docs: add responsible AI agent use & token-budget guide

.github/workflows/build-merged-website.yml

@@ -0,0 +1,63 @@
+name: Build Merged Website
+
+# Builds the website with skills and guides merged from this repo plus an
+# additional repo (e.g. an internal mirror), then uploads the static site
+# as a dist.tar.gz artifact.
+
+on:
+  workflow_dispatch:
+    inputs:
+      extra_repo:
+        description: 'Additional repo to merge (owner/name)'
+        required: true
+        default: 'absa-group/agentic-toolkit'
+      extra_ref:
+        description: 'Branch or tag of the additional repo'
+        required: true
+        default: 'main'
+
+permissions:
+  contents: read
+
+jobs:
+  build:
+    runs-on: ubuntu-latest
+    steps:
+      - uses: actions/checkout@v4
+
+      # Checked out via the Actions token (or EXTRA_REPO_TOKEN secret for
+      # private cross-org repos) so no credentials end up in clone URLs.
+      - name: Checkout extra repo
+        uses: actions/checkout@v4
+        with:
+          repository: ${{ inputs.extra_repo }}
+          ref: ${{ inputs.extra_ref }}
+          path: website/.external/extra
+          token: ${{ secrets.EXTRA_REPO_TOKEN || github.token }}
+
+      - uses: actions/setup-node@v4
+        with:
+          node-version: 22
+
+      - name: Install dependencies
+        working-directory: website
+        run: npm install
+
+      - name: Build merged website
+        working-directory: website
+        env:
+          # local = already-checked-out content; url = where the install
+          # commands on skill pages should point.
+          MERGE_REPOS: '[{"name":"${{ inputs.extra_repo }}","local":".external/extra","url":"https://github.com/${{ inputs.extra_repo }}"}]'
+        run: npm run build
+
+      - name: Pack static site
+        working-directory: website
+        run: tar -czf dist.tar.gz -C dist .
+
+      - name: Upload artifact
+        uses: actions/upload-artifact@v4
+        with:
+          name: merged-website
+          path: website/dist.tar.gz
+          if-no-files-found: error

.github/workflows/deploy-website.yml

@@ -0,0 +1,53 @@
+name: Deploy Website
+
+on:
+  push:
+    branches: [master]
+    paths:
+      - 'website/**'
+      - 'docs/**'
+      - 'skills/**'
+      - 'README.md'
+      - 'CONTRIBUTING.md'
+  workflow_dispatch:
+
+permissions:
+  contents: read
+  pages: write
+  id-token: write
+
+concurrency:
+  group: pages
+  cancel-in-progress: true
+
+jobs:
+  build:
+    runs-on: ubuntu-latest
+    steps:
+      - uses: actions/checkout@v4
+
+      - uses: actions/setup-node@v4
+        with:
+          node-version: 22
+
+      - name: Install dependencies
+        working-directory: website
+        run: npm install
+
+      - name: Build website
+        working-directory: website
+        run: npm run build
+
+      - uses: actions/upload-pages-artifact@v3
+        with:
+          path: website/dist
+
+  deploy:
+    needs: build
+    runs-on: ubuntu-latest
+    environment:
+      name: github-pages
+      url: ${{ steps.deployment.outputs.page_url }}
+    steps:
+      - id: deployment
+        uses: actions/deploy-pages@v4

docs/README.md

@@ -26,6 +26,7 @@ Navigation hub for all guides in this repository. Browse by category below.
 |----|----|
 | [PR Review](./pr-review.md)             | How the PR review skill works, what sections it applies, and how to trigger it     |
 | [Token Saving](./token-saving.md)       | Keeping AI responses concise — how the token-saving skill works and when it applies |
+| [Responsible Agent Use](./responsible-agent-use.md) | Not burning your Copilot token budget — context, models, agent mode, MCP, plugins, skills, and a must-do checklist |
 
 > **Keep this index up to date.** When you add a new guide, add a row to the appropriate table above.
 

docs/getting-started.md

@@ -17,10 +17,10 @@ content progressively:
 | **Activation** | When your task matches a skill's description, the agent reads the full `SKILL.md` into context            |
 | **Execution**  | The agent follows the skill's instructions, optionally loading reference files or running bundled scripts |
 
-> ⚠️ **The `description` field is the sole activation signal.** If a skill isn't firing, your prompt likely doesn't
-> match its description keywords. Rephrase your message to include relevant trigger terms from the skill's description.
-> Inside a Copilot CLI session, run `/skills list` to inspect loaded descriptions.
-> Outside the CLI, you can run `npx skills list -g` to see all the installed skills.
+> ⚠️ **The `description` field is the sole activation signal** — the agent matches your prompt against it to decide
+> whether to load the skill. Inspect loaded descriptions with `/skills list` inside a Copilot CLI session, or
+> `npx skills list -g` outside it. If a skill isn't firing, see
+> [Skill not activating](./troubleshooting.md#skill-not-activating).
 
 ## Prerequisites: Install Copilot CLI