diff --git a/.github/workflows/grade.yml b/.github/workflows/grade.yml
index f72d206..d88f525 100644
--- a/.github/workflows/grade.yml
+++ b/.github/workflows/grade.yml
@@ -8,6 +8,6 @@ permissions:
   pull-requests: read
 jobs:
   grade:
-    uses: TensorOpsAI/tensorlearn-intent-grader/.github/workflows/grade.yml@46de78b3462c3d3a18c2f55e81d645a816815302
+    uses: TensorOpsAI/tensorlearn-intent-grader/.github/workflows/grade.yml@6e73f4b36097d43672ff6f7afc240106445c6fd5
     with:
-      grader-sha: 46de78b3462c3d3a18c2f55e81d645a816815302
+      grader-sha: 6e73f4b36097d43672ff6f7afc240106445c6fd5
diff --git a/README.md b/README.md
index 317363e..3a1dd68 100644
--- a/README.md
+++ b/README.md
@@ -8,12 +8,17 @@ Read [the product brief and published rubric](docs/product-brief.md).
 
 1. Fork this repository to your personal GitHub account. Use fictional information
    only, keep the fork public, and keep `main` as its default branch.
-2. Clone your fork and enable GitHub Actions in it. Your facilitator enrolls you in
-   the lab, approves your exact fork, and confirms the GitHub App connection.
-3. Download the compatible TensorLearn client (v0.5.1 or later) from the lab page
+2. Clone your fork and enable GitHub Actions in its **Actions** tab. Your facilitator
+   enrolls you in the lab once; they do not create or approve a repository per student.
+   Use **Connect GitHub for scoring** on the lab page to install the read-only grading
+   App on your exercise fork. Return to the lab and use **Recheck connection** if needed.
+3. Download the compatible TensorLearn client (v0.5.2 or later) from the lab page
    and extract it outside your fork. Follow the page's `--code` connection command
    from your fork folder. Paste your learner token only into the hidden terminal
-   prompt. After the facilitator launches the round, use `/load` in Claude Code.
+   prompt. Run `/load` from your fork folder to connect that repository automatically.
+   It briefly creates and removes a verification tag using your GitHub login to prove
+   you control the fork. Setup can happen before launch; run `/load` again after the
+   facilitator launches the round to load it.
 4. Create a branch such as `intent/first-draft`. Read the brief and ask Claude to
    help you write `intent.md`. Change only that file. Review the document yourself.
 5. Start a fresh Claude session if needed and ask it to explain the loaded scope
@@ -28,6 +33,12 @@ Read [the product brief and published rubric](docs/product-brief.md).
    and `intent-score/score.json` are useful feedback, but an Actions check alone
    does not submit your work or prove that the server saved a score.
 
+The lab page shows the selected repository. **Disconnect repository** keeps saved
+scores and GitHub files, while stopping pending grading. Open another eligible fork
+and run `/load` to change repositories. **Delete my lab work** is a separate confirmed
+reset of saved submissions, scores and connections. Your instructor can also reset
+your lab work; neither reset deletes your GitHub repository.
+
 A change to your answer requires a new commit, push, and explicit `/submit`.
 Keep the PR open until your facilitator finishes reviewing the exercise. Your
 facilitator controls the official attempt allowance; advisory CI runs do not count
@@ -50,9 +61,11 @@ belong in this starter or student forks. The workflow grades the PR head commit,
 not GitHub's synthetic merge preview. Both PR branches must belong to the learner's
 approved repository; do not open a PR against the upstream starter.
 
-Before launch, verify that the deployed platform accepts approved public repositories
-and pull-request check results, the matching client is downloadable, and the learner
-repository's GitHub App installation is approved. Configure the grading allowance.
+Prepare one shared starter and exercise record, enroll learners, configure the grading
+allowance and launch. Each learner forks the starter, connects their own repository
+with `/load`, and installs the grading App. Verify the matching client is downloadable
+and that the platform can receive GitHub check results; there is no per-student
+repository creation or approval step for public starter forks.
 Observe an actual saved learner score before claiming end-to-end readiness. A client
 or server that only supports private repositories is incompatible with this public
 fork exercise. See the checker repository's rehearsal checklist.