New: 98,000+ skills indexed from GitHub repos with 100+ stars · every skill safety-checkedBrowse top skillsTop skills
Esc to closeBrowse all skills
Submit a skillBrowse skills
Submit a skillBrowse skills

Agent skill

Orchestrator Contract

by griddynamics in griddynamics/rosetta

MUST activate when you ARE an orchestrator — you are the top-level agent, you spawn subagents, you delegate work, you coordinate parallel or sequential execution.

Apache-2.0Auto-check passedAgent Workflows

Install Orchestrator Contract

skills CLI
$ npx skills add griddynamics/rosetta --skill orchestrator-contract -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install griddynamics/rosetta orchestrator-contract --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/griddynamics/rosetta.git skills-src && mkdir -p .claude/skills && cp -r skills-src/instructions/r2/core/skills/orchestrator-contract .claude/skills/orchestrator-contract && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
orchestrator-contract
GitHub stars
354
Token cost
~1.2k tokens
SKILL.md length
582 words
Files
1
Skills in repo
12
Repo updated
First seen
Licence
Apache-2.0

At a glance

MUST activate when you ARE an orchestrator — you are the top-level agent, you spawn subagents, you delegate work, you coordinate parallel or sequential execution.

  • Works in 3 steps: MUST delegate to subagents when platform… → Orchestrator is the top-level agent; it… → Subagents always start with fresh…
  • Tasks that involve Subagents
  • SKILL.md covers Tasks (SMART), Scope boundaries, Constraints and Acceptance criteria, plus 6 more sections
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

Orchestrator Contract is an agent skill from griddynamics/rosetta. MUST activate when you ARE an orchestrator — you are the top-level agent, you spawn subagents, you delegate work, you coordinate parallel or sequential execution. Defines delegation quality, subagent dispatch, routing, review, and ownership protocol.

Its SKILL.md is about 1.2k tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.

It sits in Agent Workflows, covering Subagents. The repository describes itself as: An instruction layer for AI coding agent. The licence is Apache-2.0.

When your agent uses it

  • Tasks that involve Subagents

Example prompts

  • “/orchestrator-contract”

Workflow steps

3 steps, taken from the first numbered list in SKILL.md.

  1. MUST delegate to subagents when platform supports them. Orchestrator makes decisions and orchestrates.
  2. Orchestrator is the top-level agent; it spawns subagents; subagents may not be able to spawn their subagents. Orchestrator is senior team…
  3. Subagents always start with fresh context on every run. User can not see orchestrator and subagent communication.

What it can do on your machine

Read from SKILL.md and the folder at commit 5441232. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    No scripts in the folder and no shell commands in SKILL.md.

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Orchestrator Contract loads about 1.2k tokens when it runs. Until then it costs about 68 tokens; SKILL.md has 582 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~68
When it runs · the whole SKILL.md, loaded when a task matches
~1.2k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from griddynamics/rosetta at commit 5441232, republished under its Apache-2.0 licence (© griddynamics). 582 words, ~1,191 tokens.

Download SKILL.mdSave it as .claude/skills/orchestrator-contract/SKILL.md (or your agent's skills folder).
name
orchestrator-contract
description
MUST activate when you ARE an orchestrator — you are the top-level agent, you spawn subagents, you delegate work, you coordinate parallel or sequential execution. Defines delegation quality, subagent dispatch, routing, review, and ownership protocol.
license
Apache-2.0
disable-model-invocation
false
user-invocable
false
baseSchema
docs/schemas/skill.md

<orchestrator_contract>

<process>

Topology:

  1. MUST delegate to subagents when platform supports them. Orchestrator makes decisions and orchestrates.
  2. Orchestrator is the top-level agent; it spawns subagents; subagents may not be able to spawn their subagents. Orchestrator is senior team lead and effective manager; Orchestrator is expert in meta-process engineering and makes the process poka-yoke and reliable itself, trusts but verify, if anything could go wrong - it will go wrong, provides clear context and instructions, subagents can cheat, consults with architect, and uses subagents as its team. It adapts and tunes management best practices to the specific user request. It tells WHAT to do and HOW to think, does not do subagents' tasks itself, but organizes them and encourages thinking over mechanical work. It appends to instructions instead of paraphrasing, uses MoSCoW, and grounds subagents with references to files, instructions, phases, steps, and skills instead of duplicating.
  3. Subagents always start with fresh context on every run. User can not see orchestrator and subagent communication.

Dispatch:

  1. Subagent prompt MUST follow this template (include only what applies):

""" You are [role/specialization]. [Lightweight|Full] subagent.

Tasks (SMART)

  • [task 1]
  • [task 2]

Scope boundaries

Target root folder: [path] [git worktree?] DO: [what is in scope, explicit expected outputs and clear expectations] DO NOT: [what is explicitly out of scope, what is read-only, what not to touch — forbid out-of-scope work; do not improvise beyond defined scope]

Constraints

  • [constraint: e.g., case sensitivity, naming conventions, patterns to follow]

Acceptance criteria

  • [done when: specific measurable condition]

Failure conditions

  • MUST STOP and EXPLAIN when: cannot execute as requested, off-plan, or would exceed scope; [other condition]

Skills

MUST USE SKILL [required skill]. RECOMMEND USE SKILL [recommended skill].

Original user request

[original user request/intent verbatim — always provide throughout all steps]

Context

[specific task, full context, and references — subagents know nothing except shared bootstrap, prep steps, and this contract; provide everything needed]

Output

[output can be just response message or written to file (or both - based on the task and expected volume); unique output file path per subagent and format if output to file is needed; for large output define exact path and required file format/template; or expected report-back summary — include only what applies]

Show full SKILL.md (221 more words)Show less

Evidence

[require that all claims, findings, and recommendations include proofs, references, and deep links with line ranges; include brief source quotes; explicitly distinguish verified facts from assumptions]

[free form anything else that was not provided, additional information, requirements, specifications, context, etc.] """

  1. Quality-gate before dispatch: clarify unclear task/context/constraints first. Never dispatch ambiguous instructions.
  2. Lightweight = generic, built-in, small clear tasks (e.g., build/tests). Full = user-defined, specialized role, larger work.
  3. Keep standard agent tools and required skills available to subagents; initialize skills together with subagent usage.

Routing:

  1. Route independent work in parallel and dependent work sequentially.
  2. Use TEMP folder for coordination and large input.
  3. Define collision-safe strategy for parallel file writes.

Quality:

  1. Orchestrator owns delegation quality end-to-end.
  2. MUST spawn reviewer subagents with fresh eyes to verify delegated work; never integrate unverified output. Use different model if possible.
  3. Review = static inspection (recommendations). Validate = running on real/sample tasks (catches real issues, expensive).
  4. Adapt the plan when something comes up, with proper ordering/analysis/looping; defer extra work on user approval.
  5. Keep orchestrator and subagent contexts below overload thresholds; prefer minimal state transitions.
  6. Subagent returns, at minimum: concise results, summary, side effects, anomalies, discoveries, contract changes, deviations, inconsistencies, and insights.
  7. Subagents ask orchestrator, orchestrator asks user, orchestrator is explicit and provides full context to user.
</process>

</orchestrator_contract>

© griddynamics, Apache-2.0. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

Just SKILL.md in instructions/r2/core/skills/orchestrator-contract of griddynamics/rosetta.

Open the folder on GitHubat commit 5441232

Compare with similar skills

Orchestrator Contract next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Orchestrator Contract compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Orchestrator Contract this skillgriddynamics/rosetta354—~1.2kAutomated safety check: PassApache-2.0
Claude Code Agent Developmentanthropics/claude-plugins-official38k8 repos~2.8kAutomated safety check: PassApache-2.0
Subagent Driven DevelopmentAsvarox/allkaraoke26138 repos~1.2kAutomated safety check: PassNone
Dispatching Parallel Agentsultralisp/ultralisp25841 repos~1.5kAutomated safety check: PassNone
Paseo Advisor Second Opiniongetpaseo/paseo20k1 repos~756Automated safety check: PassCustom licence
Task Observerrebelytics/one-skill-to-rule-them-all3.2k1 repos~12kAutomated safety check: PassCC-BY-4.0

Similar skills

  • Claude Code Agent Development

    anthropics/claude-plugins-official

    Official

    Explains how to write agents for Claude Code plugins: the markdown file with YAML frontmatter, trigger descriptions, model and color settings, and system prompt design.

    38k GitHub starsUsed in 8 repos~2.8k tokens
    Agent WorkflowsAuto-check passed

  • Subagent Driven Development

    Asvarox/allkaraoke

    A skill your agent uses when executing implementation plans with independent tasks in the current session

    261 GitHub starsUsed in 38 repos~1.2k tokens
    Agent WorkflowsAuto-check passed

  • Dispatching Parallel Agents

    ultralisp/ultralisp

    A skill your agent uses when facing 2+ independent tasks that can be worked on without shared state or sequential dependencies

    258 GitHub starsUsed in 41 repos~1.5k tokens
    Agent WorkflowsAuto-check passed

  • Paseo Advisor Second Opinion

    getpaseo/paseo

    Launches one separate agent through Paseo to give a second opinion on the current task, with a self-contained briefing and no permission to edit files.

    20k GitHub starsUsed in 1 repo~756 tokens
    Agent WorkflowsAuto-check passed

  • Task Observer

    rebelytics/one-skill-to-rule-them-all

    Monitors task execution for skill improvement opportunities.

    3.2k GitHub starsUsed in 1 repo~12k tokens
    Agent WorkflowsAuto-check passed

  • O2 Review Loop

    openobserve/openobserve

    Splits a change into planner, coder and independent reviewer roles: you confirm a spec, a subagent implements it, and a separate reviewer checks each round's local WIP commit.

    22k GitHub stars~3.7k tokensUpdated today
    Agent WorkflowsAuto-check passed

More from griddynamics/rosetta

All 12 skills in this repo

  • Collect GitHub Stats

    griddynamics/rosetta

    Collect GitHub repo health/usage stats into merged JSON. An agent skill from griddynamics/rosetta.

    354 GitHub stars~415 tokensUpdated 9 days ago
    Auto-check passed

  • External Lib Flow

    griddynamics/rosetta

    Workflow for onboarding an external private library so AI can use it without source access.

    354 GitHub stars~1.5k tokensUpdated 9 days ago
    Auto-check passed

  • Specflow Use

    griddynamics/rosetta

    To connect Rosetta with Grid Dynamics SpecFlow MCP; only when SpecFlow is mentioned and the MCP is installed.

    354 GitHub stars~780 tokensUpdated 9 days ago
    Auto-check passed

  • Harness

    griddynamics/rosetta

    To build an AI harness: run, observe, validate, automate repeated work faster — CLI/MCP actions, devcontainers, skills, subagents, hooks, pipelines, automations.

    354 GitHub stars~1.5k tokensUpdated 9 days ago
    Auto-check passed

  • Coding Agents Farm

    griddynamics/rosetta

    To orchestrate parallel coding-agent farms (Claude, Codex, Copilot, Gemini, etc.) on isolated git worktrees.

    354 GitHub stars~2.4k tokensUpdated 9 days ago
    Auto-check passed

  • Coding Agents Hooks Authoring

    griddynamics/rosetta

    To author, register, and test Rosetta hooks, add a SemanticKind, or debug a hook that won't fire.

    354 GitHub stars~1.4k tokensUpdated 9 days ago
    Auto-check passed

Categories

Questions about Orchestrator Contract

What does Orchestrator Contract do?

MUST activate when you ARE an orchestrator — you are the top-level agent, you spawn subagents, you delegate work, you coordinate parallel or sequential execution. Orchestrator Contract is an agent skill from griddynamics/rosetta. MUST activate when you ARE an orchestrator — you are the top-level agent, you spawn subagents, you delegate work, you coordinate parallel or sequential execution.

When should I use Orchestrator Contract?

Orchestrator Contract fits situations like: tasks that involve Subagents.

How do I install Orchestrator Contract in Claude Code?

Run `npx skills add griddynamics/rosetta --skill orchestrator-contract -a claude-code`. Or copy the skill folder (instructions/r2/core/skills/orchestrator-contract in griddynamics/rosetta) into .claude/skills/orchestrator-contract in your project. Claude Code loads it when a task matches its description.

How do I install Orchestrator Contract in Codex?

Run `npx skills add griddynamics/rosetta --skill orchestrator-contract -a codex`. Or copy the skill folder (instructions/r2/core/skills/orchestrator-contract in griddynamics/rosetta) into .agents/skills/orchestrator-contract in your project. Codex loads it when a task matches its description.

Can I use Orchestrator Contract in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add griddynamics/rosetta --skill orchestrator-contract -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/orchestrator-contract, .gemini/skills/orchestrator-contract, .github/skills/orchestrator-contract and .opencode/skills/orchestrator-contract in your project.

What does Orchestrator Contract need to run?

SKILL.md names no scripts, command-line tools or credentials: Orchestrator Contract is instructions for the agent only.

Does Orchestrator Contract access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is Orchestrator Contract safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does Orchestrator Contract use?

Orchestrator Contract is published under the Apache-2.0 licence (declared in SKILL.md). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Orchestrator Contract use?

About 1.2k tokens (SKILL.md is roughly 4.8k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Orchestrator Contract?

Skills that share tags, products or a category with Orchestrator Contract: Claude Code Agent Development (anthropics/claude-plugins-official, 38k stars), Subagent Driven Development (Asvarox/allkaraoke, 261 stars), Dispatching Parallel Agents (ultralisp/ultralisp, 258 stars) and Paseo Advisor Second Opinion (getpaseo/paseo, 20k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Orchestrator Contract?

griddynamics (a GitHub organization) maintains it in griddynamics/rosetta, which has 354 GitHub stars. The repository holds 12 skills in this directory. The repository was last updated on September 29, 2026.

Source: griddynamics/rosetta on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.