agentleFS
Sign inStart free
DusttooDusttoo/orka/skills/orchestration-init/SKILL.md

orchestration-init

Skill2 starsChanged 46 days agoMITView on GitHub

Bootstrap the orchestration harness in a target repo by creating configuration, checking project acceptance criteria, and wiring plugin-owned guardrails. Use when the user asks to initialize, install, bootstrap, or set up orchestration in a repository, including the equivalent of the Claude /orchestration-init command.

  • Reads credentials

1 other project uses a version of this.

Adopted by

Most recently taken up by

  • Other versions1 project uses a version of this.

    Word for word · 0

    None found.

    Edited · 0

    None found.

    Wrote their own version · 1

    1. amkfbant/claude-codex-orchestration★ 1same 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 repository7 other files it gives its agents.

The file

We split this skill into the rules it gives an agent

2 rules. About 0 are common, 0 are distinctive, and 2 are 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.

  • 2

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Very specific:

    If any role uses API execution, instruct the user to put the relevant ANTHROPIC_API_KEY and/or OPENAI_API_KEY in .orchestration/.env beside …

    line 43
  2. Very specific:

    Do not copy hook commands into project settings.

    line 57

≈ “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.

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

Initialize orchestration in a target repo

Set up the orchestration harness in the current repository. Be conservative: detect the repo's mechanics, show the inferred config, and get confirmation before writing repo files when running interactively.

Plugin paths

The templates and scripts below live in this plugin, not necessarily in the target repository. Resolve these paths from this skill file before reading or executing them:

  • ../../templates/config.yaml
  • ../../hooks/hooks.json
  • ../../scripts/orchestration-engine.py
  • ../../scripts/preflight.sh
  • ../../scripts/merge-guard.sh
  • ../../scripts/sweep-agent-worktrees.sh
  • ../../scripts/run-plugin-conformance.sh

Execute scripts by absolute path while keeping the target repository as the working directory.

Procedure

  1. Detect the target repo's stack:
    • branches from git branch -r, inferring configured branch roles
    • CI check names from .github/workflows/*.yml
    • self-check commands from package.json or the repo's language equivalent
    • ticket system from branch names, recent commits, or repo docs, defaulting to none when unclear
  2. Scaffold .orchestration/config.yaml from templates/config.yaml, filled with the detected values. Show the filled config and let the user correct branch names, checks, ticket settings, and worktree_cleanup policy before writing. Keep its safe manual default unless the user explicitly opts into automatic removal of clean, unlocked worktrees. After writing, run orchestration-engine.py validate-config. If any role uses API execution, instruct the user to put the relevant ANTHROPIC_API_KEY and/or OPENAI_API_KEY in .orchestration/.env beside the config. Container environment values take precedence. Never display or copy secret values. If ticket.kind: jira, the same file (in the shared repository root) may hold JIRA_API_TOKEN and, for Jira Cloud, JIRA_EMAIL; tell the user to chmod 600 .orchestration/.env, because sprint preflight and sync refuse a group- or world-readable credential file.
  3. Confirm a repo rules document exists. Prefer both CLAUDE.md and AGENTS.md in rules_docs; if missing, offer to create a starter so the project's real conventions have a place to live.
  4. Gitignore .orchestration/.gate-status/, .orchestration/.gate-logs/, .orchestration/.sprint-state/, .orchestration/.supervisor/, .orchestration/.review-ledger/, .orchestration/.review-results/, .orchestration/.env, .orchestration/.llm-runs/, .orchestration/.llm-usage/, and the configured worktree base.
  5. Do not copy hook commands into project settings. Claude Code and current Codex hosts may discover hooks/hooks.json after user review/trust, but support varies by host/version. Show the host's hook-review path when available. Never require registration: merge-on-green.sh validates all-green evidence directly and the skill performs configured cleanup.
  6. Optionally propose branch protection via gh api: strict required status checks, no direct pushes, and admin enforcement on production. Show the payload before applying it.
  7. Validate config and smoke-test the hooks in the target repo. Then run run-plugin-conformance.sh, which exercises the reusable merge-guard and worktree-cleanup suites from the plugin itself. Do not copy plugin tests, scripts, or process docs into the target repository. The target owns only its configuration, rules/acceptance criteria, and project-specific tests.

Report the files created or changed and any manual review left, especially config values and rules-doc content.

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