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.
Delegates a focused piece of work to a DevSpace subagent through the devspace CLI, picking a target, writing a self-contained brief, and waiting on or continuing the resulting agent.
Install DevSpace Subagent Delegation
$ npx skills add Waishnav/devspace --skill subagents -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install Waishnav/devspace 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/Waishnav/devspace.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/subagents .claude/skills/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 "subagents" agent skill from https://github.com/Waishnav/devspace/tree/main/skills/subagents into .claude/skills/subagents/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "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/Waishnav/devspace/tree/main/skills/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 Waishnav/devspace --skill subagents -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install Waishnav/devspace subagents --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/Waishnav/devspace.git skills-src && mkdir -p .agents/skills && cp -r skills-src/skills/subagents .agents/skills/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 "subagents" agent skill from https://github.com/Waishnav/devspace/tree/main/skills/subagents into .agents/skills/subagents/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "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 Waishnav/devspace --skill subagents -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install Waishnav/devspace subagents --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/Waishnav/devspace.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/skills/subagents .cursor/skills/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 "subagents" agent skill from https://github.com/Waishnav/devspace/tree/main/skills/subagents into .cursor/skills/subagents/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "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/Waishnav/devspace.git --path skills/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 Waishnav/devspace --skill subagents -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install Waishnav/devspace subagents --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/Waishnav/devspace.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/skills/subagents .gemini/skills/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 "subagents" agent skill from https://github.com/Waishnav/devspace/tree/main/skills/subagents into .gemini/skills/subagents/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "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 Waishnav/devspace 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 Waishnav/devspace --skill subagents -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/Waishnav/devspace.git skills-src && mkdir -p .github/skills && cp -r skills-src/skills/subagents .github/skills/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 "subagents" agent skill from https://github.com/Waishnav/devspace/tree/main/skills/subagents into .github/skills/subagents/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "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 Waishnav/devspace --skill 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 Waishnav/devspace subagents --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/Waishnav/devspace.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/skills/subagents .opencode/skills/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 "subagents" agent skill from https://github.com/Waishnav/devspace/tree/main/skills/subagents into .opencode/skills/subagents/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "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
subagents- GitHub stars
- 5.2k
- Token cost
- ~743 tokens
- SKILL.md length
- 325 words
- Files
- 1
- Skills in repo
- 2
- Repo updated
- First seen
- Licence
- MIT
At a glance
Delegates a focused piece of work to a DevSpace subagent through the devspace CLI, picking a target, writing a self-contained brief, and waiting on or continuing the resulting agent.
- Delegating a self-contained coding or research task to a specialist subagent
- SKILL.md covers Choose a target, Start work, Wait or inspect and Continue related work, plus 1 more section
- Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md
- Running several subagents in parallel and waiting for all of them to finish
What it does
Subagents are presented as optional: the normal workspace tools handle routine work, and delegation is reserved for tasks that benefit from independent context, a specialist profile, or a worker that can be followed up with later. A target is discovered rather than guessed by running devspace agents targets, which prints provider and profile fragments including a description, and a matching profile is preferred over a bare provider.
Starting work means writing a self-contained brief with the objective, relevant paths, constraints and expected result, since the subagent receives only that brief and its own profile instructions, not the parent conversation; devspace agents run returns a running agent's id. devspace agents wait blocks on one or more ids until they finish, or returns a timeout status per agent if a timeout is given, while show takes an immediate snapshot without polling. An existing agent can be continued with a follow-up brief when its provider context still helps, or a new one started for unrelated work.
When your agent uses it
- Delegating a self-contained coding or research task to a specialist subagent
- Running several subagents in parallel and waiting for all of them to finish
- Following up on a subagent's earlier work with a related brief
Example prompts
- “Delegate the database migration research to a subagent with research-oriented context.”
- “Run a review subagent on this PR and wait for its result.”
- “Continue agent agt_1234 with a follow-up to also check the error handling.”
Requirements
- The devspace CLI
What it can do on your machine
Read from SKILL.md and the folder at commit 531d3f9. 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 no API keys, tokens, secrets or passwords.
From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.
Context cost
DevSpace Subagent Delegation loads about 743 tokens when it runs. Until then it costs about 54 tokens; SKILL.md has 325 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 Waishnav/devspace at commit 531d3f9, republished under its MIT licence (© Waishnav). 325 words, ~743 tokens.
Download SKILL.mdSave it as
.claude/skills/subagents/SKILL.md (or your agent's skills folder).- name
- subagents
- description
- Delegate focused coding, research, review, or verification work to a bounded DevSpace subagent. Use when a task benefits from separate context, a specialist perspective, or a follow-up with the same worker.
DevSpace subagents
Subagents are optional. Use the normal workspace tools for routine work; delegate only when a separate worker materially helps through independent context, specialization, or follow-up.
Run the DevSpace CLI through the shell or process tool from the project the subagent should use. Agent commands print compact XML fragments by default. Read that output directly. Do not add --json.
Choose a target
Discover usable targets instead of guessing names:
devspace agents targetsEach line is a <provider name="..."/> or <profile name="..." provider="...">description</profile> fragment. Pass the profile or provider name as <profile-or-provider>. Prefer a matching profile. Use a provider target when no profile fits or the task needs a specific provider. Keep the configured model and effort unless the task requires a supported override.
Start work
Give the subagent a self-contained brief with the objective, relevant paths, constraints, context it cannot infer, and the expected result. The subagent receives this brief and its profile instructions, not the parent conversation.
devspace agents run <profile-or-provider> "<brief>"
devspace agents run <profile-or-provider> --model <model> --effort <effort> "<brief>"The command returns an <agent id="agt_..." status="running"/> receipt. Keep the DevSpace agent ID for inspection, waiting, or follow-up.
Wait or inspect
Use wait when work must finish before you proceed. One call can wait for several agents:
devspace agents wait <id>
devspace agents wait <id> <id> <id>
devspace agents wait <id> <id> --timeout 60Without --timeout, the command waits until every named agent's current work finishes. A timeout returns one fragment per unique agent in first-seen order; unfinished work has status="running" wait="timeout". Completed output is the element text. Failures include code and retryable attributes. The command does not stream partial results.
Use show for an immediate snapshot. Do not poll it when wait can express the dependency.
devspace agents show <id>
devspace agents lsls lists agents for the current project. Empty targets and ls results print nothing.
Continue related work
Continue an agent when its existing provider context helps. Start another agent for unrelated work.
devspace agents continue <id> "<follow-up brief>"
devspace agents wait <id>Good uses
- Review a change for correctness, security, or missing tests.
- Investigate a bounded part of a codebase and report findings.
- Implement one isolated change with clear acceptance criteria.
- Run a focused verification pass after other work.
© Waishnav, 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 skills/subagents of Waishnav/devspace.
Open the folder on GitHubat commit 531d3f9
Compare with similar skills
DevSpace Subagent Delegation 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 |
|---|---|---|---|---|---|---|
| DevSpace Subagent Delegation this skillWaishnav/devspace | 5.2k | — | ~743 | Automated safety check: Pass | MIT | |
| Claude Code Agent Developmentanthropics/claude-plugins-official | 38k | 8 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 | |
| Paseo Advisor Second Opiniongetpaseo/paseo | 20k | 1 repos | ~756 | Automated safety check: Pass | Custom licence | |
| Task Observerrebelytics/one-skill-to-rule-them-all | 3.2k | 1 repos | ~12k | Automated safety check: Pass | CC-BY-4.0 |
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
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.
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.
More from Waishnav/devspace
DevSpace Manual QA Setup
Waishnav/devspace
Prepares the current DevSpace checkout or worktree for isolated local manual QA, covering QA state seeding, UI asset builds and snapshot resets.
Related
Categories
Questions about DevSpace Subagent Delegation
What does DevSpace Subagent Delegation do?
Delegates a focused piece of work to a DevSpace subagent through the devspace CLI, picking a target, writing a self-contained brief, and waiting on or continuing the resulting agent. Subagents are presented as optional: the normal workspace tools handle routine work, and delegation is reserved for tasks that benefit from independent context, a specialist profile, or a worker that can be followed up with later. A target is discovered rather than guessed by running devspace agents targets, which prints provider and profile fragments including a description, and a matching profile is preferred over a bare provider.
When should I use DevSpace Subagent Delegation?
DevSpace Subagent Delegation fits situations like: delegating a self-contained coding or research task to a specialist subagent; running several subagents in parallel and waiting for all of them to finish; following up on a subagent's earlier work with a related brief.
How do I install DevSpace Subagent Delegation in Claude Code?
Run `npx skills add Waishnav/devspace --skill subagents -a claude-code`. Or copy the skill folder (skills/subagents in Waishnav/devspace) into .claude/skills/subagents in your project. Claude Code loads it when a task matches its description.
How do I install DevSpace Subagent Delegation in Codex?
Run `npx skills add Waishnav/devspace --skill subagents -a codex`. Or copy the skill folder (skills/subagents in Waishnav/devspace) into .agents/skills/subagents in your project. Codex loads it when a task matches its description.
Can I use DevSpace Subagent Delegation 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 Waishnav/devspace --skill 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/subagents, .gemini/skills/subagents, .github/skills/subagents and .opencode/skills/subagents in your project.
What does DevSpace Subagent Delegation need to run?
SKILL.md names no scripts, command-line tools or credentials: DevSpace Subagent Delegation is instructions for the agent only. Our summary lists: The devspace CLI.
Does DevSpace Subagent Delegation 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 DevSpace Subagent Delegation 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 DevSpace Subagent Delegation use?
DevSpace Subagent Delegation 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 DevSpace Subagent Delegation use?
About 743 tokens (SKILL.md is roughly 3k 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 DevSpace Subagent Delegation?
Skills that share tags, products or a category with DevSpace Subagent Delegation: 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 Paseo Advisor Second Opinion (getpaseo/paseo, 20k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
Who maintains DevSpace Subagent Delegation?
Waishnav (a GitHub user) maintains it in Waishnav/devspace, which has 5,210 GitHub stars. The repository holds 2 skills in this directory. The repository was last updated on October 7, 2026.
Source: Waishnav/devspace on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.