6878783bf1
Four focused review prompts for use with orch multi-model consensus: - bloat.md: file size, function length, complexity - smells.md: code smells, readability, naming - dead-code.md: zombie code, unreachable, obsolete - redundancy.md: duplication, parallel systems, YAGNI 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com> |
||
|---|---|---|
| .. | ||
| bloat.md | ||
| dead-code.md | ||
| README.md | ||
| redundancy.md | ||
| smells.md | ||
Review Lenses
Focused review prompts for multi-perspective code analysis.
Philosophy
Each lens examines code through one specific concern. Multiply lenses × models for diverse perspectives.
Usage
Single lens, multiple models:
orch consensus "$(cat reviews/bloat.md)" flash gemini gpt --file src/target.py
Pipe file content:
cat src/target.py | orch consensus "$(cat reviews/smells.md)" flash gemini
Convergent review (multiple passes):
for lens in bloat smells dead-code; do
echo "=== $lens ==="
orch chat "$(cat reviews/$lens.md)" --model gemini --file src/target.py
done
Available Lenses
| Lens | Focus |
|---|---|
bloat.md |
File size, function length, complexity metrics |
smells.md |
Code smells, readability, naming issues |
dead-code.md |
Unused exports, zombie code, unreachable paths |
redundancy.md |
Duplicate systems, YAGNI, consolidation opportunities |
Planned Lenses
coverage.md- Test gaps, untested critical pathscoupling.md- Tight coupling, leaky abstractionssecurity.md- OWASP, injection, authperf.md- Bottlenecks, N+1 queriesarchitecture.md- Boundaries, data flow, trade-offs
Output Convention
All lenses output findings in a consistent format:
[TAG] <severity:HIGH|MED|LOW> <file:line>
Issue: <description>
Suggest: <action>
This enables parsing and automated beads creation.