Fix Module 21 Part D's git diff HEAD~1 add-command.md (empty given the lab's commit ordering) #21

New Issue

2026-06-22T14:23:47-04:00

claude commented

2026-06-22 14:23:47 -04:00

Problem

Part C has the learner tighten the skill, commit it, then run the skill again on a second command (producing its own commit that doesn't touch add-command.md). Part D's git diff HEAD~1 add-command.md then compares HEAD~1 (the tighten commit) to the working tree for that path — unchanged — so it prints nothing and fails to demonstrate the claimed "workflow change as a diff." The follow-up prose ("That diff is a change to how your team adds commands…") depends on a non-empty diff.

Evidence

modules/21-skills-teaching-the-ai-your-playbook/README.md, Part D step 7 (~~line 237): "git diff HEAD~~1 add-command.md # if you tightened it in Part C — your workflow change as a diff" combined with Part C (~line 227): "Tighten that line, commit the skill change, and run it again on a second command."
Reproduced with commits [Add skill][Add clear][Tighten skill][Add high]: the diff is empty.

Why it matters

The headline payoff of the lab is silently empty.

Proposed change

Use a command that surfaces the skill's history regardless of later commits:

git log -p -- add-command.md (verified to show the tighten patch and the file's creation), or git show <tighten-commit> -- add-command.md; or instruct running the diff immediately after the tighten commit.
This dovetails with the git log --oneline add-command.md already on the line above.

Acceptance criteria

The shown command displays the tighten change regardless of later command commits.
The "workflow change as a diff" claim is demonstrably true when followed.

Affected files

modules/21-skills-teaching-the-ai-your-playbook/README.md

References

Source finding F35 (realVotes 3/3).

Filed from an adversarial multi-agent course review (217 raw findings → 54 adversarially-verified survivors). Scoped for manual review; intentionally not auto-assigned to an agent.

## Problem Part C has the learner tighten the skill, commit it, then run the skill again on a second command (producing its own commit that doesn't touch `add-command.md`). Part D's `git diff HEAD~1 add-command.md` then compares HEAD~1 (the tighten commit) to the working tree for that path — unchanged — so it prints nothing and fails to demonstrate the claimed "workflow change as a diff." The follow-up prose ("That diff *is* a change to how your team adds commands…") depends on a non-empty diff. ## Evidence `modules/21-skills-teaching-the-ai-your-playbook/README.md`, Part D step 7 (~line 237): "git diff HEAD~1 add-command.md # if you tightened it in Part C — your workflow change as a diff" combined with Part C (~line 227): "Tighten that line, commit the skill change, and run it again on a second command." Reproduced with commits [Add skill][Add clear][Tighten skill][Add high]: the diff is empty. ## Why it matters The headline payoff of the lab is silently empty. ## Proposed change Use a command that surfaces the skill's history regardless of later commits: - `git log -p -- add-command.md` (verified to show the tighten patch and the file's creation), or `git show <tighten-commit> -- add-command.md`; or instruct running the diff immediately after the tighten commit. This dovetails with the `git log --oneline add-command.md` already on the line above. ## Acceptance criteria - [ ] The shown command displays the tighten change regardless of later command commits. - [ ] The "workflow change as a diff" claim is demonstrably true when followed. ## Affected files - `modules/21-skills-teaching-the-ai-your-playbook/README.md` ## References Source finding F35 (realVotes 3/3). --- *Filed from an adversarial multi-agent course review (217 raw findings → 54 adversarially-verified survivors). Scoped for manual review; intentionally not auto-assigned to an agent.*