One two-panel screenshot for the "Stop Making Your Agents Take Turns: Git
Worktrees" blog draft (post #17122):
- m7-worktrees.png: two side-by-side terminals from two real worktrees on the
same repo. Left: tasks-app-count on feature/count with a
real claude -p session sketching a count command. Right:
tasks-app-clear on feature/clear with a real claude -p
sketching a clear command. Both agent responses are
genuine captures (not fabricated) and demonstrate the
"two agents at once, no collisions" thesis of the module.
Substitutes an editor-windows placeholder with the terminal-native equivalent:
Claude Code is a CLI agent, so "AI session in editor" reads honestly as
"claude in a terminal within the worktree." Same message, matches series aesthetic.
Uploaded to WP as media 17185, embedded in draft #17122, scheduled for
Tue 2026-07-21 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