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 Worker

by Th0rgal in Th0rgal/sandboxed.sh

Sets the rules for a worker agent spawned by a boss mission: stay in scope, verify before finishing, report blockers quickly and end with a clear status.

No licenceAuto-check passedAgent Workflows

Install Orchestrator Worker

skills CLI
$ npx skills add Th0rgal/sandboxed.sh --skill orchestrator-worker -a claude-code

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

GitHub CLI
$ gh skill install Th0rgal/sandboxed.sh orchestrator-worker --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/Th0rgal/sandboxed.sh.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/orchestrator-worker .claude/skills/orchestrator-worker && 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-worker
GitHub stars
516
Token cost
~531 tokens
SKILL.md length
292 words
Files
1
Skills in repo
9
Repo updated
First seen
Licence
None found

At a glance

Sets the rules for a worker agent spawned by a boss mission: stay in scope, verify before finishing, report blockers quickly and end with a clear status.

  • Works in 8 steps: Stay inside the assigned scope. Do not… → Work only in the provided working… → Do not modify files outside your scope… → …
  • Running as a worker agent on a task delegated by an orchestrating boss
  • SKILL.md covers Rules, Communication and Completion
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

This skill is addressed to the worker agent rather than to you. The worker runs in the same workspace as the boss, with the same container, filesystem and installed tooling, so paths and toolchains carry over. It must stay inside the assigned scope and working directory or branch, leave other files alone unless the boss widens the scope, and run the verification command from its prompt before finishing. When the task carries acceptance criteria in the task-board contract, those define success, and the simplest in-scope approach that meets them is preferred.

Reporting is strict. DONE is allowed only when the files on disk match the claim, and a wrong prompt, an impossible task or insufficient scope is reported at once instead of exploring elsewhere. Finished work is committed on the worker's branch with the verification result and changed file paths, and ends with DONE, BLOCKED or NOT_FEASIBLE. Read-only PR missions forbid edits, commits, pushes, comments and merges, and PR certifiers end with a VERDICT line: CLEAN, BLOCKED or INFRA_BLOCKED. Follow-up messages from the boss count as updated instructions.

When your agent uses it

  • Running as a worker agent on a task delegated by an orchestrating boss
  • Delivering a scoped change with a commit, changed paths and a verification result
  • Reviewing a pull request in read-only mode and returning a certifier verdict

Example prompts

  • “You are the worker for this mission: fix the failing parser test inside ./packages/parser only.”
  • “Verify with the test command from the brief, commit on your branch and report DONE, BLOCKED or NOT_FEASIBLE.”
  • “Certify this pull request in read-only mode and finish with a verdict.”

Requirements

  • A boss mission that spawns the worker in a shared workspace

Workflow steps

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

  1. Stay inside the assigned scope. Do not widen the task on your own.
  2. Work only in the provided working directory or branch.
  3. Do not modify files outside your scope unless the boss explicitly expands it.
  4. Verify with the command from the prompt before finishing. When the task
  5. Do not report DONE unless the files on disk actually match your claimed result.
  6. If the prompt is wrong, the task is impossible, or scope is insufficient, report that immediately instead of exploring unrelated work.
  7. Be concise. Prefer changes, verification, and a short status over long explanation.
  8. If the mission carries pr-readonly or the prompt says writer: false,

What it can do on your machine

Read from SKILL.md and the folder at commit 960b656. 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 Worker loads about 531 tokens when it runs. Until then it costs about 29 tokens; SKILL.md has 292 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~29
When it runs · the whole SKILL.md, loaded when a task matches
~531

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

Without a licence we can't republish the file, so here is its outline and opening line. It has 292 words (~531 tokens).

“You are a worker spawned by a boss mission. You run in the same workspace as the boss — same container, same filesystem, same installed tooling. Paths in your prompt resolve identically inside your environment; you do not need to…”

— opening of SKILL.md by Th0rgal
name
orchestrator-worker

Read the full SKILL.md on GitHub

Files

Just SKILL.md in skills/orchestrator-worker of Th0rgal/sandboxed.sh.

Open the folder on GitHubat commit 960b656

Compare with similar skills

Orchestrator Worker 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 Worker compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Orchestrator Worker this skillTh0rgal/sandboxed.sh516—~531Automated safety check: PassNone
OMA Multi-Agent Orchestrationfirst-fluke/oh-my-agent1.3k—~4.1kAutomated safety check: PassMIT
Phased Plan Executorthedotmack/claude-mem99k—~508Automated safety check: PassApache-2.0
Plan Execution WorkflowEveryInc/compound-engineering-plugin25k—~2kAutomated safety check: PassMIT
Sol and Luna Worker Routermajiayu000/spellbook287—~3.3kAutomated safety check: PassMIT
PUA Shot Agent Personatanweai/pua20k—~3.5kAutomated safety check: PassMIT

Similar skills

  • OMA Multi-Agent Orchestration

    first-fluke/oh-my-agent

    Decomposes a complex feature into tasks, dispatches parallel specialist agents with durable state, and supervises verification, QA review and retries.

    1.3k GitHub stars~4.1k tokensUpdated today
    Agent WorkflowsAuto-check passed

  • Phased Plan Executor

    thedotmack/claude-mem

    Executes a phased implementation plan by acting as an orchestrator that hands each step to subagents, verifies the results and commits only after verification passes.

    99k GitHub stars~508 tokensUpdated yesterday
    Agent WorkflowsAuto-check passed

  • Plan Execution Workflow

    EveryInc/compound-engineering-plugin

    Carries out a plan, spec or clear build request end to end with local verification, then hands off to shipping or returns a structured result to a caller.

    25k GitHub stars~2k tokensUpdated 2 days ago
    Agent WorkflowsAuto-check passed

  • Sol and Luna Worker Router

    majiayu000/spellbook

    Splits substantial coding or repository-review work between a Sol commander that decides and verifies and a separate Luna Max worker that implements, with an auditable run log.

    287 GitHub stars~3.3k tokensUpdated yesterday
    Agent WorkflowsAuto-check passed

  • PUA Shot Agent Persona

    tanweai/pua

    Compact version of the PUA persona skill that pushes an agent to act like a high-ownership engineer, with level roles, extra-work markers and corporate-style commentary.

    20k GitHub stars~3.5k tokensUpdated 1 mo ago
    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

More from Th0rgal/sandboxed.sh

All 9 skills in this repo

  • Sandboxed.sh Library Management

    Th0rgal/sandboxed.sh

    Reads and updates the Sandboxed.sh Library, a git-backed store of skills, agents, commands, tools, rules and MCP servers, through its library tools.

    516 GitHub stars~931 tokensUpdated today
    Auto-check passed

  • Hermes Mission Control

    Th0rgal/sandboxed.sh

    Teaches Hermes to monitor and steer long-running sandboxed.sh missions: spot where a model is stuck, switch backends or models between turns, and send targeted hints.

    516 GitHub stars~8.6k tokensUpdated today
    Auto-check passed

  • Sandboxed.sh Missions

    Th0rgal/sandboxed.sh

    Delegates multi-step coding or research tasks to isolated sandboxed.sh container missions through its MCP tools, each with a chosen workspace, agent profile and prompt.

    516 GitHub stars~23k tokensUpdated today
    Auto-check: notes

  • Orchestrator Executor

    Th0rgal/sandboxed.sh

    Has the agent do the implementation itself and consult one persistent, stronger advisor through ask_worker only when it reaches a dead end.

    516 GitHub stars~620 tokensUpdated today
    Auto-check passed

  • Orchestrator Advisor

    Th0rgal/sandboxed.sh

    Acts as a persistent read-only advisor that maps the repository once, then answers a cheaper executor agent's questions concisely across a long session.

    516 GitHub stars~568 tokensUpdated today
    Auto-check passed

  • Orchestrator Boss

    Th0rgal/sandboxed.sh

    Boss skill for parallel worker orchestration. An agent skill from Th0rgal/sandboxed.sh.

    516 GitHub stars~1.7k tokensUpdated today
    Auto-check passed

Categories

Questions about Orchestrator Worker

What does Orchestrator Worker do?

Sets the rules for a worker agent spawned by a boss mission: stay in scope, verify before finishing, report blockers quickly and end with a clear status. This skill is addressed to the worker agent rather than to you. The worker runs in the same workspace as the boss, with the same container, filesystem and installed tooling, so paths and toolchains carry over.

When should I use Orchestrator Worker?

Orchestrator Worker fits situations like: running as a worker agent on a task delegated by an orchestrating boss; delivering a scoped change with a commit, changed paths and a verification result; reviewing a pull request in read-only mode and returning a certifier verdict.

How do I install Orchestrator Worker in Claude Code?

Run `npx skills add Th0rgal/sandboxed.sh --skill orchestrator-worker -a claude-code`. Or copy the skill folder (skills/orchestrator-worker in Th0rgal/sandboxed.sh) into .claude/skills/orchestrator-worker in your project. Claude Code loads it when a task matches its description.

How do I install Orchestrator Worker in Codex?

Run `npx skills add Th0rgal/sandboxed.sh --skill orchestrator-worker -a codex`. Or copy the skill folder (skills/orchestrator-worker in Th0rgal/sandboxed.sh) into .agents/skills/orchestrator-worker in your project. Codex loads it when a task matches its description.

Can I use Orchestrator Worker 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 Th0rgal/sandboxed.sh --skill orchestrator-worker -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-worker, .gemini/skills/orchestrator-worker, .github/skills/orchestrator-worker and .opencode/skills/orchestrator-worker in your project.

What does Orchestrator Worker need to run?

SKILL.md names no scripts, command-line tools or credentials: Orchestrator Worker is instructions for the agent only. Our summary lists: A boss mission that spawns the worker in a shared workspace.

Does Orchestrator Worker 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 Worker 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 Worker use?

No licence was found for Orchestrator Worker or its repository. Without one, default copyright applies: ask the author before reusing or redistributing it.

How many tokens does Orchestrator Worker use?

About 531 tokens (SKILL.md is roughly 2.1k 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 Worker?

Skills that share tags, products or a category with Orchestrator Worker: OMA Multi-Agent Orchestration (first-fluke/oh-my-agent, 1.3k stars), Phased Plan Executor (thedotmack/claude-mem, 99k stars), Plan Execution Workflow (EveryInc/compound-engineering-plugin, 25k stars) and Sol and Luna Worker Router (majiayu000/spellbook, 287 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Orchestrator Worker?

Th0rgal (a GitHub user) maintains it in Th0rgal/sandboxed.sh, which has 516 GitHub stars. The repository holds 9 skills in this directory. The repository was last updated on October 9, 2026.

Source: Th0rgal/sandboxed.sh on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.