install-launchers
Skill4 starsChanged 4 months agoMITView on GitHub
Install or repair an explicit subset of the optional assistant, collab, coauthor, and tw launchers.
In this repository45 other files it gives its agents.
- AGENTS.mdAGENTS.md
- CLAUDE.mdCLAUDE.md
- bib-auditSkill
- bootstrap-dispatcher-runtimeSkill
- ci-debugSkill
- cloud-filesSkill
- connect-googleSkill
- daily-planSkill
- distill-to-ruttersSkill
- email-clientSkill
- email-triageSkill
- find-handoff-candidatesSkill
- formal-prose-reviewSkill
- get-weatherSkill
- git-workflowSkill
- hook-makerSkill
- initialize-tddSkill
- latex-workshopSkill
- list-managerSkill
- llm-wakeupSkill
- loose-modeSkill
- make-tex-docstringSkill
- math-dependency-graphSkill
- milestone-loggingSkill
- node-certifySkill
- node-driftSkill
- notation-reviewSkill
- online-calendarSkill
- pdf-to-markdownSkill
- prepare-handoffSkill
- proof-auditSkill
- recurring-tasksSkill
- refactor-nodeSkill
- regenerate-blueprintsSkill
- relocate-nodesSkill
- semantic-integrationSkill
- send-feedbackSkill
- setup-interface-managerSkill
- skill-makerSkill
- technical-flow-reviewSkill
- tight-modeSkill
- tool-applicabilitySkill
- update-standardsSkill
- using-compassSkill
- wrap-upSkill
The file
Files
<!-- BEGIN BLUEPRINT INTERFACES -->Generated from
blueprint.yaml. Do not edit this block by hand.
Executable Interfaces:
Send the required caller (caller skill), interface, version, and arguments; optional dry_run defaults to false. Compact uses ordered positionals plus an option mapping; ordered raw argv uses positionals: [] plus every argv token in list options. Never mix forms.
install-launchers._rtx.interface.agent-launchers— Install or repair only an explicit interactive launcher subset using caller-selected Python and plugin values.- Caller:
install-launchers - Version: 1
- Security level: 2
- Alternative:
setupArguments JSON (replace labels with actual values). Omit optional positionals and options that are not needed. {"options": {"--agents": "LIST", "--bin-dir": "DIR", "--canonical-python": "FILE", "--claude-home": "DIR", "--codex-home": "DIR", "--default-llm": "claude|codex", "--dry-run": true, "--home": "DIR", "--mode": "development|plugin", "--plugin-root": "DIR"}, "positionals": [], "stdin": null} Required options: ["--canonical-python", "--plugin-root"]; positional arity: 0..0; stdin: forbidden
- Caller:
<!-- END BLUEPRINT INTERFACES -->Skill: install-launchers
Require an explicit subset of assistant, collab, coauthor, and tw. If the
request names none, list those choices or ask; do not mutate anything and do not
default to installing all launchers.
Resolve the current selected plugin root from the host-loaded location of this
skill. Invoke install-launchers._rtx.interface.agent-launchers with only that
selected plugin root, the canonical executable, and the explicit launcher
subset. Do not fingerprint again, choose another Python, widen the selection,
or install a dependency owned by another feature.
Rerunning repairs only the selected launchers and refreshes their captured
plugin root. After a plugin-cache update, rerun install-launchers; there is no
generic updater.
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.

