Two screenshots for the "Half Your Teammates Aren't Human" blog draft
(post #17130):
- m11-loop.png: a designed diagram of the seven-station loop as a
horizontal row of connected cards (issue -> branch ->
implementation -> PR -> review -> merge -> closed).
Each card carries a small "who typically does it"
tag (human / agent / either / auto) to make the
handoffs visible. Same dark-slate aesthetic as the
rest of the series.
- m11-worktree-prs.png: two side-by-side terminals showing two real agents
at once: left is tasks-app-count on feature/count
with real PR #1 OPEN on recklessop/m11-worktrees-demo;
right is tasks-app-clear on feature/clear with real
PR #2 OPEN on the same repo. Real branches, real
remote pushes, real gh pr view output. The scratch
repo (recklessop/m11-worktrees-demo) is safe to
delete after publish.
Uploaded to WP as media 17194 + 17195, embedded in draft #17130, scheduled
for Tue 2026-08-04 10:00 America/New_York.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01TfzV5QvtPDz8LJS3Pu5VLT
A current frontier editor-agent told to "merge X into Y" resolves the
conflict and completes the merge in one turn, so the learner never sees a
marker. The old Part C assumed Git would stop and ask. Rework the lab into
a three-beat sequence: witness the conflict once (agent stop-on-conflict
idiom, as in Module 26), undo it with `git merge --abort`, then let the AI
merge for real and auto-resolve while the learner does the one job still
theirs: verify with `git diff` after every merge.
Updates the matching surfaces so they tell one story: learning objective
#4, the Merge-conflicts key concept, the AI-angle bullet, the
Where-it-breaks bullet, Check-for-understanding, the blog mirror, and the
make-conflict.sh on-screen guidance (read the markers yourself first).
Closes#97
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01KCv6VTpBG6Zo4xR4AvUQpj
A standalone blog/ folder (not course content) with drafts for jpaul.me:
an announcement, a getting-started piece, then a hybrid weekly series —
one post per module for Units 1-2 (posts 03-13) and one per unit for the
back half (14-16) plus a capstone finale (17). Each post carries WordPress
metadata, a [COURSE LINK] placeholder, and [insert screenshot] blocks for
Justin to fill before publishing. README.md holds the manifest + checklist.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_015EghAChc9UbcF78t55mfdf
claude
justin