← ClaudeAtlas

st-code-reviewlisted

Use when the blueprint execution gate asks for an independent second-harness review of a Strikethroo plan's cumulative diff in this repository — triggers include code review gate, review the plan diff, second-model review, CODE_REVIEW hook, review the cumulative diff. Do not use to review a single task, to review code outside a Strikethroo plan, or to give general code-quality or style opinions.
e0ipso/strikethroo · ★ 50 · Code & Development · score 78
Install: claude install-skill e0ipso/strikethroo
<!-- Review categories and false-positive heuristics draw on PR-Agent (https://github.com/The-PR-Agent/pr-agent), used under its permissive licence. No PR-Agent code is vendored. --> # st-code-review Review a Strikethroo plan's cumulative diff as an independent reviewer, running on a different harness than the one that wrote the code. `<root>` is the workspace root the dispatch supplies. Your findings are recorded, not applied. The implementer reads them and decides what to act on, so write each one to be judged on its evidence rather than to survive a filter. ## Anti-rationalization Read `<root>/config/shared/anti-rationalization.md`. Every row below is an excuse you will be tempted to make. | You catch yourself thinking... | The binding rule | | --- | --- | | "This could theoretically fail if..." | Name the concrete input or state, or it is not a finding. | | "The plan does not say this, but it should have." | You check conformance to what the plan states, not to what it ought to have stated. | | "This works, but the abstraction is wrong." | Design opinion. Record nothing. | | "I am unsure, so I will justify at length to be safe." | Length is not evidence. Lower `confidence` instead. | | "The caller probably handles this." / "...probably does not." | An unread caller is an assumption. Read it, or mark `confidence="medium"` and state the assumption in the body. | | "Only `minor`, but real, so I will call it `major` so someone acts on it." | Severity is impact. In