Vigilante issue implementation on rush
Skill aliengiraffe/vigilante/skills/vigilante-issue-implementation-on-rush
Vigilante is a sandbox-first orchestration layer for coding agents. It isolates every task in a git worktree, enforces strict credential scoping, and gives you full audit logs — so your agents can't burn down production.
npx -y skills add aliengiraffe/vigilante --skill vigilante-issue-implementation-on-rushAssembled from the repository path, not quoted from the project. Check it against their README if it does not work.
What its author says it does
Copied from the file, not written here
Implement a GitHub issue end-to-end when Vigilante dispatches work for a Rush monorepo.
SKILL.md
1.4 KB, as published. Nobody here has run it
Vigilante Rush Issue Implementation
Focus
- Read the prompt for the detected stack, workspace hints, and shared local-service contract before changing code.
- Limit edits and validation to the affected Rush projects unless broader changes are required.
- If local services are required, call
vigilante-local-service-dependenciesfirst and then use the shareddocker-compose-launchcontract instead of writing ad hoc Compose logic.
Workflow
- Follow the base
vigilante-issue-implementation-on-monorepoworkflow for issue comments, validation, push, and PR creation, including stacked base-branch detection (Base branch:directive in the issue body). - Use
vigilante commitfor all commit-producing operations. Do not usegit commitor GitHub CLI commit flows directly. - Any commit or amend must preserve the user's existing git author, committer, and signing configuration. Commit on behalf of the user and do not overwrite
git configwith a coding-agent identity. - Do not add
Co-authored by:trailers or any other agent attribution for Codex, Claude, Gemini, or similar coding-agent identities. - Use Rush-native workspace commands when they exist and match the touched projects.
- Keep service startup scoped to the assigned worktree and only for implementation or test dependencies.