Agent Squad for TypeScript
2FastLabs/agent-squad
Guide to building Node.js and TypeScript apps on the agent-squad package: orchestrator, agent types, classifier routing, storage, retrievers and MCP tools.
Patterns for building LLM agents on Trigger.dev tasks: prompt chaining, routing, parallel workers, orchestrator-workers, evaluator loops and human approval gates.
Install Trigger.dev Agent Patterns
$ npx skills add papermark/papermark --skill trigger-agents -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install papermark/papermark trigger-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/papermark/papermark.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.agents/skills/trigger-agents .claude/skills/trigger-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 "trigger-agents" agent skill from https://github.com/papermark/papermark/tree/main/.agents/skills/trigger-agents into .claude/skills/trigger-agents/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "trigger-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/papermark/papermark/tree/main/.agents/skills/trigger-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 papermark/papermark --skill trigger-agents -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install papermark/papermark trigger-agents --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/papermark/papermark.git skills-src && mkdir -p .agents/skills && cp -r skills-src/.agents/skills/trigger-agents .agents/skills/trigger-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 "trigger-agents" agent skill from https://github.com/papermark/papermark/tree/main/.agents/skills/trigger-agents into .agents/skills/trigger-agents/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "trigger-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 papermark/papermark --skill trigger-agents -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install papermark/papermark trigger-agents --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/papermark/papermark.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/.agents/skills/trigger-agents .cursor/skills/trigger-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 "trigger-agents" agent skill from https://github.com/papermark/papermark/tree/main/.agents/skills/trigger-agents into .cursor/skills/trigger-agents/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "trigger-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/papermark/papermark.git --path .agents/skills/trigger-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 papermark/papermark --skill trigger-agents -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install papermark/papermark trigger-agents --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/papermark/papermark.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/.agents/skills/trigger-agents .gemini/skills/trigger-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 "trigger-agents" agent skill from https://github.com/papermark/papermark/tree/main/.agents/skills/trigger-agents into .gemini/skills/trigger-agents/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "trigger-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 papermark/papermark trigger-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 papermark/papermark --skill trigger-agents -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/papermark/papermark.git skills-src && mkdir -p .github/skills && cp -r skills-src/.agents/skills/trigger-agents .github/skills/trigger-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 "trigger-agents" agent skill from https://github.com/papermark/papermark/tree/main/.agents/skills/trigger-agents into .github/skills/trigger-agents/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "trigger-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 papermark/papermark --skill trigger-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 papermark/papermark trigger-agents --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/papermark/papermark.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/.agents/skills/trigger-agents .opencode/skills/trigger-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 "trigger-agents" agent skill from https://github.com/papermark/papermark/tree/main/.agents/skills/trigger-agents into .opencode/skills/trigger-agents/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "trigger-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
trigger-agents- GitHub stars
- 9.2k
- Token cost
- ~2k tokens
- SKILL.md length
- 128 words
- Files
- 5 (incl. references)
- Skills in repo
- 6
- Repo updated
- First seen
- Licence
- Custom licence
At a glance
Patterns for building LLM agents on Trigger.dev tasks: prompt chaining, routing, parallel workers, orchestrator-workers, evaluator loops and human approval gates.
- Works in 5 steps: Prompt Chaining (Sequential with Gates) → Routing (Classify → Dispatch) → Parallelization → …
- Building an LLM task that fans work out to parallel workers
- SKILL.md covers Pattern Selection, Core Patterns, Trigger-Specific Features and Error Handling, plus 1 more section
- Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md
What it does
The skill is a pattern guide for AI agents built on Trigger.dev's durable task execution. A selection table maps needs to patterns, followed by TypeScript examples for prompt chaining with validation gates, routing where a cheap model classifies the input before dispatch, parallelization with `batch.triggerByTaskAndWait`, orchestrator-workers with fan-out and fan-in, and an evaluator-optimizer loop that retries with feedback until a result is approved.
Trigger-specific features are covered in reference files: waitpoints for human approval gates and external callbacks, streams for live progress to a frontend, `ai.tool` for letting an LLM call your tasks as tools, and orchestration details for typed parallel runs. An error-handling section shows checking each run's result, and a quick reference lists common calls such as `triggerAndWait`. The examples use the `ai` package with `@ai-sdk/openai`, and the excerpt is cut off inside the quick reference.
When your agent uses it
- Building an LLM task that fans work out to parallel workers
- Adding a human approval step before an agent continues
- Routing requests to different handlers after a cheap classification step
- Letting an LLM call existing Trigger.dev tasks as tools
Example prompts
- “Build a Trigger.dev task that classifies support tickets and routes each one to a billing or technical handler.”
- “Add an approval gate to this content-publishing agent using waitpoints.”
- “Refactor this report generator into an orchestrator that fans out one worker per section.”
- “Make a translation task that evaluates its own output and retries with feedback until it passes.”
Requirements
- A Trigger.dev project using the @trigger.dev/sdk package
- The `ai` and `@ai-sdk/openai` packages used by the examples
Workflow steps
5 steps, taken from the step headings in SKILL.md.
- Prompt Chaining (Sequential with Gates)
- Routing (Classify → Dispatch)
- Parallelization
- Orchestrator-Workers (Fan-out/Fan-in)
- Evaluator-Optimizer (Self-Refining Loop)
What it can do on your machine
Read from SKILL.md and the folder at commit ed19717. 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 typescript).
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
Trigger.dev Agent Patterns loads about 2k tokens when it runs, and up to ~7.5k if it reads all its reference files. Until then it costs about 65 tokens; SKILL.md has 128 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
Its licence (Custom licence) doesn't allow us to republish the file, so here is its outline and opening line. It has 128 words (~1,999 tokens).
“Build production-ready AI agents using Trigger.dev's durable execution.”
- name
- trigger-agents
Files
SKILL.md and 4 other files (references) in .agents/skills/trigger-agents of papermark/papermark.
- SKILL.md
- references/ai-tool.md
- references/orchestration.md
- references/streaming.md
- references/waitpoints.md
Open the folder on GitHubat commit ed19717
Compare with similar skills
Trigger.dev Agent Patterns 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 |
|---|---|---|---|---|---|---|
| Trigger.dev Agent Patterns this skillpapermark/papermark | 9.2k | — | ~2k | Automated safety check: Pass | Custom licence | |
| Agent Squad for TypeScript2FastLabs/agent-squad | 7.8k | — | ~4.3k | Automated safety check: Pass | Apache-2.0 | |
| Agent Squad Python Guide2FastLabs/agent-squad | 7.8k | — | ~4.7k | Automated safety check: Pass | Apache-2.0 | |
| Add Example AgentGetBindu/Bindu | 10k | — | ~1.1k | Automated safety check: Notes | Custom licence | |
| AgentSquad for Swift2FastLabs/agent-squad | 7.8k | — | ~3.5k | Automated safety check: Pass | Apache-2.0 | |
| Dive Into LangGraphluochang212/dive-into-langgraph | 457 | — | ~837 | Automated safety check: Notes | Custom licence |
Similar skills
Agent Squad Python Guide
2FastLabs/agent-squad
Map of the agent-squad Python framework for async multi-agent orchestration: which agent, classifier, storage and tool provider to pick, and the pitfalls to avoid.
Add Example Agent
GetBindu/Bindu
Add a new self-contained example agent under examples/. An agent skill from GetBindu/Bindu.
AgentSquad for Swift
2FastLabs/agent-squad
Guides building on-device multi-agent apps in Swift with the AgentSquad framework: which agent, orchestrator, classifier, storage or voice type fits each situation.
Dive Into LangGraph
luochang212/dive-into-langgraph
A Chinese-language guide and reference for building agents with LangGraph 1.0, from a first ReAct agent through middleware, memory, MCP, RAG and web search.
- Official
Langgraph Human In The Loop
langchain-ai/langchain-skills
INVOKE THIS SKILL when implementing human-in-the-loop patterns, pausing for approval, or handling errors in LangGraph.
More from papermark/papermark
Trigger.dev Configuration
papermark/papermark
Configures Trigger.dev projects through trigger.config.ts, with build extensions for Prisma, Playwright, Puppeteer, FFmpeg, Python and system packages.
Trigger.dev Cost Savings Audit
papermark/papermark
Audits Trigger.dev tasks, schedules and run history for wasteful machine sizes, retries, polling and cron frequency to cut spend.
Trigger.dev Realtime
papermark/papermark
Shows how to subscribe to Trigger.dev task runs from the backend and from React for progress indicators, live dashboards, AI response streams and approval waits.
Trigger.dev Background Tasks
papermark/papermark
Guides building durable background tasks, scheduled jobs and queues with Trigger.dev, including retries, waits, idempotency and concurrency limits.
GitHub CLI Reference
papermark/papermark
Reference for the gh command line tool covering repositories, issues, pull requests, Actions, releases, gists and codespaces, with install and login steps.
Related
Works with
Categories
Questions about Trigger.dev Agent Patterns
What does Trigger.dev Agent Patterns do?
Patterns for building LLM agents on Trigger.dev tasks: prompt chaining, routing, parallel workers, orchestrator-workers, evaluator loops and human approval gates. dev's durable task execution.triggerByTaskAndWait`, orchestrator-workers with fan-out and fan-in, and an evaluator-optimizer loop that retries with feedback until a result is approved.
When should I use Trigger.dev Agent Patterns?
Trigger.dev Agent Patterns fits situations like: building an LLM task that fans work out to parallel workers; adding a human approval step before an agent continues; routing requests to different handlers after a cheap classification step; letting an LLM call existing Trigger.dev tasks as tools.
How do I install Trigger.dev Agent Patterns in Claude Code?
Run `npx skills add papermark/papermark --skill trigger-agents -a claude-code`. Or copy the skill folder (.agents/skills/trigger-agents in papermark/papermark) into .claude/skills/trigger-agents in your project. Claude Code loads it when a task matches its description.
How do I install Trigger.dev Agent Patterns in Codex?
Run `npx skills add papermark/papermark --skill trigger-agents -a codex`. Or copy the skill folder (.agents/skills/trigger-agents in papermark/papermark) into .agents/skills/trigger-agents in your project. Codex loads it when a task matches its description.
Can I use Trigger.dev Agent Patterns 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 papermark/papermark --skill trigger-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/trigger-agents, .gemini/skills/trigger-agents, .github/skills/trigger-agents and .opencode/skills/trigger-agents in your project.
What does Trigger.dev Agent Patterns need to run?
SKILL.md names no scripts, command-line tools or credentials: Trigger.dev Agent Patterns is instructions for the agent only. Our summary lists: A Trigger.dev project using the @trigger.dev/sdk package; The `ai` and `@ai-sdk/openai` packages used by the examples.
Does Trigger.dev Agent Patterns 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 Trigger.dev Agent Patterns 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 Trigger.dev Agent Patterns use?
Trigger.dev Agent Patterns 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 Trigger.dev Agent Patterns use?
About 2k tokens (SKILL.md is roughly 8k 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 5.5k tokens, read only when the agent opens those files.
What are the alternatives to Trigger.dev Agent Patterns?
Skills that share tags, products or a category with Trigger.dev Agent Patterns: Agent Squad for TypeScript (2FastLabs/agent-squad, 7.8k stars), Agent Squad Python Guide (2FastLabs/agent-squad, 7.8k stars), Add Example Agent (GetBindu/Bindu, 10k stars) and AgentSquad for Swift (2FastLabs/agent-squad, 7.8k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
Who maintains Trigger.dev Agent Patterns?
papermark (a GitHub organization) maintains it in papermark/papermark, which has 9,242 GitHub stars. The repository holds 6 skills in this directory. The repository was last updated on August 28, 2026.
Source: papermark/papermark on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.