Agency Orchestrator Workflow Runner
jnMetaCode/superpowers-zh
Runs agency-orchestrator YAML workflows inside the current agent session, with the session's own model playing each role in turn and no API key needed.
Authors, validates, runs and participates in Prowl Agent Workflows, bundles that orchestrate several live coding agents inside the Prowl macOS app.
Install Prowl Agent Workflows
$ npx skills add onevcat/Prowl --skill prowl-workflow -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install onevcat/Prowl prowl-workflow --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/onevcat/Prowl.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/prowl-workflow .claude/skills/prowl-workflow && 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 "prowl-workflow" agent skill from https://github.com/onevcat/Prowl/tree/main/skills/prowl-workflow into .claude/skills/prowl-workflow/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "prowl-workflow", 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/onevcat/Prowl/tree/main/skills/prowl-workflowType 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 onevcat/Prowl --skill prowl-workflow -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install onevcat/Prowl prowl-workflow --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/onevcat/Prowl.git skills-src && mkdir -p .agents/skills && cp -r skills-src/skills/prowl-workflow .agents/skills/prowl-workflow && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "prowl-workflow" agent skill from https://github.com/onevcat/Prowl/tree/main/skills/prowl-workflow into .agents/skills/prowl-workflow/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "prowl-workflow", 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 onevcat/Prowl --skill prowl-workflow -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install onevcat/Prowl prowl-workflow --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/onevcat/Prowl.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/skills/prowl-workflow .cursor/skills/prowl-workflow && 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 "prowl-workflow" agent skill from https://github.com/onevcat/Prowl/tree/main/skills/prowl-workflow into .cursor/skills/prowl-workflow/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "prowl-workflow", 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/onevcat/Prowl.git --path skills/prowl-workflow--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 onevcat/Prowl --skill prowl-workflow -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install onevcat/Prowl prowl-workflow --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/onevcat/Prowl.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/skills/prowl-workflow .gemini/skills/prowl-workflow && 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 "prowl-workflow" agent skill from https://github.com/onevcat/Prowl/tree/main/skills/prowl-workflow into .gemini/skills/prowl-workflow/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "prowl-workflow", 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 onevcat/Prowl prowl-workflowInstalls 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 onevcat/Prowl --skill prowl-workflow -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/onevcat/Prowl.git skills-src && mkdir -p .github/skills && cp -r skills-src/skills/prowl-workflow .github/skills/prowl-workflow && 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 "prowl-workflow" agent skill from https://github.com/onevcat/Prowl/tree/main/skills/prowl-workflow into .github/skills/prowl-workflow/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "prowl-workflow", 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 onevcat/Prowl --skill prowl-workflow -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install onevcat/Prowl prowl-workflow --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/onevcat/Prowl.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/skills/prowl-workflow .opencode/skills/prowl-workflow && 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 "prowl-workflow" agent skill from https://github.com/onevcat/Prowl/tree/main/skills/prowl-workflow into .opencode/skills/prowl-workflow/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "prowl-workflow", 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
prowl-workflow- GitHub stars
- 631
- Token cost
- ~2.7k tokens
- SKILL.md length
- 1,228 words
- Files
- 4 (incl. references)
- Skills in repo
- 10
- Repo updated
- First seen
- Licence
- Custom licence
At a glance
Authors, validates, runs and participates in Prowl Agent Workflows, bundles that orchestrate several live coding agents inside the Prowl macOS app.
- Works in 6 steps: Do the work the prompt asks for,… → Deliver by running the exact rendered… → Include the declared sections, format,… → …
- Creating a workflow in which two agents review each other's work
- SKILL.md covers Authoring loop, Built-in handoff, Built-in Review Loop and Running a workflow, plus 2 more sections
- Needs PROWL_WORKFLOW_TOKEN
What it does
A workflow is a `.pwlworkflow` directory containing `workflow.yaml` with the `prowl.workflow/v1` schema, plus optional local script actions, helpers, schemas and assets. It declares roles, sequential steps, typed state, conditions and loops, and Prowl runs it with agent roles in real terminal panes. Workflows come from the app bundle, the user's `~/.prowl/workflows/` folder or a repository's `.prowl/workflows/` folder, with later sources shadowing earlier ones by ID.
The authoring loop reads `references/authoring.md`, drafts the workflow and checks it with `prowl workflow validate`, which works with Prowl closed, although passing validation does not guarantee a successful run. For launch roles the agent omits `agents` unless you require particular runtimes. Other references cover script actions and running or debugging a run. When a `[Prowl]` line with a `prowl workflow deliver` command appears in the pane, the agent is a participant and delivers through the workflow protocol. The skill is not for driving individual panes with prowl-cli or for Prowl settings questions.
When your agent uses it
- Creating a workflow in which two agents review each other's work
- Running an existing Prowl workflow on a branch
- Debugging a workflow run or writing a script action
- Responding to a Prowl workflow delivery prompt in a pane
Example prompts
- “Write me a Prowl workflow that has two agents review each other's changes.”
- “Add an input to the guessing-game workflow and validate it.”
- “Run the count-files workflow and tell me where the result files are.”
Requirements
- The Prowl macOS app and its `prowl` command-line tool
Workflow steps
6 steps, taken from the first numbered list in SKILL.md.
- Do the work the prompt asks for, completely, before delivering.
- Deliver by running the exact rendered command with the body on stdin as markdown
- Include the declared sections, format, and verdict. Empty bodies are rejected; other
- Lost? prowl workflow status (no arguments) answers "who am I": this pane's run, role,
- Never use prowl agents dispatch-complete for a workflow activation — it is rejected
- A launched participant finds the same contract in its kickoff prompt ("Prowl workflow
What it can do on your machine
Read from SKILL.md and the folder at commit 386b8d0. 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 (its code samples are bash).
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 these keys or tokens, usually read from environment variables:
PROWL_WORKFLOW_TOKEN
From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.
Context cost
Prowl Agent Workflows loads about 2.7k tokens when it runs, and up to ~10k if it reads all its reference files. Until then it costs about 244 tokens; SKILL.md has 1,228 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
Its licence (Custom licence) doesn't allow us to republish the file, so here is its outline and opening line. It has 1,228 words (~2,686 tokens).
“A workflow is a .pwlworkflow directory with workflow.yaml (schema: prowl.workflow/v1) and optional local script actions, helpers, schemas, and assets. It declares roles and sequential steps, typed state, nested conditions and loops. Prowl executes it; agent roles use real terminal panes…”
- name
- prowl-workflow
- metadata.prowl-summary
- Teaches an agent to write, validate, and run Prowl Agent Workflow bundles, to create and test local script actions, to act as a participant when a workflow…
Files
SKILL.md and 3 other files (references) in skills/prowl-workflow of onevcat/Prowl.
- SKILL.md
- references/actions.md
- references/authoring.md
- references/runbook.md
Open the folder on GitHubat commit 386b8d0
Compare with similar skills
Prowl Agent Workflows 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 |
|---|---|---|---|---|---|---|
| Prowl Agent Workflows this skillonevcat/Prowl | 631 | — | ~2.7k | Automated safety check: Pass | Custom licence | |
| Agency Orchestrator Workflow RunnerjnMetaCode/superpowers-zh | 8.3k | 1 repos | ~885 | Automated safety check: Pass | MIT | |
| Orchestration Graph RunnerYeachan-Heo/oh-my-claudecode | 40k | — | ~1.3k | Automated safety check: Pass | MIT | |
| CodegridBankrBot/skills | 1.2k | — | ~1.1k | Automated safety check: Pass | None | |
| cmux Cloud Machinesmanaflow-ai/cmux | 28k | — | ~864 | Automated safety check: Pass | Custom licence | |
| Fastgpt Workflow GeneratorYYH211/Claude-meta-skill | 282 | — | ~5.5k | Automated safety check: Pass | MIT |
Similar skills
Orchestration Graph Runner
Yeachan-Heo/oh-my-claudecode
Runs deterministic DAG pipelines from a JSON descriptor with journal-based crash recovery, so an interrupted run resumes without repeating finished nodes.
Codegrid
BankrBot/skills
CodeGrid is a native macOS canvas where multiple coding agents (Claude, Codex, Gemini, Cursor, Grok, shells) run side by side in panes and collaborate via a local agent bus — no tmux, no cloud, no…
cmux Cloud Machines
manaflow-ai/cmux
Operates cmux Cloud machines from the cmux CLI, running durable remote commands or detached agents and presenting their workspaces, with authorization limits on destructive steps.
Fastgpt Workflow Generator
YYH211/Claude-meta-skill
Generates production-ready FastGPT workflow JSON from natural language requirements.
cmux Agent Surface Control
disler/learning-cmux-with-agents
Drives the cmux terminal multiplexer from natural language to open, inspect, prompt, read and close windows, workspaces, panes, surfaces and agent sessions.
More from onevcat/Prowl
All 10 skills in this repoProwl UI Verification
onevcat/Prowl
Drives and verifies the native macOS Prowl Debug UI through accessibility automation, proving behavior with before-and-after evidence instead of reasoning from code.
Prowl Self-Verify
onevcat/Prowl
Runs an opt-in end-to-end verification of Prowl changes in a separate debug instance, writing a verification contract first and reporting pass, fail, skipped or inconclusive for every scenario.
Prowl Performance Benchmark Runner
onevcat/Prowl
Runs Prowl's benchmark layers for a branch or release against recorded baselines, only when explicitly asked and the machine is quiet.
Release-Time Localization Sync
onevcat/Prowl
Catches an app's string catalog up with the code once per release: translating new text, pruning unused entries, and flagging unlocalized strings.
Write AI Doc
onevcat/Prowl
Create and maintain curated docs-ai/ records for substantial features and non-trivial, decision-shaping fixes (numbered entries with 000-plan.md before implementation and 001-action.md after).
Doc Sync for Agent Manuals
onevcat/Prowl
Keeps an agent-facing documentation set accurate against the implementation through small, diff-driven edits since a committed baseline.
Related
Works with
Categories
Questions about Prowl Agent Workflows
What does Prowl Agent Workflows do?
Authors, validates, runs and participates in Prowl Agent Workflows, bundles that orchestrate several live coding agents inside the Prowl macOS app. workflow/v1` schema, plus optional local script actions, helpers, schemas and assets. It declares roles, sequential steps, typed state, conditions and loops, and Prowl runs it with agent roles in real terminal panes.
When should I use Prowl Agent Workflows?
Prowl Agent Workflows fits situations like: creating a workflow in which two agents review each other's work; running an existing Prowl workflow on a branch; debugging a workflow run or writing a script action; responding to a Prowl workflow delivery prompt in a pane.
How do I install Prowl Agent Workflows in Claude Code?
Run `npx skills add onevcat/Prowl --skill prowl-workflow -a claude-code`. Or copy the skill folder (skills/prowl-workflow in onevcat/Prowl) into .claude/skills/prowl-workflow in your project. Claude Code loads it when a task matches its description.
How do I install Prowl Agent Workflows in Codex?
Run `npx skills add onevcat/Prowl --skill prowl-workflow -a codex`. Or copy the skill folder (skills/prowl-workflow in onevcat/Prowl) into .agents/skills/prowl-workflow in your project. Codex loads it when a task matches its description.
Can I use Prowl Agent Workflows 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 onevcat/Prowl --skill prowl-workflow -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/prowl-workflow, .gemini/skills/prowl-workflow, .github/skills/prowl-workflow and .opencode/skills/prowl-workflow in your project.
What does Prowl Agent Workflows need to run?
Going by SKILL.md and its folder, Prowl Agent Workflows needs credentials named PROWL_WORKFLOW_TOKEN. Our summary lists: The Prowl macOS app and its `prowl` command-line tool.
Does Prowl Agent Workflows 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 Prowl Agent Workflows 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 Prowl Agent Workflows use?
Prowl Agent Workflows has a licence file (the repository's licence) that doesn't match a standard licence. Read it on GitHub before reusing the skill.
How many tokens does Prowl Agent Workflows use?
About 2.7k tokens (SKILL.md is roughly 11k 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 7.7k tokens, read only when the agent opens those files.
What are the alternatives to Prowl Agent Workflows?
Skills that share tags, products or a category with Prowl Agent Workflows: Agency Orchestrator Workflow Runner (jnMetaCode/superpowers-zh, 8.3k stars), Orchestration Graph Runner (Yeachan-Heo/oh-my-claudecode, 40k stars), Codegrid (BankrBot/skills, 1.2k stars) and cmux Cloud Machines (manaflow-ai/cmux, 28k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
Who maintains Prowl Agent Workflows?
onevcat (a GitHub user) maintains it in onevcat/Prowl, which has 631 GitHub stars. The repository holds 10 skills in this directory. The repository was last updated on October 6, 2026.
Source: onevcat/Prowl on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.