Skip to content

An agentic skills framework & software development methodology that works.

Close the Minor-severity escape hatch

Jesse Vincentc73e9a9a3fa9
diff --git a/skills/subagent-driven-development/SKILL.md b/skills/subagent-driven-development/SKILL.md
index ee0639573..67257e186 100644
--- a/skills/subagent-driven-development/SKILL.md
+++ b/skills/subagent-driven-development/SKILL.md
@@ -158,7 +158,9 @@ final whole-branch review. When you fill a reviewer template:
lines). A reviewer with the diff in hand needs few or no tool calls; do
not make reviewers re-derive the diff.
- Dispatch fix subagents for Critical and Important findings. Record Minor
- findings and move on — they roll up to the final whole-branch review.
+ findings and move on — then paste the accumulated Minor findings into the
+ final whole-branch review dispatch so it can triage which must be fixed
+ before merge. A roll-up nobody reads is a silent discard.
## Prompt Templates
diff --git a/skills/subagent-driven-development/task-reviewer-prompt.md b/skills/subagent-driven-development/task-reviewer-prompt.md
index 744cfe638..12c6da515 100644
--- a/skills/subagent-driven-development/task-reviewer-prompt.md
+++ b/skills/subagent-driven-development/task-reviewer-prompt.md
@@ -104,8 +104,11 @@ Subagent (general-purpose):
## Calibration
Categorize issues by actual severity. Not everything is Critical.
- Important means this task cannot be trusted until it is fixed;
- "coverage could be broader" and polish suggestions are Minor.
+ Important means this task cannot be trusted until it is fixed: incorrect
+ or fragile behavior, a missed requirement, or maintainability damage you
+ would block a merge over — verbatim duplication of a logic block,
+ swallowed errors, tests that assert nothing. "Coverage could be broader"
+ and polish suggestions are Minor.
Acknowledge what was done well before listing issues — accurate praise
helps the implementer trust the rest of the feedback.