> ## Documentation Index
> Fetch the complete documentation index at: https://docs.bellows.cloud/llms.txt
> Use this file to discover all available pages before exploring further.

# Glossary

> Every term you meet in the Bellows app, CLI and docs, in alphabetical order.

For a guided tour of the main ideas, read [Core concepts](https://docs.bellows.cloud/overview/concepts.md) first.

## A

**Agent.** The coding model that edits your code in a run. In Bellows it is chosen through an [executor](https://docs.bellows.cloud/guides/executors.md).

**Attachment.** A screenshot, PDF or other file you add to a task or follow-up so the agent can work from it. See [Attachments](https://docs.bellows.cloud/guides/attachments.md).

## B

**Base branch.** The branch a task starts from and its pull request targets. You can pick it in the task composer. Bellows reads `.bellows.yaml` from its tip. See [Policy and reviewers](https://docs.bellows.cloud/guides/policy-and-reviewers.md).

## C

**Connection.** A stored third-party credential, such as Jira, that you attach to a task so the agent can use it. See [Connections](https://docs.bellows.cloud/guides/connections.md).

## D

**Driver.** The part of Bellows that picks up queued jobs and starts a runner for each one. See [Introduction](https://docs.bellows.cloud/overview/introduction.md).

## E

**Evidence.** What a [policy](https://docs.bellows.cloud/guides/policy-and-reviewers.md) requires before Bellows publishes work: a passing full gate run, a clean review, or both. Without it the task fails with `evidence required`.

**Executor.** The coding agent that does the work: Claude Code, OpenCode, or a custom profile built on them. See [Executors](https://docs.bellows.cloud/guides/executors.md).

**Executor profile.** A saved executor setup with a name, an agent, a model and optional configuration. It is personal (only you) or organization-wide (every member). See [Executors](https://docs.bellows.cloud/guides/executors.md).

## F

**Failure kind.** The reason shown on a failed run, such as `timed out`, `gate failed` or `config error`. Each one is explained in [Task lifecycle](https://docs.bellows.cloud/guides/task-lifecycle.md#when-a-run-fails).

**Follow-up.** Your next message on a finished task. It starts a new job on the same checkout and session. See [Run tasks](https://docs.bellows.cloud/guides/run-tasks.md).

## G

**Gate.** A named check command in `.bellows.yaml`, such as build, test or lint. A run succeeds only if its gates pass. See [Gates](https://docs.bellows.cloud/guides/gates.md).

**Gate filter.** A `filter: true` gate that lets the agent run part of a suite. The value reaches your command as `$GATE_FILTER`. A filtered run never counts as proof. See [Gates](https://docs.bellows.cloud/guides/gates.md#filters).

**Gate repair.** The automatic rounds in which the agent gets a failing gate's output and tries to fix it. The limit is the executor's **Gate repair rounds** setting. See [Gates](https://docs.bellows.cloud/guides/gates.md#when-a-gate-fails).

## I

**Inbox.** The **Tasks** page. Its **Needs attention** tab holds everything waiting on you: answers, reviews and failures. See [Run tasks](https://docs.bellows.cloud/guides/run-tasks.md#the-inbox).

## J

**Job.** One attempt by the agent inside a task. Also called a **run**. Follow-ups, answers, retries and edits each start a new job. See [Task lifecycle](https://docs.bellows.cloud/guides/task-lifecycle.md).

## M

**Mark done.** Closes a task in Bellows. It does not merge or close the pull request. **Reopen** brings the task back.

**MCP.** Model Context Protocol. The Bellows MCP server lets an assistant such as Claude Code create and follow tasks for you. See [Connect an MCP client](https://docs.bellows.cloud/mcp/connect.md).

## N

**Needs attention.** The inbox tab for tasks waiting on you. See **Inbox**.

## O

**On-demand gate.** A gate marked `on_demand: true`. The agent can run it while it works. The end-of-run pass skips it, and it never fails the task. See [Gates](https://docs.bellows.cloud/guides/gates.md#on-demand-gates).

**Organization.** One Bellows GitHub App installation. It owns the repository list and keeps its data apart from other organizations. See [Core concepts](https://docs.bellows.cloud/overview/concepts.md).

**Organization access token.** A token with the `oat_` prefix. It is read-only and meant for automation that should outlive any member. See [Install and sign in](https://docs.bellows.cloud/cli/install.md#token-types).

## P

**Personal access token.** A token with the `fat_` prefix that acts as you in the CLI. You create it on your **Account** page. See [Install and sign in](https://docs.bellows.cloud/cli/install.md).

**Policy.** The `policy` block in `.bellows.yaml`. It requires passing gates, a review, or both before work is published. See [Policy and reviewers](https://docs.bellows.cloud/guides/policy-and-reviewers.md).

**Preflight.** An advisory check of a task selection (repository, executor, skills, connections) that creates nothing. Use `bellows job preflight` or the `preflight_task` MCP tool. The server checks again when you create the task.

## Q

**Question.** The agent asking you something mid-run. The task shows **Needs answer** until you answer. See [Run tasks](https://docs.bellows.cloud/guides/run-tasks.md).

## R

**Repository.** A GitHub repository tracked by Bellows. You choose which ones under **Settings → Repositories**. See [Configure your repo](https://docs.bellows.cloud/guides/configure-repo.md).

**Reviewer.** A separate agent run, declared under `reviewers` in `.bellows.yaml`, that reviews the work and returns a verdict of `clean` or `blockers`. See [Policy and reviewers](https://docs.bellows.cloud/guides/policy-and-reviewers.md#reviewers).

**Run.** See **Job**.

**Runner.** The container your `.bellows.yaml` describes. The agent works and the gates run there. See [Introduction](https://docs.bellows.cloud/overview/introduction.md).

## S

**Secret.** An environment value that is write-only after you save it. The opposite is a **variable**, which stays readable. See [Environment variables and secrets](https://docs.bellows.cloud/guides/env-and-secrets.md).

**Service.** A sidecar container, such as Postgres or Redis, that runs next to the agent so tests have something to talk to. See [Services](https://docs.bellows.cloud/guides/services.md).

**Setup.** The `setup` command in `.bellows.yaml`. It runs before the agent starts and is retried while it fails. See [Configure your repo](https://docs.bellows.cloud/guides/configure-repo.md).

**Skill.** A versioned bundle of instructions (`SKILL.md`) the agent can load. Call one from a task with a `/`. See [Skills](https://docs.bellows.cloud/guides/skills.md).

## T

**Task.** One thread of work: your request and everything that follows it. A task holds one or more jobs. See [Task lifecycle](https://docs.bellows.cloud/guides/task-lifecycle.md).

## V

**Variable.** An environment value that stays visible after saving. Set at the organization, workspace or repository level. See [Environment variables and secrets](https://docs.bellows.cloud/guides/env-and-secrets.md).

**Verification.** The panel on a task page that lists each gate with its result, exit code and output. See [Gates](https://docs.bellows.cloud/guides/gates.md#where-results-show).

## W

**Workspace.** Your personal scope in Settings, shown as **Workspace** (and **My workspace** for executors). Things set there apply only to you. The task's own checkout is also called its workspace. See [Environment variables and secrets](https://docs.bellows.cloud/guides/env-and-secrets.md).


This documentation is built and hosted on [Mintlify](https://mintlify.com), a developer documentation platform.