> For the complete documentation index, see [llms.txt](https://learn.heeler.com/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://learn.heeler.com/tenant-admin-guide/program/agent-pr-template.md).

# Agent PR Template

## Customizing the Pull Request Body Heeler's Agent Opens

When Heeler's remediation agent opens a fix pull request, the body of that PR uses a template you control. The **Agent PR Template** page is where you paste in your repo's `pull_request_template.md` content (or any other content you want appended) so the PRs match your team's conventions.

### Where to find it

Administration → **Program** → **Agent PR Template** in the left sidebar.

URL: `https://app.heeler.com/administration/program/agent_pr_template`

### Quick start

1. Paste the content you want included in every agent-opened PR into the textarea. Markdown is supported. The page has a 5,000-character limit.
2. Choose whether to **Append agent conversation history** to the bottom (default: on). This is useful for auditability.
3. Choose whether to **Append Heeler footer linking back to the finding and scan details in Heeler** (default: on). This makes reviewers one click away from the full context.
4. Click **Save**.

From the next agent-opened PR onward, this template is used.

### Reference

#### Page elements

| Element                                                                         | Description                                                                                                                                    |
| ------------------------------------------------------------------------------- | ---------------------------------------------------------------------------------------------------------------------------------------------- |
| **Template textarea**                                                           | Up to 5,000 characters. Markdown. This content becomes the body of agent-opened PRs (typically before any auto-generated remediation details). |
| **Character counter**                                                           | Shown above the textarea (`N / 5000 characters`).                                                                                              |
| **Append agent conversation history**                                           | Toggle. When on, the agent's reasoning trace and conversation are appended to the bottom of the PR. Recommended for auditable workflows.       |
| **Append Heeler footer linking back to the finding and scan details in Heeler** | Toggle. When on, a Heeler footer with a link to the originating finding is appended. Recommended so reviewers can verify the fix in context.   |
| **Save**                                                                        | Persists the template. Disabled when no changes have been made.                                                                                |

#### Tips

* **Match your existing PR template.** If your repos have a `pull_request_template.md`, copy/paste it here so agent PRs look like any other PR.
* **Use placeholders sparingly.** The agent's auto-generated content already includes finding details, severity, and a summary of the fix. Your template should focus on team norms (checklists, reviewer @-mentions, etc.) rather than restating finding metadata.

### Related documentation

* Auto-Fix (Deterministic Agentic Remediation) — overview of agentic remediation
* Eliminating Dependency Debt at Scale with Agentic Remediation
* Agent Executions — view history of agent runs


---

# Agent Instructions
This documentation is published with GitBook. GitBook is the documentation platform designed so that both humans and AI agents can read, navigate, and reason over technical content effectively. Learn more at gitbook.com.

## Querying This Documentation
If you need additional information that is not directly available in this page, you can query the documentation dynamically by asking a question.

Perform an HTTP GET request on the current page URL with the `ask` query parameter:

```
GET https://learn.heeler.com/tenant-admin-guide/program/agent-pr-template.md?ask=<question>
```

The question should be specific, self-contained, and written in natural language.
The response will contain a direct answer to the question and relevant excerpts and sources from the documentation.

Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.