xonecas.io
64875
Mc

mini-coder / commit 7477de9

fix: command changes

xonecas2026-03-14 7477de9b4a5078412e1c7d82888da75b4bbb9e65 parent 60d7395

1 file changed

.agents/commands/ui-probe.md+5−3
@@ -2,6 +2,8 @@
22 description: Run one-shot mc sessions across all SDK paths, capture output, and write a UI/UX analysis report to UI-REPORT.md.
33 ---
44
5+The goal is to capture a realistic perspective of what the users see when using mini-coder.
6+
57 Run `mc` one-shots using one cheap model per Zen SDK path, capture their raw terminal output, then analyse it yourself and write `UI-REPORT.md` in the repo root. Do NOT delegate the report to the models under test.
68
79 ## Models to use (one per SDK path)
@@ -10,8 +12,8 @@ Pick cheap/free options. Verify available models at https://opencode.ai/docs/zen
1012
1113 - `@ai-sdk/anthropic` path → a `zen/claude-*` haiku-class model
1214 - `@ai-sdk/google` path → a `zen/gemini-*` flash-class model
13-- `@ai-sdk/openai` path (responses endpoint) → a `zen/gpt-*` nano/mini-class model
14-- `@ai-sdk/openai-compatible` path → `zen/big-pickle` (free) or similar free model
15+- `@ai-sdk/openai` path (responses endpoint) → a `zen/gpt-*` small low cost model
16+- `@ai-sdk/openai-compatible` path → `zen/*` or similar small low cost model
1517
1618 ## Prompt to give each model
1719
@@ -34,7 +36,7 @@ This prompt is intentionally simple: it covers file reads, a write, and exposes
3436 sed 's/\x1b\[[0-9;?]*[mKlh]//g; s/\r//g' logs/<model>.log > logs/<model>-clean.log
3537 ```
3638 4. Read all clean logs yourself and analyse what a user would actually see.
37-5. Clean up any `mc-summary.md` files left behind by the test models.
39+5. Clean up any `mc-summary.md` files left behind by the test models. And the log files
3840
3941 ## Report structure for UI-REPORT.md