agtx One-Shot Project Runner
fynnfluegge/agtx
Runs a whole project unattended on an agtx kanban board, decomposing the goal, starting tasks, unblocking workers and merging each result.
Splits a large goal into a tree of parallel Cursor cloud agents, with planners, workers and verifiers coordinated by a script and reporting through structured handoffs.
Install Cursor Orchestrate
$ npx skills add cursor/plugins --skill orchestrate -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install cursor/plugins orchestrate --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/cursor/plugins.git skills-src && mkdir -p .claude/skills && cp -r skills-src/orchestrate/skills/orchestrate .claude/skills/orchestrate && 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 "orchestrate" agent skill from https://github.com/cursor/plugins/tree/main/orchestrate/skills/orchestrate into .claude/skills/orchestrate/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "orchestrate", 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/cursor/plugins/tree/main/orchestrate/skills/orchestrateType 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 cursor/plugins --skill orchestrate -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install cursor/plugins orchestrate --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/cursor/plugins.git skills-src && mkdir -p .agents/skills && cp -r skills-src/orchestrate/skills/orchestrate .agents/skills/orchestrate && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "orchestrate" agent skill from https://github.com/cursor/plugins/tree/main/orchestrate/skills/orchestrate into .agents/skills/orchestrate/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "orchestrate", 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 cursor/plugins --skill orchestrate -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install cursor/plugins orchestrate --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/cursor/plugins.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/orchestrate/skills/orchestrate .cursor/skills/orchestrate && 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 "orchestrate" agent skill from https://github.com/cursor/plugins/tree/main/orchestrate/skills/orchestrate into .cursor/skills/orchestrate/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "orchestrate", 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/cursor/plugins.git --path orchestrate/skills/orchestrate--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 cursor/plugins --skill orchestrate -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install cursor/plugins orchestrate --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/cursor/plugins.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/orchestrate/skills/orchestrate .gemini/skills/orchestrate && 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 "orchestrate" agent skill from https://github.com/cursor/plugins/tree/main/orchestrate/skills/orchestrate into .gemini/skills/orchestrate/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "orchestrate", 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 cursor/plugins orchestrateInstalls 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 cursor/plugins --skill orchestrate -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/cursor/plugins.git skills-src && mkdir -p .github/skills && cp -r skills-src/orchestrate/skills/orchestrate .github/skills/orchestrate && 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 "orchestrate" agent skill from https://github.com/cursor/plugins/tree/main/orchestrate/skills/orchestrate into .github/skills/orchestrate/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "orchestrate", 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 cursor/plugins --skill orchestrate -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install cursor/plugins orchestrate --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/cursor/plugins.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/orchestrate/skills/orchestrate .opencode/skills/orchestrate && 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 "orchestrate" agent skill from https://github.com/cursor/plugins/tree/main/orchestrate/skills/orchestrate into .opencode/skills/orchestrate/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "orchestrate", 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
orchestrate- GitHub stars
- 10k
- Token cost
- ~1.1k tokens
- SKILL.md length
- 509 words
- Files
- 87 (incl. scripts, references)
- Skills in repo
- 99
- Repo updated
- First seen
- Licence
- None found
At a glance
Splits a large goal into a tree of parallel Cursor cloud agents, with planners, workers and verifiers coordinated by a script and reporting through structured handoffs.
- Works in 6 steps: Planners own scopes and publish tasks.… → Planners don't know who picks up their… → Workers are isolated. One task, one… → …
- Explicitly fanning out a large, splittable task across parallel cloud agents
- SKILL.md covers Setup, Core principles, Node types and Role
- Calls git; needs CURSOR_API_KEY and SLACK_BOT_TOKEN
What it does
This skill runs only when you type /orchestrate with a goal; the agent never starts it on its own. A planner writes plan.json, a script (scripts/cli.ts) carries out the spawn, wait and handoff loop, and the planner reads the handoffs to decide what comes next. A JSON state file keeps the run on track where long agent loops tend to drift. Workers are isolated, each with one task, one clone of the repo and one handoff, and subplanners are recursive planners that own a slice of the work.
Planners publish tasks and do no coding themselves, siblings never talk to each other, and each level sees only its children's handoffs. You need a personal CURSOR_API_KEY, and the cursor-sdk skill is required reading for spawning, auth and errors. An optional SLACK_BOT_TOKEN lets the script post a kickoff thread, mirror task status and read Andon reactions; without it the run behaves the same but with no Slack visibility. The folder ships prompts for each node type and JSON schemas for the plan and state.
When your agent uses it
- Explicitly fanning out a large, splittable task across parallel cloud agents
- Running planner, worker and verifier roles with recorded handoffs
- Following a long multi-agent run through a Slack thread
Example prompts
- “/orchestrate migrate the monorepo packages from Jest to Vitest, one worker per package”
- “/orchestrate add audit logging to every API route and have a verifier check each change”
Requirements
- A personal Cursor API key in CURSOR_API_KEY
- The cursor-sdk skill
- A Slack bot token, only for status threads
Workflow steps
6 steps, taken from the first numbered list in SKILL.md.
- Planners own scopes and publish tasks. They do no coding. Writing plan.json, reading handoffs, and deciding what's next are planner work…
- Planners don't know who picks up their tasks. The script routes each task to a cloud agent. The planner's mental model stays at the task…
- Workers are isolated. One task, one clone of the repo, no channel to any other agent. One handoff when done.
- Subplanners are recursive planners. A planner publishes a "subplan this slice" task; the subplanner fully owns that slice and hands back…
- Continuous motion via handoffs. A planner that thought it was done can receive a late handoff and replan. No "finished" state until the…
- Propagation, not synchronization. No cross-talk between siblings. No shared state between levels. Each level sees only its children's…
What it can do on your machine
Read from SKILL.md and the folder at commit 9f451cf. 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
Ships 1 file in scripts/, which the agent can run.
Shell commands in SKILL.md call:
git
From the folder's file list and the shell code blocks in SKILL.md.
Network
Links to these hosts (documentation or services it may open):
cursor.com
From URLs in SKILL.md, links to its own repository left out.
Credentials
Names these keys or tokens, usually read from environment variables:
CURSOR_API_KEYSLACK_BOT_TOKEN
From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.
Context cost
Cursor Orchestrate loads about 1.1k tokens when it runs, and up to ~9.1k if it reads all its reference files. Until then it costs about 62 tokens; SKILL.md has 509 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); the scripts in this folder are not scanned.
SKILL.md
Without a licence we can't republish the file, so here is its outline and opening line. It has 509 words (~1,055 tokens).
“An explicit /orchestrate fans out a large task across parallel Cursor cloud agents. Workers don't talk to each other; they talk up through structured handoffs. The spawn, wait, and handoff loop lives in scripts/cli.ts. The planner writes plan.json, the script…”
- name
- orchestrate
- disable-model-invocation
- true
Files
SKILL.md and 86 other files (scripts, references) in orchestrate/skills/orchestrate of cursor/plugins.
- SKILL.md
- prompts/andon-block.md
- prompts/empty-error-handoff.md
- prompts/failure-handoff.md
- prompts/finished-no-handoff.md
- prompts/loop-hygiene.md
- prompts/root.md
- prompts/slack-block.md
- prompts/subplanner.md
- prompts/verifier.md
- prompts/worker.md
- references/dispatcher.md
- references/handoffs.md
- references/planner.md
- references/spawning.md
- schemas/plan.schema.json
- schemas/state.schema.json
- scripts
- … and 69 more
Open the folder on GitHubat commit 9f451cf
Compare with similar skills
Cursor Orchestrate 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 |
|---|---|---|---|---|---|---|
| Cursor Orchestrate this skillcursor/plugins | 10k | — | ~1.1k | Automated safety check: Pass | None | |
| agtx One-Shot Project Runnerfynnfluegge/agtx | 1.7k | — | ~3.8k | Automated safety check: Pass | Apache-2.0 | |
| OMA Multi-Agent Orchestratorfirst-fluke/oh-my-agent | 1.3k | — | ~3.1k | Automated safety check: Pass | MIT | |
| Swarm Parallel Dispatchlangchain-ai/langchain-skills | 1.3k | — | ~3k | Automated safety check: Pass | MIT | |
| Agents Project Coordinatorasgeirtj/system_prompts_leaks | 69k | — | ~2.9k | Automated safety check: Pass | CC0-1.0 | |
| Launching Agent Teamslexler/skill-factory | 239 | — | ~1.3k | Automated safety check: Pass | Apache-2.0 |
Similar skills
OMA Multi-Agent Orchestrator
first-fluke/oh-my-agent
Splits a complex feature into prioritized tasks, spawns specialist CLI subagents in parallel, tracks them through shared memory and verifies each result.
- Official
Swarm Parallel Dispatch
langchain-ai/langchain-skills
Fans a list of independent items out to subagents in parallel, merges the results back into a table and supports retrying only the rows that failed.
Agents Project Coordinator
asgeirtj/system_prompts_leaks
Runs a goal as a project in which the agent coordinates separate agent threads, judging when to split the work, and interviews you first when nothing can be verified.
Launching Agent Teams
lexler/skill-factory
Plans and launches Claude Code agent teams with distinct roles, right-sized tasks and detailed spawn prompts, and says when subagents or worktrees fit better.
Team Agent Pipeline
zereight/gitlab-mcp
Spawns a chosen number of coordinated agents on a shared task list and runs them through plan, requirements, execution, verification and fix stages.
More from cursor/plugins
All 99 skills in this repo- Official
Show Me Your Work Decision Log
cursor/plugins
Keeps a TSV decision log for long or unattended agent runs, one row per decision with what, why, evidence and result, so a reviewer can check the work later.
- Official
Code Design Rationale Investigator
cursor/plugins
Digs into why code is shaped the way it is by checking git history, pull requests and connected tools in parallel, then reporting a cited read on the tradeoffs.
- Official
Reflect on Session Learnings
cursor/plugins
Starts three parallel reviewer subagents over the current conversation transcript, then turns their findings into concrete edits to existing skills.
- Official
Technical Writing Standard
cursor/plugins
Applies four layers of technical-writing rules to docs, RFCs, readmes, PR descriptions and commit messages so a tired engineer follows them on the first read.
- Official
Advisor Mode
cursor/plugins
Adds a second, stronger model that the main agent consults before major decisions, when stuck and before finishing, controlled by /advisor commands.
- Official
Make PR Easy To Review
cursor/plugins
Prepare PRs for review by cleaning noisy history, improving PR descriptions, and adding reviewer guidance without changing code behavior.
Related
Works with
Categories
Questions about Cursor Orchestrate
What does Cursor Orchestrate do?
Splits a large goal into a tree of parallel Cursor cloud agents, with planners, workers and verifiers coordinated by a script and reporting through structured handoffs. This skill runs only when you type /orchestrate with a goal; the agent never starts it on its own.ts) carries out the spawn, wait and handoff loop, and the planner reads the handoffs to decide what comes next.
When should I use Cursor Orchestrate?
Cursor Orchestrate fits situations like: explicitly fanning out a large, splittable task across parallel cloud agents; running planner, worker and verifier roles with recorded handoffs; following a long multi-agent run through a Slack thread.
How do I install Cursor Orchestrate in Claude Code?
Run `npx skills add cursor/plugins --skill orchestrate -a claude-code`. Or copy the skill folder (orchestrate/skills/orchestrate in cursor/plugins) into .claude/skills/orchestrate in your project. Claude Code loads it when a task matches its description.
How do I install Cursor Orchestrate in Codex?
Run `npx skills add cursor/plugins --skill orchestrate -a codex`. Or copy the skill folder (orchestrate/skills/orchestrate in cursor/plugins) into .agents/skills/orchestrate in your project. Codex loads it when a task matches its description.
Can I use Cursor Orchestrate 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 cursor/plugins --skill orchestrate -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/orchestrate, .gemini/skills/orchestrate, .github/skills/orchestrate and .opencode/skills/orchestrate in your project.
What does Cursor Orchestrate need to run?
Going by SKILL.md and its folder, Cursor Orchestrate needs the command-line tools its instructions call (git) and credentials named CURSOR_API_KEY and SLACK_BOT_TOKEN. Our summary lists: A personal Cursor API key in CURSOR_API_KEY; The cursor-sdk skill; A Slack bot token, only for status threads.
Does Cursor Orchestrate access the network?
SKILL.md names 1 domain. As links in the text: cursor.com. This is read from the text; nothing was executed.
Is Cursor Orchestrate 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. The check reads SKILL.md only: the scripts in the folder are not scanned, so read them before running anything.
What licence does Cursor Orchestrate use?
No licence was found for Cursor Orchestrate or its repository. Without one, default copyright applies: ask the author before reusing or redistributing it.
How many tokens does Cursor Orchestrate use?
About 1.1k tokens (SKILL.md is roughly 4.2k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full. Its references folder adds about 8.1k tokens, read only when the agent opens those files.
What are the alternatives to Cursor Orchestrate?
Skills that share tags, products or a category with Cursor Orchestrate: agtx One-Shot Project Runner (fynnfluegge/agtx, 1.7k stars), OMA Multi-Agent Orchestrator (first-fluke/oh-my-agent, 1.3k stars), Swarm Parallel Dispatch (langchain-ai/langchain-skills, 1.3k stars) and Agents Project Coordinator (asgeirtj/system_prompts_leaks, 69k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
Who maintains Cursor Orchestrate?
cursor (a GitHub organization, an official publisher) maintains it in cursor/plugins, which has 10,130 GitHub stars. The repository holds 99 skills in this directory. The repository was last updated on October 6, 2026.
Source: cursor/plugins on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.