GitHub Issues backlog agent

The GitHub Issues backlog agent reads every open GitHub issue labelled agent-ready, implements the dbt™ models each one needs with tests and YAML docs, opens one PR per issue, and posts the link to Slack. It is a single YAML file in your repo, triggered on a schedule by Bolt: no custom Python, SDK glue, or orchestrator.

Prerequisites

Slack connected (the agent posts status updates to its configured channel via post_slack_message).
Your repository connected so the agent can branch, commit, and open PRs.
Familiarity with programmable agents and running an agent with Bolt.
Issues to automate must be open and carry the label agent-ready.

Estimated time: 20 minutes.

Steps

Create the agent

Build the agent in the Agent UI (start from the github-backlog-agent template), or commit this file at .dinoai/agents/github-backlog-agent.yml:

.dinoai/agents/github-backlog-agent.yml

name: github-backlog-agent
version: 1

role: >
  Analytics Engineer turning GitHub issues into well-scoped dbt model PRs,
  using the gh CLI.

goal: >
  For each open GitHub issue labelled "agent-ready" — or the specific issue
  number in the trigger message: read it, implement the dbt
  models it needs (staging, plus a mart where appropriate) with tests and YAML
  docs on a new branch, open a PR that closes the issue, and post the PR link
  to Slack. One branch and one PR per issue. Skip any issue that already has an
  open PR.

backstory: >
  You never invent a column that isn't in the source. When an issue is
  ambiguous, you flag it under "Open questions" in the PR instead of guessing.
  You follow the project's dinorules conventions and implement everything
  yourself — no delegation.

tools:
  mode: allowlist
  list:
    - read_file
    - write_file
    - replace_in_file
    - search_files_and_directories
    - ripgrep_search
    - run_sql_query
    - run_terminal_command
    - post_slack_message

slack:
  channel: "#analytics-eng"

tools.mode: allowlist means the agent can call only the tools listed, which keeps each session focused. Update slack.channel before committing if your team uses a different channel.

Commit the agent to your repo

Commit the YAML to the git branch your Bolt schedule runs against (for example main):

git add .dinoai/agents/github-backlog-agent.yml
git commit -m "Add github-backlog-agent"
git push

The agent now appears in the Agent Name dropdown when you configure a Bolt command. The list is populated from .dinoai/agents/*.yml on the configured branch.

Run it with Bolt

Trigger the agent from a Bolt schedule using the Run Paradime DinoAI Agent command. See Run an agent with Bolt for the full walkthrough.Pick github-backlog-agent as the Agent Name, then set the Task, the agent’s opening message. For a full backlog sweep:

Find every open GitHub issue labelled agent-ready. For each one: read it, implement the required dbt models with tests and YAML docs on a new branch, open a PR with Closes #<number>.

If you manage schedules as YAML, the command is a single paradime dinoai invocation:

schedules:
  - name: github backlog agent
    slug: github-backlog-agent-l3m4n5
    description: "Sweep open Agent Ready GitHub issues into dbt PRs"
    owner_email: data-team@acme.io
    environment: production
    git_branch: main
    commands:
      - >-
        paradime dinoai --agent="github-backlog-agent" --message="Find
        every open GitHub issue labelled agent-ready. For each one: read it,
        implement the required dbt models with tests and YAML docs on a new branch,
        open a PR with Closes #<number>."
    schedule: "0 9 * * 1-5"
    timezone: UTC

UI field	CLI flag	Notes
Agent Name	`--agent=<name>`	Must match an existing `.dinoai/agents/<name>.yml` on the schedule’s branch.
Task	`--message="<task>"`	The agent’s opening user message. Use a single quoted string.

Choose a schedule frequency

Pick the cadence that matches how often your team labels new issues as agent-ready:

Cadence	Cron expression	When it runs
Every day at 9 AM	`0 9 * * *`	Monday–Sunday, 9:00 AM
Weekdays at 9 AM	`0 9 * * 1-5`	Monday–Friday, 9:00 AM
Once a week (Monday 9 AM)	`0 9 * * 1`	Every Monday, 9:00 AM
Twice a week (Mon & Thu)	`0 9 * * 1,4`	Monday and Thursday, 9:00 AM
Every 6 hours	`0 /6 * *`	12 AM, 6 AM, 12 PM, 6 PM

For most teams, weekdays at 9 AM (0 9 * * 1-5) is a good default. If there are no Agent Ready issues, the agent reports an empty backlog and the run completes cleanly.

After a run, each open agent-ready issue has one PR that closes it, and its link is posted to your Slack channel. When an issue already has an open PR, the agent skips it. Review the PRs, resolve any Open questions the agent flagged, and merge.

How it works

Bolt runs a single paradime dinoai command on your chosen cadence. That spins up one agent pod with a task message telling it to process the agent-ready backlog. The agent lists the issues, creates a branch and implements each one, pushes, opens a PR, then posts to Slack. Bolt blocks until the agent reaches a terminal state and inherits its success or failure, and the agent’s messages stream into the Bolt run logs. The only file you author lives in your repo:

your-repo/
├── dbt_project.yml
└── .dinoai/
    └── agents/
        └── github-backlog-agent.yml

Everything else (triggering, polling, notifications) is handled natively by Bolt and the agent runtime.

Next steps

Linear backlog agent

The same pattern, fanned out one session per Linear ticket.

Jira backlog agent

A single-session variant for a Jira backlog.

Run an agent with Bolt

Trigger agents from a Bolt schedule.

Programmable Agents reference

The agent YAML schema and tools.

Foundations

Automate with AI agents

Set up & configure

Orchestrate data pipelines

Migrate to Paradime

Develop in Paradime

Learn dbt™

GitHub Issues backlog agent

Steps

How it works

Next steps

Linear backlog agent

Jira backlog agent

Run an agent with Bolt

Programmable Agents reference

​Steps

​How it works

​Next steps

Linear backlog agent

Jira backlog agent

Run an agent with Bolt

Programmable Agents reference

Steps

How it works

Next steps