to it automatically, so normally it "just works" once the plugin is installed — this skill is for manual control.

The bridge + dashboard live under the plugin root (${CLAUDE_PLUGIN_ROOT} in hook/MCP contexts). When running commands from this skill, use the plugin's bridge/ and dashboard/ folders.

Open / start the dashboard

Run the launcher. It starts the bridge if it isn't already running and opens the dashboard once:

node "<plugin-root>/bridge/launch.js"

If the browser tab doesn't open, navigate to http://localhost:3131/ manually.

Check status

A quick request to the state endpoint tells you if the bridge is up and how many agents are tracked:

PowerShell: Invoke-RestMethod http://localhost:3131/api/state
curl: curl -s http://localhost:3131/api/state

Reset the tiles

Clears all agents back to just the root Orchestrator:

PowerShell: Invoke-RestMethod -Method Post http://localhost:3131/api/reset
curl: curl -s -X POST http://localhost:3131/api/reset

Stop the bridge

Stop the Node process serving port 3131:

PowerShell: Get-NetTCPConnection -LocalPort 3131 | Select-Object -Expand OwningProcess | ForEach-Object { Stop-Process -Id $_ -Force }
macOS/Linux: lsof -ti:3131 | xargs kill

Drive it from a one-off Claude run (no hooks)

You can also pipe a headless run straight into the bridge:

claude -p "task" --output-format stream-json --verbose | node "<plugin-root>/bridge/server.js" --stdin

Notes

Default port is 3131; override with the AOC_PORT environment variable (and update the hook URLs in hooks/hooks.json to match).
Avatar style (pixel art / abstract / GIF) and grid layout (Solo / Squad / War Room / Broadcast / Mosaic) are selectable from the dashboard top bar.
To use your own GIF avatars, drop files in dashboard/assets/avatars/ and list them in dashboard/assets/avatars/manifest.json.

Download now (ZIP)

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

What did you use it for? e.g. Reviewing pull requests in a Rails app

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.

Check your setup, free