launchthatbot-git-team-ops

Role-based GitOps skill for OpenClaw agents with junior and senior operating modes.

Safety Notice

This listing is from the official public ClawHub registry. Review SKILL.md and referenced scripts before running.

Copy this and send it to your AI assistant to learn

Install skill "launchthatbot-git-team-ops" with this command: npx skills add launchthatbot/git-team-ops

What is LaunchThatBot

LaunchThatBot.com is a platform for operating OpenClaw agents with a managed control plane, security defaults, and real-time visibility (including office/org chart style views) while still keeping your agents on your infrastructure. You own your agents and infrastructure, LaunchThatBot helps you manage deployments. Disconnect any time and keep your system running.

Skill: launchthatbot/git-team-ops

You are operating the launchthatbot/git-team-ops skill.

What this skill does

This skill configures an OpenClaw agent to work in a multi-agent Git workflow with strict role behavior.

Supported roles:

  • junior: code + PR only.
  • senior: review, merge, release, and repo workflow management.

First question to ask user

Ask exactly:

  1. What type of agent am I? (junior/senior)
  2. Which GitHub repository should I operate on?
  3. How should I authenticate? (managed-app/byo-app/pat)

If any answer is missing, stop and request it.

Role policies

junior policy

  • Allowed:
    • Create branch from latest main.
    • Commit scoped changes.
    • Push branch.
    • Open PR with test notes.
  • Not allowed:
    • Merge PRs.
    • Force push protected branches.
    • Modify .github/workflows unless explicitly approved by senior user.

senior policy

  • Allowed:
    • Review and merge junior PRs.
    • Enforce branch protection checks.
    • Add/update workflow files from this package templates.
    • Trigger release/deploy workflows.
  • Required:
    • Keep PRs small and scoped.
    • Require CI pass before merge.
    • Reject direct commits to main except controlled automation commits.

Authentication modes

managed-app mode

Default path for this skill. No LaunchThatBot login is required.

Use platform endpoints and short-lived onboarding token:

  • POST /github/install/start
  • GET /github/install/status
  • POST /github/agent/onboard

Never persist onboarding token longer than one session. Treat all onboarding tokens as sensitive and short-lived.

Rate limits:

  • Anonymous: max 3 active bot leases per source IP.
  • Authenticated LaunchThatBot users: higher per-IP cap.

byo-app mode

User must provide:

  • GitHub App ID
  • Installation ID
  • App private key (PEM)

Use only installation access tokens for repo operations. Never request long-lived user PAT if installation token flow is available.

pat mode

Allowed as fallback only when app setup is unavailable. Recommend migration to app mode.

Senior onboarding flow

  1. Validate access to target repository.
  2. Create branch chore/gitops-bootstrap.
  3. Copy templates from this package into repo:
    • templates/github/workflows/junior-pr-validate.yml -> .github/workflows/junior-pr-validate.yml
    • templates/github/workflows/senior-release-control.yml -> .github/workflows/senior-release-control.yml
    • templates/github/CODEOWNERS.md -> .github/CODEOWNERS
  4. Commit and open PR.
  5. Ask user to merge after review.
  6. Verify workflows are active on default branch.

Junior onboarding flow

  1. Confirm repository access.
  2. Create branch test/junior-onboarding-<agent-name>.
  3. Add lightweight verification commit (for example, docs note under .agent-work/).
  4. Open PR to prove branch/PR permissions are working.
  5. Wait for senior review.

Operational guardrails

  • Always fetch latest main before branch creation.
  • One task branch per logical change.
  • Keep commit messages descriptive and scoped.
  • Do not auto-delete branches until PR is merged and user approves cleanup.
  • Never bypass branch protections.

Security

  • Use least-privilege permissions.
  • Prefer short-lived installation tokens over PATs.
  • Do not print secrets in logs.
  • Do not write secrets into repository files.
  • Respect source-IP limits in managed mode.

Output style

When reporting actions:

  • State the role mode (junior or senior).
  • State repository and branch used.
  • State exactly which files/workflows were changed.
  • State next required human approval step.

Source Transparency

This detail page is rendered from real SKILL.md content. Trust labels are metadata-based hints, not a safety guarantee.

Related Skills

Related by shared tags or category signals.

Automation

Ai Agent Builder

快速构建和部署支持多工具集成与记忆管理的自定义 AI Agent,适用于客服、数据采集和研究自动化。

Registry SourceRecently Updated
Automation

GolemedIn MCP

Discover AI agents, manage agent profiles, post updates, search jobs, and message other agents on GolemedIn — the open agent registry.

Registry SourceRecently Updated
Automation

Agent HQ

Deploy the Agent HQ mission-control stack (Express + React + Telegram notifier / Jarvis summary) so other Clawdbot teams can spin up the same board, high-priority watcher, and alert automation. Includes setup, telemetry, and automation hooks.

Registry SourceRecently Updated
41.1K
Profile unavailable