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.
Call nodetool.agents from a code action: hand a self-contained task to a sub-agent, fan several out in parallel, or start background sub-agents and collect their results later.
Install API Agents
$ npx skills add nodetool-ai/nodetool --skill api-agents -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install nodetool-ai/nodetool api-agents --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/nodetool-ai/nodetool.git skills-src && mkdir -p .claude/skills && cp -r skills-src/packages/system-skills/api-agents .claude/skills/api-agents && 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 "api-agents" agent skill from https://github.com/nodetool-ai/nodetool/tree/main/packages/system-skills/api-agents into .claude/skills/api-agents/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "api-agents", 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/nodetool-ai/nodetool/tree/main/packages/system-skills/api-agentsType 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 nodetool-ai/nodetool --skill api-agents -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install nodetool-ai/nodetool api-agents --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/nodetool-ai/nodetool.git skills-src && mkdir -p .agents/skills && cp -r skills-src/packages/system-skills/api-agents .agents/skills/api-agents && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "api-agents" agent skill from https://github.com/nodetool-ai/nodetool/tree/main/packages/system-skills/api-agents into .agents/skills/api-agents/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "api-agents", 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 nodetool-ai/nodetool --skill api-agents -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install nodetool-ai/nodetool api-agents --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/nodetool-ai/nodetool.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/packages/system-skills/api-agents .cursor/skills/api-agents && 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 "api-agents" agent skill from https://github.com/nodetool-ai/nodetool/tree/main/packages/system-skills/api-agents into .cursor/skills/api-agents/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "api-agents", 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/nodetool-ai/nodetool.git --path packages/system-skills/api-agents--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 nodetool-ai/nodetool --skill api-agents -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install nodetool-ai/nodetool api-agents --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/nodetool-ai/nodetool.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/packages/system-skills/api-agents .gemini/skills/api-agents && 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 "api-agents" agent skill from https://github.com/nodetool-ai/nodetool/tree/main/packages/system-skills/api-agents into .gemini/skills/api-agents/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "api-agents", 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 nodetool-ai/nodetool api-agentsInstalls 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 nodetool-ai/nodetool --skill api-agents -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/nodetool-ai/nodetool.git skills-src && mkdir -p .github/skills && cp -r skills-src/packages/system-skills/api-agents .github/skills/api-agents && 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 "api-agents" agent skill from https://github.com/nodetool-ai/nodetool/tree/main/packages/system-skills/api-agents into .github/skills/api-agents/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "api-agents", 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 nodetool-ai/nodetool --skill api-agents -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install nodetool-ai/nodetool api-agents --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/nodetool-ai/nodetool.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/packages/system-skills/api-agents .opencode/skills/api-agents && 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 "api-agents" agent skill from https://github.com/nodetool-ai/nodetool/tree/main/packages/system-skills/api-agents into .opencode/skills/api-agents/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "api-agents", 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
api-agents- GitHub stars
- 554
- Token cost
- ~638 tokens
- SKILL.md length
- 297 words
- Files
- 1
- Skills in repo
- 130
- Repo updated
- First seen
- Licence
- AGPL-3.0
At a glance
Call nodetool.agents from a code action: hand a self-contained task to a sub-agent, fan several out in parallel, or start background sub-agents and collect their results later.
- Tasks that involve Subagents
- SKILL.md covers Write the prompt for a stranger, When to delegate and Patterns
- Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md
What it does
API Agents is an agent skill from nodetool-ai/nodetool. Call nodetool.agents from a code action: hand a self-contained task to a sub-agent, fan several out in parallel, or start background sub-agents and collect their results later. Load before the first call into nodetool.agents.
Its SKILL.md is about 640 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: Agent-first Creative Workspace. The licence is AGPL-3.0.
When your agent uses it
- Tasks that involve Subagents
Example prompts
- “/api-agents”
What it can do on your machine
Read from SKILL.md and the folder at commit f99c652. 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 javascript).
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
API Agents loads about 638 tokens when it runs. Until then it costs about 59 tokens; SKILL.md has 297 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 nodetool-ai/nodetool at commit f99c652, republished under its AGPL-3.0 licence (© nodetool-ai). 297 words, ~638 tokens.
Download SKILL.mdSave it as
.claude/skills/api-agents/SKILL.md (or your agent's skills folder).- name
- api-agents
- description
- Call nodetool.agents from a code action: hand a self-contained task to a sub-agent, fan several out in parallel, or start background sub-agents and collect their results later. Load before the first call into nodetool.agents.
nodetool.agents
A sub-agent is a fresh agent loop with the same tools as you and none of this conversation. It answers with its final message as text.
| Call | Does | Answers |
|---|---|---|
run(prompt, {description}) | Runs a sub-agent and blocks until it finishes. | The final message of the sub-agent, as text |
start(prompt, {description}) | Starts a sub-agent and returns at once. | {subtask_id, status: "running"} |
wait({ids, timeoutMs}) | Blocks until the named sub-agents finish. Omit ids to wait for every one this turn started. timeoutMs is 1000–900000, default 300000. | Rows {subtask_id, status, result | error}. status is completed, failed, aborted, or running after a timeout. |
description is the 3–7 word label the user sees. Without it the first six
words of the prompt are used.
Write the prompt for a stranger
- Put everything the child needs in the prompt: the goal, the inputs (ids, uris, the text), the constraints, and what to return.
- Ask for the answer shape you want: "reply as JSON with fields title, url, summary". Parse the text you get back.
- Pass ids and
asset://uris, not descriptions of them. The child can read them with its own tools.
When to delegate
Delegate work that gains from a fresh, focused context: research one question end to end, draft a self-contained section, review a result against a brief. Do not delegate a single tool call. A sub-agent costs real time and money.
Patterns
Parallel, blocking — one settled entry per prompt:
const answers = await nodetool.batch(prompts, (p) => nodetool.agents.run(p),
{ concurrency: 4 });Background — start, do other work, then collect in the same action:
const a = await nodetool.agents.start(researchPrompt, { description: "Research competitors" });
const draft = await draftOutline(); // your own work meanwhile
const [row] = await nodetool.agents.wait({ ids: [a.subtask_id] });Results of a sub-agent you never wait for are lost to the turn. Always wait for what you need before the action ends.
Sub-agents can start sub-agents of their own, up to a depth limit. Results
they publish with nodetool.shared.publish are readable by the parent in the
same run (see api-memory).
© nodetool-ai, AGPL-3.0. 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 packages/system-skills/api-agents of nodetool-ai/nodetool.
Open the folder on GitHubat commit f99c652
Compare with similar skills
API Agents 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 |
|---|---|---|---|---|---|---|
| API Agents this skillnodetool-ai/nodetool | 554 | — | ~638 | Automated safety check: Pass | AGPL-3.0 | |
| Claude Code Agent Developmentanthropics/claude-plugins-official | 37k | 8 repos | ~2.8k | Automated safety check: Pass | Apache-2.0 | |
| Subagent Driven DevelopmentAsvarox/allkaraoke | 261 | 37 repos | ~1.2k | Automated safety check: Pass | None | |
| Dispatching Parallel Agentsultralisp/ultralisp | 258 | 40 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 nodetool-ai/nodetool
All 130 skills in this repoBeat Sync Editing
nodetool-ai/nodetool
Cut a NodeTool timeline to music and shape its pacing — detect the beat grid, place cuts on phrases, pick a cut type, build speed ramps with time remap, and give the piece an arc.
Caption Titles
nodetool-ai/nodetool
Add and animate a consistent text layer on an existing NodeTool timeline.
Color Motion
nodetool-ai/nodetool
Choose and animate colour on a NodeTool timeline, including shape and text gradients, colour grades, 3D LUTs, and dither.
Commercial Beat Sheet
nodetool-ai/nodetool
Write a shootable, precisely timed commercial beat sheet and store it as a NodeTool storyboard, with a consistent entity roster behind every shot.
Elevenlabs Audio Prompting
nodetool-ai/nodetool
Direct ElevenLabs speech, dialogue, sound effects and music — the bracketed audio tags v3 acts on and why the voice decides whether a tag lands, stability as the delivery dial, punctuation instead…
Frame Composition
nodetool-ai/nodetool
Stage the frame on a NodeTool timeline — grids, focal placement, safe areas per aspect ratio, depth layers and parallax, camera moves, and where elements enter and leave.
Related
Categories
Questions about API Agents
What does API Agents do?
Call nodetool.agents from a code action: hand a self-contained task to a sub-agent, fan several out in parallel, or start background sub-agents and collect their results later. API Agents is an agent skill from nodetool-ai/nodetool.agents from a code action: hand a self-contained task to a sub-agent, fan several out in parallel, or start background sub-agents and collect their results later.
When should I use API Agents?
API Agents fits situations like: tasks that involve Subagents.
How do I install API Agents in Claude Code?
Run `npx skills add nodetool-ai/nodetool --skill api-agents -a claude-code`. Or copy the skill folder (packages/system-skills/api-agents in nodetool-ai/nodetool) into .claude/skills/api-agents in your project. Claude Code loads it when a task matches its description.
How do I install API Agents in Codex?
Run `npx skills add nodetool-ai/nodetool --skill api-agents -a codex`. Or copy the skill folder (packages/system-skills/api-agents in nodetool-ai/nodetool) into .agents/skills/api-agents in your project. Codex loads it when a task matches its description.
Can I use API Agents 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 nodetool-ai/nodetool --skill api-agents -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/api-agents, .gemini/skills/api-agents, .github/skills/api-agents and .opencode/skills/api-agents in your project.
What does API Agents need to run?
SKILL.md names no scripts, command-line tools or credentials: API Agents is instructions for the agent only.
Does API Agents 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 API Agents 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 API Agents use?
API Agents is published under the AGPL-3.0 licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.
How many tokens does API Agents use?
About 638 tokens (SKILL.md is roughly 2.6k 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 API Agents?
Skills that share tags, products or a category with API Agents: Claude Code Agent Development (anthropics/claude-plugins-official, 37k 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 API Agents?
nodetool-ai (a GitHub organization) maintains it in nodetool-ai/nodetool, which has 554 GitHub stars. The repository holds 130 skills in this directory. The repository was last updated on October 7, 2026.
Source: nodetool-ai/nodetool on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.