Lesson Cut Critic — Development agent for Claude Code
Reads the simulated delivered transcript of a lesson after every proposed cut is applied, and finds what per-window review cannot see: joins that break, cuts that conflict, dangling references, and th.
How to install Lesson Cut Critic
Installs to ~/.claude/agents/aiwithmo-lesson-cut-lesson-cut-critic.md
mkdir -p ~/.claude/agents && curl -fsSL https://raw.githubusercontent.com/aiwithmo/lesson-cut/HEAD/agents/lesson-cut-critic.md -o ~/.claude/agents/aiwithmo-lesson-cut-lesson-cut-critic.md Restart Claude Code, or start a new session, for it to be picked up.
What Lesson Cut Critic does
description: "Reads the simulated delivered transcript of a lesson after every proposed cut is applied, and finds what per-window review cannot see: joins that break, cuts that conflict, dangling references, and the delivered length. Run once over the surviving cut list."
Read the editorial brief first (the filled `cut-brief.md` in the shared scratch directory) and follow it. You are the completeness critic. Cuts that are each individually correct can still combine into a broken piece,
Alternatives in Development
- Review Workflow Context Budget — Reviews workflow machinery for context-window budget on three axes: always-loaded surface, load-on-demand disc 432 ★
- 🖥️ Multi-Window Context — TL;DR: State persistence across Claude Code sessions 243 ★
- Peer Reviewer Demographics — A simulated peer reviewer specializing in population representativeness, demographic measurement, and populati 134 ★
Full documentation available on GitHub
View Source RepositoryRelated Agents
Skill Applied Judge
Use this agent at session-end Phase 3.6.6 (#645 L3) to judge — from the session transcript tail — whether each
Agent Harness Optimizer
Context window, token budget, and agent harness optimization specialist. Analyzes transcript bloat, tunes prom
Skill Improver
Use proactively before adding an agent or a skill, and after any model or plugin upgrade, to verdict how the h
Verify Agent
Verifies a plan has no loose ends before it gets implemented. Checks every step against the real codebase for
Shakespeare Reviewer
Review a PR diff, branch, or patch with full Shakespearean Bardic register — substantive technical feedback, d
Courier
Close out a delivered effort. Packages the output, generates recipient-specific briefs, and writes the permane
Related Skills
Claudemd Bypass Audit
R3 Step 2 — lesson-bypass detector. Joins memory-prompt-hint suggest events with subsequent transcript activit
Cr Tune
Mine the CR ledger for disproved classes per critic and draft citation-backed tuning proposals (.coderabbit.ya
Issue Autofix Session
Run a full overnight autofix session — loop issue_autofix over the queue, skip (never halt) on a failure or co