Claude Code
kortix-ai/suna
Drive Anthropic's Claude Code CLI (claude -p) as a non-interactive coding sub-agent from inside Codex.
Run fix/refactor work with parallel subagents split into non-overlapping file batches; agents never build or test — the coordinator verifies once at the end.
Install Subagent Batches
$ npx skills add LunCoSim/lunco-sim --skill subagent-batches -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install LunCoSim/lunco-sim subagent-batches --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/LunCoSim/lunco-sim.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/subagent-batches .claude/skills/subagent-batches && 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 "subagent-batches" agent skill from https://github.com/LunCoSim/lunco-sim/tree/main/skills/subagent-batches into .claude/skills/subagent-batches/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "subagent-batches", 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/LunCoSim/lunco-sim/tree/main/skills/subagent-batchesType 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 LunCoSim/lunco-sim --skill subagent-batches -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install LunCoSim/lunco-sim subagent-batches --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/LunCoSim/lunco-sim.git skills-src && mkdir -p .agents/skills && cp -r skills-src/skills/subagent-batches .agents/skills/subagent-batches && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "subagent-batches" agent skill from https://github.com/LunCoSim/lunco-sim/tree/main/skills/subagent-batches into .agents/skills/subagent-batches/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "subagent-batches", 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 LunCoSim/lunco-sim --skill subagent-batches -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install LunCoSim/lunco-sim subagent-batches --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/LunCoSim/lunco-sim.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/skills/subagent-batches .cursor/skills/subagent-batches && 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 "subagent-batches" agent skill from https://github.com/LunCoSim/lunco-sim/tree/main/skills/subagent-batches into .cursor/skills/subagent-batches/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "subagent-batches", 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/LunCoSim/lunco-sim.git --path skills/subagent-batches--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 LunCoSim/lunco-sim --skill subagent-batches -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install LunCoSim/lunco-sim subagent-batches --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/LunCoSim/lunco-sim.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/skills/subagent-batches .gemini/skills/subagent-batches && 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 "subagent-batches" agent skill from https://github.com/LunCoSim/lunco-sim/tree/main/skills/subagent-batches into .gemini/skills/subagent-batches/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "subagent-batches", 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 LunCoSim/lunco-sim subagent-batchesInstalls 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 LunCoSim/lunco-sim --skill subagent-batches -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/LunCoSim/lunco-sim.git skills-src && mkdir -p .github/skills && cp -r skills-src/skills/subagent-batches .github/skills/subagent-batches && 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 "subagent-batches" agent skill from https://github.com/LunCoSim/lunco-sim/tree/main/skills/subagent-batches into .github/skills/subagent-batches/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "subagent-batches", 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 LunCoSim/lunco-sim --skill subagent-batches -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install LunCoSim/lunco-sim subagent-batches --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/LunCoSim/lunco-sim.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/skills/subagent-batches .opencode/skills/subagent-batches && 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 "subagent-batches" agent skill from https://github.com/LunCoSim/lunco-sim/tree/main/skills/subagent-batches into .opencode/skills/subagent-batches/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "subagent-batches", 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
subagent-batches- GitHub stars
- 107
- Token cost
- ~899 tokens
- SKILL.md length
- 501 words
- Files
- 1
- Skills in repo
- 40
- Repo updated
- First seen
- Licence
- Apache-2.0
At a glance
Run fix/refactor work with parallel subagents split into non-overlapping file batches; agents never build or test — the coordinator verifies once at the end.
- Works in 5 steps: Prioritize first, run second. Read the… → Split work into lots with disjoint file… → Agents never run builds or tests. Every… → …
- Multi-finding fix sweeps (review reports
- SKILL.md covers Core rules, Agent prompt template, Coordinator duties between… and End of run
- Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md
What it does
Subagent Batches is an agent skill from LunCoSim/lunco-sim. Run fix/refactor work with parallel subagents split into non-overlapping file batches; agents never build or test — the coordinator verifies once at the end. Use for multi-finding fix sweeps (review reports, audits, migrations).
Its SKILL.md is about 900 tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.
It sits in Agent Workflows, covering Subagents and Refactoring. The repository describes itself as: Collaborative Multiphysics Cosimulator For Space Missions 🌎🚀🌚. The licence is Apache-2.0.
When your agent uses it
- Multi-finding fix sweeps (review reports
- Tasks that involve Subagents
- Tasks that involve Refactoring
Example prompts
- “/subagent-batches”
Workflow steps
5 steps, taken from the first numbered list in SKILL.md.
- Prioritize first, run second. Read the source reports yourself, group findings, present the batch plan to the user, get agreement on scope…
- Split work into lots with disjoint file ownership. Each agent gets an explicit list of files it owns and the instruction "other agents own…
- Agents never run builds or tests. Every agent prompt includes: "do NOT run cargo, tests, or builds of any kind; do not commit." The…
- Launch each batch's agents in a single message (parallel tool calls). Batches are sequential rounds; agents within a batch are parallel.
- New batches must avoid files owned by still-running agents. Track ownership; a finished agent's files are free for the next round.
What it can do on your machine
Read from SKILL.md and the folder at commit 43f1301. 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
Subagent Batches loads about 899 tokens when it runs. Until then it costs about 61 tokens; SKILL.md has 501 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
The full file from LunCoSim/lunco-sim at commit 43f1301, republished under its Apache-2.0 licence (© LunCoSim). 501 words, ~899 tokens.
Download SKILL.mdSave it as
.claude/skills/subagent-batches/SKILL.md (or your agent's skills folder).- name
- subagent-batches
- description
- Run fix/refactor work with parallel subagents split into non-overlapping file batches; agents never build or test — the coordinator verifies once at the end. Use for multi-finding fix sweeps (review reports, audits, migrations).
Subagent batches — parallel fixes without collisions
Workflow for executing many independent code changes (e.g. findings from a review report) with parallel subagents.
Core rules
Prioritize first, run second. Read the source reports yourself, group findings, present the batch plan to the user, get agreement on scope BEFORE launching any fix agent. Deferred scopes (e.g. multiplayer/RBAC while focused on singleplayer) get a comment-only batch, not fixes.
Split work into lots with disjoint file ownership. Each agent gets an explicit list of files it owns and the instruction "other agents own other files — do not touch anything else." No two agents in flight may share a file. Group by file/crate proximity, not by finding severity — the lot boundary is the file set.
Agents never run builds or tests. Every agent prompt includes: "do NOT run cargo, tests, or builds of any kind; do not commit." The coordinator runs focused checks with
-j 4after all batches land, then expands coverage only when the changed owners require it. This avoids N agents compiling the same workspace concurrently.Launch each batch's agents in a single message (parallel tool calls). Batches are sequential rounds; agents within a batch are parallel.
New batches must avoid files owned by still-running agents. Track ownership; a finished agent's files are free for the next round.
Agent prompt template
Every fix-agent prompt contains:
- Repo path + which report file(s) and sections to read for finding details.
- "Verify each cited site by reading the CURRENT code before editing" — findings go stale (line drift, refactors, already-fixed). If a file was edited by an earlier batch, say so explicitly ("line numbers may have shifted; do not disturb those changes").
- The exact item list with file:line and expected fix direction.
- Owned-file list (exclusive).
- Style rules: match surrounding code; no comments explaining the change or its provenance; smallest correct diff; don't overengineer.
- Required return format: terse list of file → what changed → anything NOT fixed and why.
Show full SKILL.md (176 more words)Show less
Coordinator duties between batches
- Handoffs: if an agent reports an item it couldn't fix because the file belongs to another lot, either (a) SendMessage the owning agent if still running, or (b) fix it yourself if tiny, or (c) queue it for the next batch. Never let it silently drop.
- Caveat forwarding: when a later report refutes/downgrades a finding an in-flight agent is working on, SendMessage the agent immediately with the correction rather than waiting.
- Cross-check agent claims that remove code paths: if an agent deletes "the only call site" of something (e.g. the only registry-removal path), verify the replacement path actually exists before moving on.
- False-positive tolerance: agents should report "finding is stale/wrong, nothing to change" as a valid outcome — put nuances you already know (e.g. deliberate bypass patterns) into the prompt so agents don't "fix" intentional code.
End of run
- Focused build and test checks over touched crates with
-j 4; expand only when the change crosses a workspace boundary. - Summarize per-lot: fixed / skipped-with-reason / deferred-with-comment.
- User commits; never commit or push from the workflow.
© LunCoSim, Apache-2.0. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file
Files
Just SKILL.md in skills/subagent-batches of LunCoSim/lunco-sim.
Open the folder on GitHubat commit 43f1301
Compare with similar skills
Subagent Batches 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 |
|---|---|---|---|---|---|---|
| Subagent Batches this skillLunCoSim/lunco-sim | 107 | — | ~899 | Automated safety check: Pass | Apache-2.0 | |
| Claude Codekortix-ai/suna | 20k | — | ~1.2k | Automated safety check: Pass | Custom licence | |
| Workflow Orchestrationvxcozy/workflow-orchestration | 116 | — | ~1k | Automated safety check: Pass | MIT | |
| Antigravity Agentsmarkfulton/claude-antigravity-agents | 130 | — | ~2.1k | Automated safety check: Pass | MIT | |
| Subagent Coordinatorflyxl/datazen | 114 | — | ~936 | Automated safety check: Pass | GPL-3.0 | |
| Orchestrate Batch RefactorDimillian/Skills | 4k | — | ~889 | Automated safety check: Pass | MIT |
Similar skills
Workflow Orchestration
vxcozy/workflow-orchestration
Disciplined task execution with planning, verification, and self-improvement loops.
Antigravity Agents
markfulton/claude-antigravity-agents
Delegate coding, code review, analysis, and research jobs to Google Antigravity CLI (agy) sub-agents that run alongside your own work.
Subagent Coordinator
flyxl/datazen
Orchestrate multi-track parallel feature development with subagents and git worktrees.
Orchestrate Batch Refactor
Dimillian/Skills
Plan and execute large refactor or rewrite efforts efficiently with parallel multi-agent analysis and implementation.
Batch Orchestration
rohitg00/pro-workflow
Decompose large-scale changes into independent units and spawn parallel agents in isolated worktrees.
More from LunCoSim/lunco-sim
All 40 skills in this repoNightly Changelog
LunCoSim/lunco-sim
Generate concise LunCoSim nightly GitHub release notes with platform downloads, installation guidance, an AI-agent mission prompt, and a changelog link.
Interactive Component Authoring
LunCoSim/lunco-sim
Build or repair a reusable scene component through a live LunCoSim Editor session.
Assembly Quality
LunCoSim/lunco-sim
Build or review a componentized LunCoSim USD assembly with a realistic, dimensionally checkable presentation.
Author Rhai Tests
LunCoSim/lunco-sim
Author and review LunCoSim behavioral, asset-backed, component, mission, visual, and requirements-verification tests.
Author Rhai Tool
LunCoSim/lunco-sim
Create, extend, register, or debug a reusable LunCoSim Rhai tool library for live USD authoring, component linting, inspection, or test support.
Author Tutorial
LunCoSim/lunco-sim
Author an interactive tutorial, guided lesson, onboarding flow, coach-mark tour, or objectives checklist in LunCoSim.
Related
Categories
Questions about Subagent Batches
What does Subagent Batches do?
Run fix/refactor work with parallel subagents split into non-overlapping file batches; agents never build or test — the coordinator verifies once at the end. Subagent Batches is an agent skill from LunCoSim/lunco-sim. Run fix/refactor work with parallel subagents split into non-overlapping file batches; agents never build or test — the coordinator verifies once at the end.
When should I use Subagent Batches?
Subagent Batches fits situations like: multi-finding fix sweeps (review reports; tasks that involve Subagents; tasks that involve Refactoring.
How do I install Subagent Batches in Claude Code?
Run `npx skills add LunCoSim/lunco-sim --skill subagent-batches -a claude-code`. Or copy the skill folder (skills/subagent-batches in LunCoSim/lunco-sim) into .claude/skills/subagent-batches in your project. Claude Code loads it when a task matches its description.
How do I install Subagent Batches in Codex?
Run `npx skills add LunCoSim/lunco-sim --skill subagent-batches -a codex`. Or copy the skill folder (skills/subagent-batches in LunCoSim/lunco-sim) into .agents/skills/subagent-batches in your project. Codex loads it when a task matches its description.
Can I use Subagent Batches 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 LunCoSim/lunco-sim --skill subagent-batches -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/subagent-batches, .gemini/skills/subagent-batches, .github/skills/subagent-batches and .opencode/skills/subagent-batches in your project.
What does Subagent Batches need to run?
SKILL.md names no scripts, command-line tools or credentials: Subagent Batches is instructions for the agent only.
Does Subagent Batches 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 Subagent Batches 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 Subagent Batches use?
Subagent Batches is published under the Apache-2.0 licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.
How many tokens does Subagent Batches use?
About 899 tokens (SKILL.md is roughly 3.6k 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 Subagent Batches?
Skills that share tags, products or a category with Subagent Batches: Claude Code (kortix-ai/suna, 20k stars), Workflow Orchestration (vxcozy/workflow-orchestration, 116 stars), Antigravity Agents (markfulton/claude-antigravity-agents, 130 stars) and Subagent Coordinator (flyxl/datazen, 114 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
Who maintains Subagent Batches?
LunCoSim (a GitHub organization) maintains it in LunCoSim/lunco-sim, which has 107 GitHub stars. The repository holds 40 skills in this directory. The repository was last updated on October 10, 2026.
Source: LunCoSim/lunco-sim on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.