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.
Has the agent do the implementation itself and consult one persistent, stronger advisor through ask_worker only when it reaches a dead end.
Install Orchestrator Executor
$ npx skills add Th0rgal/sandboxed.sh --skill orchestrator-executor -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install Th0rgal/sandboxed.sh orchestrator-executor --agent claude-codeProject scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).
$ git clone --depth 1 https://github.com/Th0rgal/sandboxed.sh.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/orchestrator-executor .claude/skills/orchestrator-executor && rm -rf skills-srcUse ~/.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/
Install the "orchestrator-executor" agent skill from https://github.com/Th0rgal/sandboxed.sh/tree/master/skills/orchestrator-executor into .claude/skills/orchestrator-executor/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "orchestrator-executor", then confirm the skill loads.Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$skill-installer install https://github.com/Th0rgal/sandboxed.sh/tree/master/skills/orchestrator-executorType this inside Codex. $skill-installer <name> installs a curated skill from openai/skills. The installer writes to $CODEX_HOME/skills (default ~/.codex/skills). Restart Codex if the skill does not show up.
$ npx skills add Th0rgal/sandboxed.sh --skill orchestrator-executor -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install Th0rgal/sandboxed.sh orchestrator-executor --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/Th0rgal/sandboxed.sh.git skills-src && mkdir -p .agents/skills && cp -r skills-src/skills/orchestrator-executor .agents/skills/orchestrator-executor && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "orchestrator-executor" agent skill from https://github.com/Th0rgal/sandboxed.sh/tree/master/skills/orchestrator-executor into .agents/skills/orchestrator-executor/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "orchestrator-executor", then confirm the skill loads.Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add Th0rgal/sandboxed.sh --skill orchestrator-executor -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install Th0rgal/sandboxed.sh orchestrator-executor --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/Th0rgal/sandboxed.sh.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/skills/orchestrator-executor .cursor/skills/orchestrator-executor && rm -rf skills-srcUse ~/.cursor/skills/ instead of .cursor/skills for a personal install.
Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/
Install the "orchestrator-executor" agent skill from https://github.com/Th0rgal/sandboxed.sh/tree/master/skills/orchestrator-executor into .cursor/skills/orchestrator-executor/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "orchestrator-executor", then confirm the skill loads.Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gemini skills install https://github.com/Th0rgal/sandboxed.sh.git --path skills/orchestrator-executor--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.
$ npx skills add Th0rgal/sandboxed.sh --skill orchestrator-executor -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install Th0rgal/sandboxed.sh orchestrator-executor --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/Th0rgal/sandboxed.sh.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/skills/orchestrator-executor .gemini/skills/orchestrator-executor && rm -rf skills-srcUse ~/.gemini/skills/ instead of .gemini/skills for a personal install, then run /skills reload.
Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/
Install the "orchestrator-executor" agent skill from https://github.com/Th0rgal/sandboxed.sh/tree/master/skills/orchestrator-executor into .gemini/skills/orchestrator-executor/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "orchestrator-executor", then confirm the skill loads.Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gh skill install Th0rgal/sandboxed.sh orchestrator-executorInstalls for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).
$ npx skills add Th0rgal/sandboxed.sh --skill orchestrator-executor -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/Th0rgal/sandboxed.sh.git skills-src && mkdir -p .github/skills && cp -r skills-src/skills/orchestrator-executor .github/skills/orchestrator-executor && rm -rf skills-srcUse ~/.copilot/skills/ instead of .github/skills for a personal install. Commit .github/skills so cloud agent and code review can use it.
GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/
Install the "orchestrator-executor" agent skill from https://github.com/Th0rgal/sandboxed.sh/tree/master/skills/orchestrator-executor into .github/skills/orchestrator-executor/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "orchestrator-executor", then confirm the skill loads.GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add Th0rgal/sandboxed.sh --skill orchestrator-executor -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install Th0rgal/sandboxed.sh orchestrator-executor --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/Th0rgal/sandboxed.sh.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/skills/orchestrator-executor .opencode/skills/orchestrator-executor && rm -rf skills-srcUse ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.
OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/
Install the "orchestrator-executor" agent skill from https://github.com/Th0rgal/sandboxed.sh/tree/master/skills/orchestrator-executor into .opencode/skills/orchestrator-executor/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "orchestrator-executor", then confirm the skill loads.OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
Facts
- Skill name
orchestrator-executor- GitHub stars
- 515
- Token cost
- ~620 tokens
- SKILL.md length
- 286 words
- Files
- 1
- Skills in repo
- 9
- Repo updated
- First seen
- Licence
- None found
At a glance
Has the agent do the implementation itself and consult one persistent, stronger advisor through ask_worker only when it reaches a dead end.
- Running as an executor that escalates only after real dead ends
- SKILL.md covers The advisor, When to ask (and when not), How to ask and Otherwise
- Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md
- Keeping a single read-only advisor on hand for architectural questions
What it does
In this role the agent writes the code, runs the commands and verifies results itself instead of delegating the work. Its escape hatch is a single advisor, a stronger and more expensive model created lazily with `create_worker_mission` the first time the agent is truly stuck. The same mission ID is reused for every later question, so the advisor keeps its context and does not re-read the repository.
Questions go through `ask_worker`; when a reply is still pending, the agent calls it again with the same mission ID, an empty question and the returned baseline unchanged. Ask after two failed attempts at the same problem, before an architectural choice with lasting consequences, in an unfamiliar subsystem or when a test or build failure makes no sense. Skip it for anything one file read or search can settle, since the advisor is read-only. Each question states the goal, what was tried with the trimmed error text, relevant paths and the decision needed, within a budget of about 20 questions per mission.
When your agent uses it
- Running as an executor that escalates only after real dead ends
- Keeping a single read-only advisor on hand for architectural questions
- Controlling the cost of consulting a stronger model during a long task
Example prompts
- “Work this mission as the executor and ask the advisor only if you fail twice on the same problem.”
- “Implement the retry logic yourself, and use the advisor for the queue design if you get stuck.”
- “Create the advisor lazily and keep every question focused with file paths and exact errors.”
Requirements
- The create_worker_mission and ask_worker tools in the host runtime
What it can do on your machine
Read from SKILL.md and the folder at commit f7dcb98. 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 Executor loads about 620 tokens when it runs. Until then it costs about 38 tokens; SKILL.md has 286 words of instructions outside code blocks.
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 286 words (~620 tokens).
“You are the executor: you implement the mission yourself. Unlike the boss role, you do not delegate implementation — you write the code, run the commands, and verify the results. Your escape hatch is a persistent advisor: a stronger (more…”
- name
- orchestrator-executor
Files
Just SKILL.md in skills/orchestrator-executor of Th0rgal/sandboxed.sh.
Open the folder on GitHubat commit f7dcb98
Compare with similar skills
Orchestrator Executor 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.
| Skill | Stars | Used in | Tokens | Auto-check | Licence | Repo updated |
|---|---|---|---|---|---|---|
| Orchestrator Executor this skillTh0rgal/sandboxed.sh | 515 | — | ~620 | Automated safety check: Pass | None | |
| Paseo Advisor Second Opiniongetpaseo/paseo | 20k | 1 repos | ~756 | Automated safety check: Pass | Custom licence | |
| O2 Review Loopopenobserve/openobserve | 22k | — | ~3.7k | Automated safety check: Pass | AGPL-3.0 | |
| Harness Agent Team Designerrevfactory/harness | 9.1k | — | ~4.5k | Automated safety check: Pass | Apache-2.0 | |
| ClawTeam Multi-Agent Swarmwin4r/ClawTeam-OpenClaw | 1.5k | 1 repos | ~2.9k | Automated safety check: Pass | MIT | |
| Sub-Agent Delegationcodewhale-hq/Codewhale | 41k | — | ~790 | Automated safety check: Pass | MIT |
Similar skills
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.
Harness Agent Team Designer
revfactory/harness
Designs a project-specific agent harness: defines specialist agents, writes the skills they follow, picks an execution mode and model for each, and keeps the setup maintained.
ClawTeam Multi-Agent Swarm
win4r/ClawTeam-OpenClaw
Launches a swarm of specialist Hermes agents in git-worktree-isolated tmux windows with a kanban board and file-based inboxes, using built-in templates like hedge-fund and code-review.
Sub-Agent Delegation
codewhale-hq/Codewhale
Guides when and how to split multi-step coding, research or verification work into focused sub-agent runs while the parent keeps integration and final checks.
Parallel Agents
xenitV1/Antigravity-Workflows
Native multi-agent orchestration using Claude Code's Agent Tool.
More from Th0rgal/sandboxed.sh
All 9 skills in this repoSandboxed.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.
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.
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.
Orchestrator Worker
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.
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.
Orchestrator Boss
Th0rgal/sandboxed.sh
Boss skill for parallel worker orchestration. An agent skill from Th0rgal/sandboxed.sh.
Related
Categories
Questions about Orchestrator Executor
What does Orchestrator Executor do?
Has the agent do the implementation itself and consult one persistent, stronger advisor through ask_worker only when it reaches a dead end. In this role the agent writes the code, runs the commands and verifies results itself instead of delegating the work. Its escape hatch is a single advisor, a stronger and more expensive model created lazily with `create_worker_mission` the first time the agent is truly stuck.
When should I use Orchestrator Executor?
Orchestrator Executor fits situations like: running as an executor that escalates only after real dead ends; keeping a single read-only advisor on hand for architectural questions; controlling the cost of consulting a stronger model during a long task.
How do I install Orchestrator Executor in Claude Code?
Run `npx skills add Th0rgal/sandboxed.sh --skill orchestrator-executor -a claude-code`. Or copy the skill folder (skills/orchestrator-executor in Th0rgal/sandboxed.sh) into .claude/skills/orchestrator-executor in your project. Claude Code loads it when a task matches its description.
How do I install Orchestrator Executor in Codex?
Run `npx skills add Th0rgal/sandboxed.sh --skill orchestrator-executor -a codex`. Or copy the skill folder (skills/orchestrator-executor in Th0rgal/sandboxed.sh) into .agents/skills/orchestrator-executor in your project. Codex loads it when a task matches its description.
Can I use Orchestrator Executor 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-executor -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-executor, .gemini/skills/orchestrator-executor, .github/skills/orchestrator-executor and .opencode/skills/orchestrator-executor in your project.
What does Orchestrator Executor need to run?
SKILL.md names no scripts, command-line tools or credentials: Orchestrator Executor is instructions for the agent only. Our summary lists: The create_worker_mission and ask_worker tools in the host runtime.
Does Orchestrator Executor 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 Executor 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 Executor use?
No licence was found for Orchestrator Executor or its repository. Without one, default copyright applies: ask the author before reusing or redistributing it.
How many tokens does Orchestrator Executor use?
About 620 tokens (SKILL.md is roughly 2.5k 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 Executor?
Skills that share tags, products or a category with Orchestrator Executor: Paseo Advisor Second Opinion (getpaseo/paseo, 20k stars), O2 Review Loop (openobserve/openobserve, 22k stars), Harness Agent Team Designer (revfactory/harness, 9.1k stars) and ClawTeam Multi-Agent Swarm (win4r/ClawTeam-OpenClaw, 1.5k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
Who maintains Orchestrator Executor?
Th0rgal (a GitHub user) maintains it in Th0rgal/sandboxed.sh, which has 515 GitHub stars. The repository holds 9 skills in this directory. The repository was last updated on October 6, 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.