workshop docs: add gh-aw doc links (round 6) (#2718)

- side-quest-09-01f: link 'safe-output' → safe-outputs reference
- side-quest-10-02: link 'sandbox' → sandbox configuration reference
- side-quest-11-01: link 'agentic workflow' → introduction/overview
- side-quest-11-02: link 'agentic workflow' → introduction/overview
- side-quest-11-05: link 'schedule' → triggers/#scheduled-triggers-schedule
- side-quest-11-06: link 'agentic workflow' → introduction/overview

Co-authored-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>
Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>

Author: github-actions[bot]

workshop/side-quest-09-01f-debugging-checklist.md

@@ -24,7 +24,7 @@ You will apply a repeatable seven-step triage flow whenever a run produces unexp
 ## ✅ Checkpoint
 
 - [ ] I can run this checklist in order without skipping steps
-- [ ] I know where to find both live logs and safe-output records
+- [ ] I know where to find both live logs and [safe-output](https://github.github.com/gh-aw/reference/safe-outputs/) records
 - [ ] I can decide whether the root cause is prompt, data, [permissions](https://github.github.com/gh-aw/reference/permissions/), or output limits
 - [ ] I can gather a minimal log snippet to share for deeper diagnosis
 

workshop/side-quest-10-02-jailbreak-brief.md

@@ -40,7 +40,7 @@ gh-aw can combine five [defence layers](https://github.github.com/gh-aw/introduc
 
 - **[Compiled task brief](https://github.github.com/gh-aw/reference/compilation-process/#overview)** — The task brief is baked in before any data arrives. Issue bodies and PR descriptions reach the agent as structured tool call results, competing with an authoritative baseline rather than replacing it.
 - **Minimal `permissions:` + `safe-outputs`** — The `GITHUB_TOKEN` enforces declared permission boundaries; `safe-outputs` removes write tool paths that were never declared, so a jailbreak instruction to push a commit has no execution path.
-- **`network.allowed` + optional [agentic threat detection](https://github.github.com/gh-aw/reference/threat-detection/)** — The [network layer](https://github.github.com/gh-aw/reference/network/#configuration) blocks data exfiltration to unlisted endpoints; if you enable `threat-detection` under `safe-outputs:`, a separate detection job reviews agent output in an isolated sandbox before any declared write lands.
+- **`network.allowed` + optional [agentic threat detection](https://github.github.com/gh-aw/reference/threat-detection/)** — The [network layer](https://github.github.com/gh-aw/reference/network/#configuration) blocks data exfiltration to unlisted endpoints; if you enable `threat-detection` under `safe-outputs:`, a separate detection job reviews agent output in an isolated [sandbox](https://github.github.com/gh-aw/reference/sandbox/) before any declared write lands.
 
 <details>
 <summary>Detailed breakdown of each layer</summary>

workshop/side-quest-11-01-frontmatter-deep-dive.md

@@ -2,7 +2,7 @@
 <!-- page-adventure: side-quest -->
 # Side Quest: Frontmatter Deep Dive — Part A
 
-> _Optional: configure each of the opening three frontmatter sections of an agentic workflow file — metadata, triggers, and permissions. Work through this before building Step 11, then continue to [Part B: Tools, Outputs, and the Agent Body](side-quest-11-08-frontmatter-tools-outputs.md) or return to the main path._
+> _Optional: configure each of the opening three frontmatter sections of an [agentic workflow](https://github.github.com/gh-aw/introduction/overview/) file — metadata, triggers, and permissions. Work through this before building Step 11, then continue to [Part B: Tools, Outputs, and the Agent Body](side-quest-11-08-frontmatter-tools-outputs.md) or return to the main path._
 
 ## :clipboard: Before You Start
 

workshop/side-quest-11-02-yaml-frontmatter.md

@@ -4,7 +4,7 @@
 
 > _Optional: work through these common YAML mistakes if you hit a [compile error](https://github.github.com/gh-aw/reference/compilation-process/) in Step 11, then return to the main path._
 
-YAML is unforgiving. Here are the five errors learners hit most often when building agentic workflow [frontmatter](https://github.github.com/gh-aw/reference/frontmatter/), each with a broken :x: and correct :white_check_mark: example.
+YAML is unforgiving. Here are the five errors learners hit most often when building [agentic workflow](https://github.github.com/gh-aw/introduction/overview/) [frontmatter](https://github.github.com/gh-aw/reference/frontmatter/), each with a broken :x: and correct :white_check_mark: example.
 
 ---
 

workshop/side-quest-11-05-event-triggers.md

@@ -22,7 +22,7 @@ A **scheduled** workflow runs because the clock says it is time. An **event-driv
 | Scheduled | Time passes | Daily summaries, reminders, audits |
 | Event-driven | A GitHub event happens | PR review, issue triage, post-push follow-up |
 
-If you want the workflow to react to a specific repository action, use an event trigger. If you want it to run even when nobody touched the repo, use a schedule.
+If you want the workflow to react to a specific repository action, use an event trigger. If you want it to run even when nobody touched the repo, use a [schedule](https://github.github.com/gh-aw/reference/triggers/#scheduled-triggers-schedule).
 
 ## Four common trigger patterns
 

workshop/side-quest-11-06-anthropic-key.md

@@ -2,7 +2,7 @@
 <!-- page-adventure: side-quest -->
 # Side Quest: Configure an Anthropic API Key
 
-> _Optional: work through this guide when you want to use [Claude](side-quest-01-02-environment-reference.md#claude) (Anthropic's model family) as the AI engine for your agentic workflow, then return to your main path._
+> _Optional: work through this guide when you want to use [Claude](side-quest-01-02-environment-reference.md#claude) (Anthropic's model family) as the AI engine for your [agentic workflow](https://github.github.com/gh-aw/introduction/overview/), then return to your main path._
 
 By default, [agentic workflows](https://github.github.com/gh-aw/introduction/overview/) run on the [GitHub Copilot engine](https://github.github.com/gh-aw/reference/engines/). If you prefer to use **[Claude](https://github.github.com/gh-aw/reference/auth/#claude)**, you'll need an Anthropic API key stored as a repository secret and a one-line change to your [workflow frontmatter](https://github.github.com/gh-aw/reference/frontmatter/).