cockpit
Skill13 starsChanged 14 days agoMITView on GitHub
Open the Bridge cockpit, the local web page (127.0.0.1) that watches and steers the whole Bridge: briefing, work (inbox and tasks), agent tabs and sessions, workers, machines, tokens. Starts the server if needed. Not the per-project view (/dashboard). Trigger: "/cockpit", "cockpit", "open the cockpit", "web cockpit", "bridge dashboard in the browser", "Cockpit öffnen".
1 other project uses a version of this.
Adopted by
Most recently taken up by
- aalishan001/opencockpittheir own version, first seen Oct 25, 2026
Other versions1 project uses a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 1
- aalishan001/opencockpit★ 2same 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 repository44 other files it gives its agents.
- AGENTS.mdAGENTS.md
- skills/board-pilot/references/agents.mdAGENTS.md
- .github/copilot-instructions.mdCopilot instructions
- a2aSkill
- archiveSkill
- board-pilotSkill
- bridge-auditSkill
- bridge-contributeSkill
- bridge-curatorSkill
- bridge-explorerSkill
- bridge-greetingSkill
- bridge-leak-checkSkill
- bridge-learnSkill
- bridge-onboardSkill
- bridge-overlaySkill
- bridge-promoteSkill
- bridge-statusSkill
- bridge-syncSkill
- briefingSkill
- calendarSkill
- capability-brokerSkill
- channelSkill
- cmuxSkill
- dashboardSkill
- debriefSkill
- doc-systemSkill
- github-projects-managerSkill
- html-canvasSkill
- html-slidesSkill
- knowledge-repo-initSkill
- mail-draftSkill
- mandantsSkill
- meeting-transcriptionSkill
- object-storeSkill
- onboard-simSkill
- remoteSkill
- scheduleSkill
- secretsSkill
- spec-kickoffSkill
- task-close-postmortemSkill
- tmuxSkill
- tracker-syncSkill
- workloadSkill
- workspaceSkill
The file
We split this skill into the rules it gives an agent
1 rule. About 0 are common, 0 are distinctive, and 1 is very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈0
Distinctive · estimate
This author's own choices. Worth a look.
1
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Very specific: line 31
After opening, run python3 scripts/bridge-cockpit.py status --json once.
≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
Cockpit
Opens the cockpit (scripts/bridge-cockpit.py, guide docs/bridge-cockpit.md).
It is an early version (alpha) and still being extended; mention that when a user meets it for the first time.
Run
python3 scripts/bridge-cockpit.py open --jsonIt starts the server in the background (or reuses the running one) and opens the page itself: a
browser tab in the control workspace when the terminal driver can, else the default browser. The
answer is {"opened": ..., "port": ..., "reused": ...}: report in one line where it opened and
the address http://127.0.0.1:<port>/, nothing else. Never run url or start just to show a link:
their link carries a login code, and a login code does not belong in the conversation. Arguments after /cockpit pass through:
--via auto|cmux|system|none picks where it opens, status and stop run that command instead of
open. /cockpit url is never run here: tell the user to type python3 scripts/bridge-cockpit.py
url in their own terminal, which prints a login link to open by hand.
--json applies only to open, start and status; never append it to stop, which refuses it
with a usage text (exit 2).
After opening, run python3 scripts/bridge-cockpit.py status --json once. When can_launch is
false, no terminal driver starts agent tabs, so every "Let AI do it" in the cockpit would fail:
say so in one line and offer to set workplace.driver in bridge-config.yaml for the terminal this
machine has (cmux: skills/cmux/scripts/cmux_driver.py, tmux: skills/tmux/scripts/tmux_driver.py,
detected as in bridge-onboard D1d), written only on a yes, then stop and open again. null
means the driver did not answer: say nothing. When provider_gaps is not empty, a service that is on
stays off: for provider_unsupported say so in one line and offer to adapt the service and propose the
fork PR, for config_invalid name the file and its error (docs/ai-services.md, A service your provider cannot run).
On a first open, add one line: Settings, Setup (the first area of Settings, whose tab carries a count while something is wrong) lists what still keeps the cockpit from working well and what can be switched on, and the first visit's welcome offers it before the tour.
When it refuses
| Exit | Meaning | Say |
| 1 | not running (from status or stop), not an error | that the cockpit is not running and that /cockpit (or python3 scripts/bridge-cockpit.py start) starts it |
| 2 | with a usage text on stderr: a wrong call (an unknown subcommand or flag) | nothing to the user about the config: fix the arguments and run it again |
| 2 | without a usage text: cockpit.enabled is not true (or the config is invalid) | how to switch it on: cockpit: {enabled: true} in bridge-config.yaml |
| 3 | the port is taken | which port (cockpit.port) and that another program holds it |
| 4 | the server did not come up | the last lines of .bridge/cockpit/stdout.log, then server.log |
| 5 | the page could not be opened | that python3 scripts/bridge-cockpit.py url in a terminal prints a login link to open by hand (once, within a minute) |
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.