From fe90d6c46946c46b47adc677eefe3aa9b5804683 Mon Sep 17 00:00:00 2001 From: Jesse Vincent Date: Wed, 10 Jun 2026 13:08:19 -0700 Subject: [PATCH] Adopt audited positive phrasings: evidence rule leads positive; fix-report completeness as checklist --- skills/subagent-driven-development/SKILL.md | 5 +++-- skills/subagent-driven-development/task-reviewer-prompt.md | 7 ++++--- 2 files changed, 7 insertions(+), 5 deletions(-) diff --git a/skills/subagent-driven-development/SKILL.md b/skills/subagent-driven-development/SKILL.md index 64b9e723..55c8e3d1 100644 --- a/skills/subagent-driven-development/SKILL.md +++ b/skills/subagent-driven-development/SKILL.md @@ -178,8 +178,9 @@ final whole-branch review. When you fill a reviewer template: - Every fix dispatch carries the implementer contract: the fix subagent re-runs the tests covering its change and reports the results. Name the covering test files in the dispatch — a one-line fix does not need the - whole suite. A fix report without test evidence is incomplete — do not - re-review on top of it. + whole suite. Before re-dispatching the reviewer, confirm the fix report + contains the covering tests, the command run, and the output; dispatch + the re-review once all three are present. - If the final whole-branch review returns findings, dispatch ONE fix subagent with the complete findings list — not one fixer per finding. Per-finding fixers each rebuild context and re-run suites; a real diff --git a/skills/subagent-driven-development/task-reviewer-prompt.md b/skills/subagent-driven-development/task-reviewer-prompt.md index 19f56b9a..3bc019a0 100644 --- a/skills/subagent-driven-development/task-reviewer-prompt.md +++ b/skills/subagent-driven-development/task-reviewer-prompt.md @@ -110,9 +110,10 @@ Subagent (general-purpose): significantly grow existing files? (Don't flag pre-existing file sizes — focus on what this change contributed.) - Cite file:line evidence for every finding and for any check you would - otherwise answer with a bare "yes." Cite, don't narrate — a tight report - that points at lines beats a long one that retells the diff. + Your report should point at evidence: file:line references for every + finding and for any check you would otherwise answer with a bare + "yes." A tight report that cites lines gives the controller everything + it needs. ## Calibration