Skip to content
Agentmart
Submit a tool

run-agents

Runs a Gumloop agent, continues its session, checks a session, answers its approval requests, and fetches files it produced.

Skill by gumloop

IndexedMIT★ 3
Write a review

Chalk Labs

Need help deploying run-agents?

Chalk Labs sets up agents like this inside real teams: connected to your tools, tested on your data, with a human in the loop where it matters.

Book a call

Install

Works with Claude Code, Claude apps, Codex, Cursor, Gemini CLI, GitHub Copilot, VS Code, OpenCode, Goose, Windsurf. Read the repository before you give any tool access to your data.

npx agentmarket install skill/gumloop-run-agents

Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.

Get the weekly diff

The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.

We use your email only for this newsletter. Privacy

About

Runs a Gumloop agent, continues its session, checks a session, answers its approval requests, and fetches files it produced. Use when the user names one of their Gumloop agents, says "ask my agent" or "run the X agent", asks what an agent did or whether a run finished, or needs an agent's output file.

Use cases: agent-building

No reviews yet. Installed it? Reviews come from verified installers only. How reviews work

Permissions

What this skill can do and what it asks for, from its SKILL.md and code. Checked Oct 26, 2026.

Tools
No tools found
Secrets
None asked for
Install scripts
None found

Network hosts it talks to 1

  • codeload.github.com · found in install command

Files it touches

  • ~/.claude/skills/run-agents

What's inside

Skill name
run-agents
Description
Runs a Gumloop agent, continues its session, checks a session, answers its approval requests, and fetches files it produced. Use when the user names one of their Gumloop agents, says "ask my agent" or "run the X agent", asks what an agent did or whether a run finished, or needs an agent's output file.
License
MIT
Instructions
32 lines in SKILL.md · view on GitHub

Files (1)

  • SKILL.md

SKILL.md (first lines)

# Run agents

## Find the agent

`list_agents` with `search`. On several matches, ask. `get_agent` shows the model, system prompt, skills, and connected apps; use it to say what the agent will do before running it.

## Sessions

| Do | Tool | Note |
| --- | --- | --- |
| Start | `create_agent_session` (`agent_id`, `message`) | Returns the finished response. `input` carries structured inputs the agent declares. |
| Follow up | `send_session_message` (`session_id`, `message`) | |
| Check | `get_session` (`session_id`) | After a timeout, or for a session started in Gumloop, Slack, or by a trigger. |
| Stop | `cancel_session` | Ask first. |
| Rename | `rename_session` | |
| Browse | `list_agent_sessions` (`agent_id`) | `state` is one of `idle`, `queued`, `processing`, `approval_required`, `completed`, `failed`. |

Use sessions, not `start_agent` and `get_agent_status`.

## Approvals

State `approval_required` means the agent is waiting on a person. `get_session` lists the asks under `pending_approvals`. Show each ask (what, to whom) and wait for the user's answer. Then `resolve_session_approvals` with one entry per `action_request_id`: `action` `accept` or `reject`, `reason` on a rejection, `response.values` when the agent asked a question. Never accept for the user.

## Files

`list_agent_artifacts` (`agent_id`, optional `session_id`, `search_query`), then `download_artifact` (`artifact_id`) for a signed URL. Give the URL; don't fetch the file.

## Reply

Session ID, state, the agent's answer, artifact names with URLs.

From gumloop/gumloop-plugin, MIT.

Signals

Stars
3
Forks
1
Open issues
2
Last commit (this folder)
Oct 13, 2026 (17 days ago)

From GitHub (fetched Oct 24, 2026).

Details

License
MIT
First seen
Oct 24, 2026
Last checked
Oct 24, 2026

More from gumloop

Done for you

Rather not set it up yourself?

Chalk Labs scopes, builds and runs agents for your team: the task audit, the eval harness, the integrations and the weekly ops report. Fixed scope, priced before we start.

See how we build AI agents →Read the case studies

Chalk Labs is a two-founder AI and growth studio. We build AI agents, CRMs and MVPs for Web3 and AI companies, and have shipped 50+ product and token launches.

launches shipped
50+
launches shipped
media placements
500+
media placements
founders on every account
2
founders on every account

Press we've placed: Forbes · CoinDesk · Decrypt · Cointelegraph · The Block

Rahil Jain, Co-founder, Chalk Labs. Ex-Goldman Sachs engineer. You talk to the person who builds it.

Get run-agents running in your business

Tell us what you want to automate. A founder replies within one working day with a plan, not a pitch deck.

Goes to the Chalk Labs founders, not the newsletter. Privacy

Need help deploying run-agents?

CallGet help
Cite this page

run-agents skill. Agent Mart. https://agentmart.dev/skills/gumloop-run-agents (last updated 2026-10-24)