docs: sort Prerequisites lists numerically ascending (#100)
CI / check (pull_request) Successful in 6s

Reorder the `## Prerequisites` bullets in 9 modules so prior modules
are listed lowest number first instead of by pedagogical importance or
at random. A trailing "Helpful but not required" group stays last and
is sorted within itself; multi-module bullets sort by their lowest
number. Intro/closing paragraphs are left in place. Prose is unchanged;
only bullet order moves.

Modules touched: 7, 9, 14, 15, 22, 24, 25, 26, 27. The other 18 modules
were already ascending (or have one/zero prereqs) and are untouched.
Module 19's "Helpful but not required: Module 16" correctly trails its
ascending 8/14/18 main list, so it stays as is.

Closes #100

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01CamgR4HaVpfaqUViuHUcWw
This commit is contained in:
2026-06-23 09:53:05 -04:00
parent edf3f34336
commit 65c6c6b2b6
9 changed files with 49 additions and 49 deletions
+2 -2
View File
@@ -25,14 +25,14 @@ trusting an agent in the loop, before Module 25 lets one actually open a PR.
## Prerequisites
- **Module 5: Commit the AI's config.** The review rubric and the label taxonomy in this lab are
committed, versioned config: change how the agent behaves and it arrives as a reviewable diff.
- **Module 9: Issues and the task layer.** You have issues describing work, and the idea that an
assignee can be a human *or* an agent. The triage half of this module is the agent that sorts the
incoming pile and decides which is which.
- **Module 10: Reviewing code you didn't write.** You learned to read an AI's diff for plausibility
traps, not just correctness. The review half hands the *first pass* of exactly that skill to an
agent, so your attention lands where it matters.
- **Module 5: Commit the AI's config.** The review rubric and the label taxonomy in this lab are
committed, versioned config: change how the agent behaves and it arrives as a reviewable diff.
- **Module 22: Securing third-party MCP servers and skills.** The least-privilege and
prompt-injection thinking from there is what keeps an assistive agent inside its lane. We lean on
it directly in "Where it breaks."