Phase 1 of the reframe (M1-6). M1-3 stay manual-by-hand on purpose; M4 pivots to the AI agent (Claude Code as the worked example); M5-6 are agent-driven. Applies the new AGENTS.md/_TEMPLATE.md direction + the audit + your module-specific issues, preserving every deliberate teaching device (verified: M1 seam engineering, M2 restore/cold-session, M3 branch/gotcha, M4 throwaway-restore, M6 engineered conflict — now AI-resolved).
Verified: 'prose' gone from M3, no /path/to in M1-6, Claude Code + arithmetic->calculator analogy in M4, all labs compile/parse.
Phase 1 of the reframe (M1-6). M1-3 stay manual-by-hand on purpose; M4 pivots to the AI agent (Claude Code as the worked example); M5-6 are agent-driven. Applies the new AGENTS.md/_TEMPLATE.md direction + the audit + your module-specific issues, preserving every deliberate teaching device (verified: M1 seam engineering, M2 restore/cold-session, M3 branch/gotcha, M4 throwaway-restore, M6 engineered conflict — now AI-resolved).
Verified: 'prose' gone from M3, no /path/to in M1-6, Claude Code + arithmetic->calculator analogy in M4, all labs compile/parse.
Closes #78
Closes #79
Closes #80
Closes #81
Closes #82
Closes #84
Closes #85
Closes #87
Closes #88
Closes #90
Holding #83 (slop, all modules), #86 (paths, check others), #89 (lesson=theory, all modules) until the Phase 2 sweep closes them course-wide.
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Phase 1 of the reframe. M1-3 stay manual-by-hand (browser chat); M4 is the pivot
to the AI agent (Claude Code as example); M5-6 are agent-driven.
- M1: de-slop (em-dashes), relocate the build-note out of the lab. Seam devices kept.
- M2: #78 tell learner how to paste cli.py into chat; #79 commit the delete so the
tree ends clean. restore/cold-session devices kept.
- M3: #80 define ADR; #81 create-file-before-add; #82 ls before/after merge to prove
branch isolation; #83 drop "prose"; M3 now owns the branch-basics intro.
- M4: #84 Claude Code as the worked example; #85 AI drives git (arithmetic->calculator);
#86 /path/to -> ~/ai-workflow-course; #87 agent does the revert+verify.
- M5: #88 ask the agent which config files to commit, then let it stage/commit
(CLAUDE.md example; repo still uses AGENTS.md).
- M6: #90 stop re-teaching branch basics; rescope to the AI experimenting on a branch;
the engineered conflict is now AI-resolved, learner-verified.
Closes#78Closes#79Closes#80Closes#81Closes#82Closes#84Closes#85Closes#87Closes#88Closes#90
Co-Authored-By: Claude Opus 4.8 (1M context) <[email protected]>
Claude-Session: https://claude.ai/code/session_01TfzV5QvtPDz8LJS3Pu5VLT
claude
merged commit a29823f4b3 into main2026-06-22 21:41:32 -04:00
claude
deleted branch fix/phase1-m1-62026-06-22 21:41:32 -04:00
Blocking a user prevents them from interacting with repositories, such as opening or commenting on pull requests or issues. Learn more about blocking a user.
Phase 1 of the reframe (M1-6). M1-3 stay manual-by-hand on purpose; M4 pivots to the AI agent (Claude Code as the worked example); M5-6 are agent-driven. Applies the new AGENTS.md/_TEMPLATE.md direction + the audit + your module-specific issues, preserving every deliberate teaching device (verified: M1 seam engineering, M2 restore/cold-session, M3 branch/gotcha, M4 throwaway-restore, M6 engineered conflict — now AI-resolved).
Verified: 'prose' gone from M3, no /path/to in M1-6, Claude Code + arithmetic->calculator analogy in M4, all labs compile/parse.
Closes #78
Closes #79
Closes #80
Closes #81
Closes #82
Closes #84
Closes #85
Closes #87
Closes #88
Closes #90
Holding #83 (slop, all modules), #86 (paths, check others), #89 (lesson=theory, all modules) until the Phase 2 sweep closes them course-wide.
🤖 Generated with Claude Code