Claude Code Agent Development
anthropics/claude-plugins-official
Explains how to write agents for Claude Code plugins: the markdown file with YAML frontmatter, trigger descriptions, model and color settings, and system prompt design.
Tiering and economics for delegating to subagents: which agent type, model, and effort to use per role (explorer, implementer, reviewer, critic), how many agents to launch in parallel, how to write…
Install Orchestrating Subagents
$ npx skills add ZaxbyHub/opencode-swarm --skill orchestrating-subagents -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install ZaxbyHub/opencode-swarm orchestrating-subagents --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/ZaxbyHub/opencode-swarm.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.claude/skills/orchestrating-subagents .claude/skills/orchestrating-subagents && 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 "orchestrating-subagents" agent skill from https://github.com/ZaxbyHub/opencode-swarm/tree/main/.claude/skills/orchestrating-subagents into .claude/skills/orchestrating-subagents/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "orchestrating-subagents", 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/ZaxbyHub/opencode-swarm/tree/main/.claude/skills/orchestrating-subagentsType 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 ZaxbyHub/opencode-swarm --skill orchestrating-subagents -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install ZaxbyHub/opencode-swarm orchestrating-subagents --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/ZaxbyHub/opencode-swarm.git skills-src && mkdir -p .agents/skills && cp -r skills-src/.claude/skills/orchestrating-subagents .agents/skills/orchestrating-subagents && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "orchestrating-subagents" agent skill from https://github.com/ZaxbyHub/opencode-swarm/tree/main/.claude/skills/orchestrating-subagents into .agents/skills/orchestrating-subagents/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "orchestrating-subagents", 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 ZaxbyHub/opencode-swarm --skill orchestrating-subagents -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install ZaxbyHub/opencode-swarm orchestrating-subagents --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/ZaxbyHub/opencode-swarm.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/.claude/skills/orchestrating-subagents .cursor/skills/orchestrating-subagents && 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 "orchestrating-subagents" agent skill from https://github.com/ZaxbyHub/opencode-swarm/tree/main/.claude/skills/orchestrating-subagents into .cursor/skills/orchestrating-subagents/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "orchestrating-subagents", 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/ZaxbyHub/opencode-swarm.git --path .claude/skills/orchestrating-subagents--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 ZaxbyHub/opencode-swarm --skill orchestrating-subagents -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install ZaxbyHub/opencode-swarm orchestrating-subagents --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/ZaxbyHub/opencode-swarm.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/.claude/skills/orchestrating-subagents .gemini/skills/orchestrating-subagents && 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 "orchestrating-subagents" agent skill from https://github.com/ZaxbyHub/opencode-swarm/tree/main/.claude/skills/orchestrating-subagents into .gemini/skills/orchestrating-subagents/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "orchestrating-subagents", 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 ZaxbyHub/opencode-swarm orchestrating-subagentsInstalls 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 ZaxbyHub/opencode-swarm --skill orchestrating-subagents -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/ZaxbyHub/opencode-swarm.git skills-src && mkdir -p .github/skills && cp -r skills-src/.claude/skills/orchestrating-subagents .github/skills/orchestrating-subagents && 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 "orchestrating-subagents" agent skill from https://github.com/ZaxbyHub/opencode-swarm/tree/main/.claude/skills/orchestrating-subagents into .github/skills/orchestrating-subagents/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "orchestrating-subagents", 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 ZaxbyHub/opencode-swarm --skill orchestrating-subagents -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install ZaxbyHub/opencode-swarm orchestrating-subagents --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/ZaxbyHub/opencode-swarm.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/.claude/skills/orchestrating-subagents .opencode/skills/orchestrating-subagents && 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 "orchestrating-subagents" agent skill from https://github.com/ZaxbyHub/opencode-swarm/tree/main/.claude/skills/orchestrating-subagents into .opencode/skills/orchestrating-subagents/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "orchestrating-subagents", 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
orchestrating-subagents- GitHub stars
- 494
- Token cost
- ~1.5k tokens
- SKILL.md length
- 772 words
- Files
- 1
- Skills in repo
- 91
- Repo updated
- First seen
- Licence
- MIT
At a glance
Tiering and economics for delegating to subagents: which agent type, model, and effort to use per role (explorer, implementer, reviewer, critic), how many agents to launch in parallel, how to write…
- Works in 5 steps: Scope — exact directories, files, or… → Deliverable — the structure of the… → Evidence bar — exact file:line… → …
- Launching subagents
- SKILL.md covers Role → tier mapping, Fan-out discipline, Subagent prompt contract and Independence and staleness, plus 3 more sections
- Calls git
What it does
Orchestrating Subagents is an agent skill from ZaxbyHub/opencode-swarm. Tiering and economics for delegating to subagents: which agent type, model, and effort to use per role (explorer, implementer, reviewer, critic), how many agents to launch in parallel, how to write scoped subagent prompts with bounded structured returns, and how to keep the main context clean. Use when launching subagents, parallel explorers, independent reviewers, or critic passes — especially for swarm-mode, qa-sweep, or issue-tracer work.
Its SKILL.md is about 1.5k 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. The repository describes itself as: Architect-centric agentic swarm plugin for OpenCode. Hub-and-spoke orchestration with SME consultation, code generation, and QA review. The licence is MIT.
When your agent uses it
- Launching subagents
- Parallel explorers
- Independent reviewers
- Critic passes — especially for swarm-mode
Example prompts
- “/orchestrating-subagents”
Workflow steps
5 steps, taken from the first numbered list in SKILL.md.
- Scope — exact directories, files, or question. Name what is out of scope.
- Deliverable — the structure of the report (per-item findings, then a
- Evidence bar — exact file:line references; no invented paths; verify a
- Status labels — explorers return CANDIDATE findings only; reviewers
- Output bound — compact structured returns; no full-file dumps.
What it can do on your machine
Read from SKILL.md and the folder at commit b63a4bd. 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
Shell commands in SKILL.md call:
git
From the folder's file list and the shell code blocks in SKILL.md.
Network
No URLs in SKILL.md. Its commands use git, which can reach the network depending on how they are called.
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
Orchestrating Subagents loads about 1.5k tokens when it runs. Until then it costs about 117 tokens; SKILL.md has 772 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 ZaxbyHub/opencode-swarm at commit b63a4bd, republished under its MIT licence (© ZaxbyHub). 772 words, ~1,529 tokens.
Download SKILL.mdSave it as
.claude/skills/orchestrating-subagents/SKILL.md (or your agent's skills folder).- name
- orchestrating-subagents
- description
- Tiering and economics for delegating to subagents: which agent type, model, and effort to use per role (explorer, implementer, reviewer, critic), how many agents to launch in parallel, how to write scoped subagent prompts with bounded structured returns, and how to keep the main context clean. Use when launching subagents, parallel explorers, independent reviewers, or critic passes — especially for swarm-mode, qa-sweep, or issue-tracer work.
- audience
- swarm-plugin
Orchestrating Subagents
Swarm-mode work in this repo delegates heavily (explorer → reviewer → critic).
This skill defines HOW to delegate so validation gates stay strong while
breadth stays fast and cheap. It complements — never replaces — the gates in
.claude/session/swarm-mode.md, qa-sweep, and swarm-implement.
Role → tier mapping
| Role | Agent type | Model / effort | Rationale |
|---|---|---|---|
| Explorer (mapping, candidate findings) | Explore when read-only suffices | Cheaper/faster tier acceptable; low–medium effort | Recall-bound, not reasoning-bound; the reviewer gate catches misses |
| Implementer (scoped edits) | general-purpose | Session model; medium–high effort | Edits need project conventions (CLAUDE.md context) |
| Reviewer (independent validation) | general-purpose, fresh context | Session (strongest) model; high effort | Precision-bound; false approvals are the expensive failure |
| Critic (final challenge) | general-purpose, fresh context | Session (strongest) model; high effort | Same — this is the last line of defense |
Hard rule: economize on explorers, never on reviewers or critics. If the
harness exposes model or effort overrides for subagents, tier explorers down;
do not tier the reviewer or critic below the session model or below high
effort. If no override is available, tier by agent type (Explore is
lightweight: read-only tools, skips CLAUDE.md) and by prompt scope.
Fan-out discipline
- Launch parallel agents only for disjoint scopes. Before launching, write one line per agent stating its scope; if two overlap, merge them.
- 2–4 explorers per wave is a heuristic only when the active workflow does not define its own fan-out contract. A workflow-specific contract overrides this heuristic: PR review, for example, requires all six base dimensions and all eleven risk families to be covered on every PR — its capability profiles and depth tiers (see swarm-pr-review) govern how many lanes carry that coverage, and under the plugin's mechanical controller the tier is computed from the bound diff and the matching lane floors are enforced outright. No time, cost, repository-size, or simplicity rationale may reduce the coverage a workflow mandates. Outside fixed-fan-out workflows, more agents than distinct scopes adds token cost and synthesis burden without adding recall.
- Launch independent agents in a single message so they run concurrently.
- Do not re-run a search an agent is already doing; wait for its report.
- Scale waves, not width: if the first wave surfaces new territory, launch a second targeted wave rather than one giant speculative first wave.
Subagent prompt contract
Every delegation prompt must state:
- Scope — exact directories, files, or question. Name what is out of scope.
- Deliverable — the structure of the report (per-item findings, then a ranked summary). The agent's final message is the only thing you receive.
- Evidence bar — exact
file:linereferences; no invented paths; verify a path exists before citing it. - Status labels — explorers return CANDIDATE findings only; reviewers classify CONFIRMED / DISPROVED / UNVERIFIED / PRE_EXISTING; reviewer and critic verdicts are APPROVE / NEEDS_REVISION / BLOCKED.
- Output bound — compact structured returns; no full-file dumps.
For reviewers and critics additionally:
- Give the claims and locations, not the author's justification — the reviewer must re-derive, not confirm, the reasoning.
- State the adversarial default explicitly: "default to DISPROVED/UNVERIFIED unless the code evidence supports the finding."
- A reviewer or critic must be a fresh agent, never a continued conversation with the agent whose work it judges.
Show full SKILL.md (260 more words)Show less
Independence and staleness
- Reviewer and critic review the latest diff, not a description of it. Give
them the branch state and the validation evidence, and require them to run
git diff/git logthemselves. - Any edit after an approval invalidates it. Record what was approved (e.g.
git rev-parse HEAD,git diff --stat) so staleness is checkable — see the durable-session-state skill.
Nesting limitation
Whether a subagent can spawn further subagents depends on the harness and
agent type — check whether a subagent tool (Agent or Task) is actually
available in your context before assuming either way. If a skill mandating
fresh-subagent review (qa-sweep, swarm-implement) executes in a context
without a subagent tool:
- perform the same review checklist yourself as a clearly labeled fallback self-review, and
- disclose in your report that independent review was unavailable in this context, so the orchestrator can re-run the gate with a real fresh agent. Never silently present self-review as independent review.
Main-context hygiene
- Push reading-heavy work into subagents; keep the main thread for scoping, synthesis, and decisions.
- Do not paste subagent transcripts or large tool outputs back into the main thread; carry forward only validated findings and verdicts.
- When a subagent report arrives, extract the load-bearing facts into your durable task artifacts (see durable-session-state) before moving on.
When not to delegate
Answer directly, without a subagent, when the task is a single-fact lookup you can resolve with one or two targeted Grep/Read calls, or when you already know the file and symbol. Delegation overhead should buy breadth, isolation, or independence — if it buys none of those, skip it.
© ZaxbyHub, MIT. 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 .claude/skills/orchestrating-subagents of ZaxbyHub/opencode-swarm.
Open the folder on GitHubat commit b63a4bd
Compare with similar skills
Orchestrating Subagents 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 |
|---|---|---|---|---|---|---|
| Orchestrating Subagents this skillZaxbyHub/opencode-swarm | 494 | — | ~1.5k | Automated safety check: Pass | MIT | |
| Claude Code Agent Developmentanthropics/claude-plugins-official | 38k | 7 repos | ~2.8k | Automated safety check: Pass | Apache-2.0 | |
| Subagent Driven DevelopmentAsvarox/allkaraoke | 261 | 38 repos | ~1.2k | Automated safety check: Pass | None | |
| Dispatching Parallel Agentsultralisp/ultralisp | 258 | 41 repos | ~1.5k | Automated safety check: Pass | None | |
| Reflect on Session Learningscursor/plugins | 11k | 5 repos | ~1.2k | Automated safety check: Pass | None | |
| Paseo Advisor Second Opiniongetpaseo/paseo | 20k | 1 repos | ~756 | Automated safety check: Pass | Custom licence |
Similar skills
- Official
Subagent Driven Development
Asvarox/allkaraoke
A skill your agent uses when executing implementation plans with independent tasks in the current session
Dispatching Parallel Agents
ultralisp/ultralisp
A skill your agent uses when facing 2+ independent tasks that can be worked on without shared state or sequential dependencies
- 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.
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.
Task Observer
rebelytics/one-skill-to-rule-them-all
Monitors task execution for skill improvement opportunities.
More from ZaxbyHub/opencode-swarm
All 91 skills in this repoCodebase Review Swarm
ZaxbyHub/opencode-swarm
Runs an evidence-gated, quote-grounded audit of a codebase for security, QA, accessibility, performance and more, and writes a verified report without changing source files.
Issue Tracer
ZaxbyHub/opencode-swarm
Drives a bug report from validation and root-cause tracing through a critic-reviewed plan, an approved minimal fix and a PR-ready closure, never merging without recorded human approval.
Commit and PR Publishing for Codex
ZaxbyHub/opencode-swarm
Codex adapter for opencode-swarm that governs commits, pushes, draft PRs, PR body updates and CI closeout, deferring to the repo's canonical commit-pr protocol.
Durable Session State
ZaxbyHub/opencode-swarm
Keeps plans, decisions, evidence and reviewer verdicts in small files so long multi-phase tasks survive context compaction and session resumes.
Swarm PR Feedback Closer
ZaxbyHub/opencode-swarm
Ingests existing pull request feedback such as review comments and CI failures, verifies each claim, fixes confirmed issues and reports closure status for every item.
Swarm PR Subscribe
ZaxbyHub/opencode-swarm
Monitor a pull request after creation and act autonomously on pushed PR activity.
Related
Categories
Questions about Orchestrating Subagents
What does Orchestrating Subagents do?
Tiering and economics for delegating to subagents: which agent type, model, and effort to use per role (explorer, implementer, reviewer, critic), how many agents to launch in parallel, how to write…. Orchestrating Subagents is an agent skill from ZaxbyHub/opencode-swarm. Tiering and economics for delegating to subagents: which agent type, model, and effort to use per role (explorer, implementer, reviewer, critic), how many agents to launch in parallel, how to write scoped subagent prompts with bounded structured returns, and how to keep the main context clean.
When should I use Orchestrating Subagents?
Orchestrating Subagents fits situations like: launching subagents; parallel explorers; independent reviewers; critic passes — especially for swarm-mode.
How do I install Orchestrating Subagents in Claude Code?
Run `npx skills add ZaxbyHub/opencode-swarm --skill orchestrating-subagents -a claude-code`. Or copy the skill folder (.claude/skills/orchestrating-subagents in ZaxbyHub/opencode-swarm) into .claude/skills/orchestrating-subagents in your project. Claude Code loads it when a task matches its description.
How do I install Orchestrating Subagents in Codex?
Run `npx skills add ZaxbyHub/opencode-swarm --skill orchestrating-subagents -a codex`. Or copy the skill folder (.claude/skills/orchestrating-subagents in ZaxbyHub/opencode-swarm) into .agents/skills/orchestrating-subagents in your project. Codex loads it when a task matches its description.
Can I use Orchestrating Subagents 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 ZaxbyHub/opencode-swarm --skill orchestrating-subagents -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/orchestrating-subagents, .gemini/skills/orchestrating-subagents, .github/skills/orchestrating-subagents and .opencode/skills/orchestrating-subagents in your project.
What does Orchestrating Subagents need to run?
Going by SKILL.md and its folder, Orchestrating Subagents needs the command-line tools its instructions call (git).
Does Orchestrating Subagents access the network?
SKILL.md contains no URLs. Its commands use git, which can reach the network depending on how they are called. This is read from the text; nothing was executed.
Is Orchestrating Subagents 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 Orchestrating Subagents use?
Orchestrating Subagents is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.
How many tokens does Orchestrating Subagents use?
About 1.5k tokens (SKILL.md is roughly 6.1k 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 Orchestrating Subagents?
Skills that share tags, products or a category with Orchestrating Subagents: Claude Code Agent Development (anthropics/claude-plugins-official, 38k stars), Subagent Driven Development (Asvarox/allkaraoke, 261 stars), Dispatching Parallel Agents (ultralisp/ultralisp, 258 stars) and Reflect on Session Learnings (cursor/plugins, 11k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
Who maintains Orchestrating Subagents?
ZaxbyHub (a GitHub organization) maintains it in ZaxbyHub/opencode-swarm, which has 494 GitHub stars. The repository holds 91 skills in this directory. The repository was last updated on October 10, 2026.
Source: ZaxbyHub/opencode-swarm on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.