Files
droid_rules/VISION.md

2.6 KiB

VISION

Need a skill for factory droid which can launch droid exec for multiple things.

Available Models

Model Name Alias
opus_4.5 Opus 4.5
gpt_5.2 GPT 5.2
gpt_5.2_codex GPT 5.2 Codex
kimi_k2.5 Kimi k2.5

Model Selection Criteria

Role Recommended Model Reason
The workhorse kimi_k2.5 Fast and cost-effective
The critic opus_4.5 Good at reviewing and finding issues
The brainy one gpt_5.2 Highest code intelligence
The coder gpt_5.2_codex Specialized for code generation
The fast one kimi_k2.5 Fastest response time
Good Instructions Following kimi_k2.5, gpt_5.2_codex Strong adherence to requirements

Coding Task Breakdown

  1. Code exploration
  2. Planning/spec generation
  3. Code generation
  4. Formatting, linting, typecheck and other quality checks
  5. Review and find bugs
  6. Build or test or run the code

Model Rejection Criteria

gpt_5.2 and gpt_5.2_codex

  • Too slow and expensive for the workhorse role
  • Not at all suggested for exploration or tool calls
  • Strictly for planning/spec gen and code gen

opus_4.5

  • Very buggy and looks for shortcuts in code gen
  • Can be a good critic and reviewer
  • Never use for code gen

kimi_k2.5

  • OK in all areas and fast
  • Never be primary for large code gen
  • Can be used for a second opinion

Model Performance Comparison

Cost (High to Low)

Rank Model
1 opus_4.5
2 gpt_5.2
3 gpt_5.2_codex
4 kimi_k2.5

Speed (Fast to Slow)

Rank Model
1 kimi_k2.5
2 opus_4.5
3 gpt_5.2_codex
4 gpt_5.2

Code Intelligence (High to Low)

Rank Model
1 gpt_5.2
2 gpt_5.2_codex
3 opus_4.5
4 kimi_k2.5

Overthinking (High to Low)

Rank Model
1 gpt_5.2
2 gpt_5.2_codex
3 opus_4.5
4 kimi_k2.5