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.
COSTLY: Spawns a separate sub-agent CLI session. An agent skill from Wide-Moat/open-computer-use.
Install Sub Agent
$ npx skills add Wide-Moat/open-computer-use --skill sub-agent -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install Wide-Moat/open-computer-use sub-agent --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/Wide-Moat/open-computer-use.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/public/sub-agent .claude/skills/sub-agent && 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 "sub-agent" agent skill from https://github.com/Wide-Moat/open-computer-use/tree/main/skills/public/sub-agent into .claude/skills/sub-agent/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "sub-agent", 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/Wide-Moat/open-computer-use/tree/main/skills/public/sub-agentType 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 Wide-Moat/open-computer-use --skill sub-agent -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install Wide-Moat/open-computer-use sub-agent --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/Wide-Moat/open-computer-use.git skills-src && mkdir -p .agents/skills && cp -r skills-src/skills/public/sub-agent .agents/skills/sub-agent && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "sub-agent" agent skill from https://github.com/Wide-Moat/open-computer-use/tree/main/skills/public/sub-agent into .agents/skills/sub-agent/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "sub-agent", 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 Wide-Moat/open-computer-use --skill sub-agent -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install Wide-Moat/open-computer-use sub-agent --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/Wide-Moat/open-computer-use.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/skills/public/sub-agent .cursor/skills/sub-agent && 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 "sub-agent" agent skill from https://github.com/Wide-Moat/open-computer-use/tree/main/skills/public/sub-agent into .cursor/skills/sub-agent/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "sub-agent", 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/Wide-Moat/open-computer-use.git --path skills/public/sub-agent--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 Wide-Moat/open-computer-use --skill sub-agent -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install Wide-Moat/open-computer-use sub-agent --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/Wide-Moat/open-computer-use.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/skills/public/sub-agent .gemini/skills/sub-agent && 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 "sub-agent" agent skill from https://github.com/Wide-Moat/open-computer-use/tree/main/skills/public/sub-agent into .gemini/skills/sub-agent/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "sub-agent", 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 Wide-Moat/open-computer-use sub-agentInstalls 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 Wide-Moat/open-computer-use --skill sub-agent -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/Wide-Moat/open-computer-use.git skills-src && mkdir -p .github/skills && cp -r skills-src/skills/public/sub-agent .github/skills/sub-agent && 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 "sub-agent" agent skill from https://github.com/Wide-Moat/open-computer-use/tree/main/skills/public/sub-agent into .github/skills/sub-agent/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "sub-agent", 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 Wide-Moat/open-computer-use --skill sub-agent -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install Wide-Moat/open-computer-use sub-agent --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/Wide-Moat/open-computer-use.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/skills/public/sub-agent .opencode/skills/sub-agent && 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 "sub-agent" agent skill from https://github.com/Wide-Moat/open-computer-use/tree/main/skills/public/sub-agent into .opencode/skills/sub-agent/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "sub-agent", 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
sub-agent- GitHub stars
- 126
- Token cost
- ~1.9k tokens
- SKILL.md length
- 644 words
- Files
- 4 (incl. scripts, references)
- Skills in repo
- 5
- Repo updated
- First seen
- Licence
- Custom licence
At a glance
COSTLY: Spawns a separate sub-agent CLI session. An agent skill from Wide-Moat/open-computer-use.
- Any task completable in fewer than 10 tool calls
- SKILL.md covers Before Any sub_agent Call, When to Use (ONLY complex CODE…, When NOT to Use and MANDATORY: Task Structure, plus 4 more sections
- Runs Shell scripts from its folder; calls bash and claude
- Tasks that involve Subagents
What it does
Sub Agent is an agent skill from Wide-Moat/open-computer-use. COSTLY: Spawns a separate sub-agent CLI session. Use ONLY for complex CODE tasks requiring 10+ iterative tool calls (multi-file refactoring with tests, code review with fixes, test-fix cycles). IMPORTANT: Always run the model discovery script first before any subagent call. Do NOT use for presentations, research, documentation, or any task completable in fewer than 10 tool calls.
Its SKILL.md is about 1.9k tokens, which your agent loads only when the skill is triggered. The skill folder holds 5 other files, including scripts and reference files (for example `references/security-review.md`, `references/usage.md` and `scripts/list_subagent_models.sh`).
It sits in Agent Workflows, covering Subagents. The repository describes itself as: ARCHIVED — superseded by Wide Moat.
When your agent uses it
- Any task completable in fewer than 10 tool calls
- Tasks that involve Subagents
Example prompts
- “/sub-agent”
Requirements
- Python 3
- A Bash shell
What it can do on your machine
Read from SKILL.md and the folder at commit 1ddf832. 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/ (Shell), which the agent can run.
Shell commands in SKILL.md call:
bashclaude
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
Sub Agent loads about 1.9k tokens when it runs, and up to ~4.6k if it reads all its reference files. Until then it costs about 98 tokens; SKILL.md has 644 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
Its licence (Custom licence) doesn't allow us to republish the file, so here is its outline and opening line. It has 644 words (~1,872 tokens).
“Delegate complex, multi-step tasks to an autonomous sub-agent that can iterate until completion.”
- name
- sub-agent
Files
SKILL.md and 3 other files (scripts, references) in skills/public/sub-agent of Wide-Moat/open-computer-use.
- SKILL.md
- references/security-review.md
- references/usage.md
- scripts/list_subagent_models.sh
Open the folder on GitHubat commit 1ddf832
Compare with similar skills
Sub Agent 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 |
|---|---|---|---|---|---|---|
| Sub Agent this skillWide-Moat/open-computer-use | 126 | — | ~1.9k | Automated safety check: Pass | Custom licence | |
| O2 Review Loopopenobserve/openobserve | 22k | — | ~3.7k | Automated safety check: Pass | AGPL-3.0 | |
| Kimi Code DelegationCherryHQ/cherry-studio | 52k | 1 repos | ~504 | Automated safety check: Pass | AGPL-3.0 | |
| V2 Perf Iterationmirage-project/mirage | 2.5k | — | ~4k | Automated safety check: Pass | Apache-2.0 | |
| Clone App Pat Proper-simmons/clone-app-pat-pro-public | 259 | — | ~1.9k | Automated safety check: Notes | None | |
| Swarm Orchestrationruvnet/ruflo | 74k | 2 repos | ~779 | Automated safety check: Pass | MIT |
Similar skills
Kimi Code Delegation
CherryHQ/cherry-studio
Delegates one bounded repository task to Kimi Code in non-interactive prompt mode and reads back the final result from its JSON event stream.
V2 Perf Iteration
mirage-project/mirage
Runtime-V2 performance-iteration workflow. An agent skill from mirage-project/mirage.
Clone App Pat Pro
per-simmons/clone-app-pat-pro-public
Clones any web app pixel-for-pixel from a URL. An agent skill from per-simmons/clone-app-pat-pro-public.
Swarm Orchestration
ruvnet/ruflo
Coordinates a hierarchical swarm of specialized agents through the claude-flow CLI for work that spans several files or modules at once.
Team Mode
oil-oil/codex-team-mode
A skill your agent uses when a task may benefit from a bounded subagent for implementation, large-codebase discovery at task start, independent review, requested or pre-commit code simplification…
More from Wide-Moat/open-computer-use
GitLab Explorer
Wide-Moat/open-computer-use
Explore GitLab repositories using glab CLI and git commands.
File Reading
Wide-Moat/open-computer-use
A skill your agent uses when a file has been uploaded but its content is NOT in your context — only its path at /mnt/user-data/uploads/ is listed in an uploadedfiles block.
PDF Reading
Wide-Moat/open-computer-use
A skill your agent uses when you need to read, inspect, or extract content from PDF files — especially when file content is NOT in your context and you need to read it from disk.
Describe Image
Wide-Moat/open-computer-use
Describe images (charts, diagrams, tables, screenshots) using Vision AI.
Related
Categories
Questions about Sub Agent
What does Sub Agent do?
COSTLY: Spawns a separate sub-agent CLI session. An agent skill from Wide-Moat/open-computer-use. Sub Agent is an agent skill from Wide-Moat/open-computer-use. COSTLY: Spawns a separate sub-agent CLI session.
When should I use Sub Agent?
Sub Agent fits situations like: any task completable in fewer than 10 tool calls; tasks that involve Subagents.
How do I install Sub Agent in Claude Code?
Run `npx skills add Wide-Moat/open-computer-use --skill sub-agent -a claude-code`. Or copy the skill folder (skills/public/sub-agent in Wide-Moat/open-computer-use) into .claude/skills/sub-agent in your project. Claude Code loads it when a task matches its description.
How do I install Sub Agent in Codex?
Run `npx skills add Wide-Moat/open-computer-use --skill sub-agent -a codex`. Or copy the skill folder (skills/public/sub-agent in Wide-Moat/open-computer-use) into .agents/skills/sub-agent in your project. Codex loads it when a task matches its description.
Can I use Sub Agent 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 Wide-Moat/open-computer-use --skill sub-agent -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/sub-agent, .gemini/skills/sub-agent, .github/skills/sub-agent and .opencode/skills/sub-agent in your project.
What does Sub Agent need to run?
Going by SKILL.md and its folder, Sub Agent needs a shell for the scripts in its folder and the command-line tools its instructions call (bash and claude). Our summary lists: Python 3; A Bash shell.
Does Sub Agent 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 Sub Agent 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 Sub Agent use?
Sub Agent 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 Sub Agent use?
About 1.9k tokens (SKILL.md is roughly 7.5k 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 2.7k tokens, read only when the agent opens those files.
What are the alternatives to Sub Agent?
Skills that share tags, products or a category with Sub Agent: O2 Review Loop (openobserve/openobserve, 22k stars), Kimi Code Delegation (CherryHQ/cherry-studio, 52k stars), V2 Perf Iteration (mirage-project/mirage, 2.5k stars) and Clone App Pat Pro (per-simmons/clone-app-pat-pro-public, 259 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
Who maintains Sub Agent?
Wide-Moat (a GitHub organization) maintains it in Wide-Moat/open-computer-use, which has 126 GitHub stars. The repository holds 5 skills in this directory. The repository was last updated on October 5, 2026.
Source: Wide-Moat/open-computer-use on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.