rogee/superpowers
1
0
Fork 0
mirror of https://github.com/obra/superpowers.git synced 2026-08-05 13:48:46 +08:00
Code Issues Packages Projects Releases Wiki Activity

fix(sdd): task reviewers re-read illegible evidence instead of re-running to regenerate it

Browse Source 
Interrogation of reviewers who bypassed test-evidence leases showed a
convergent driver: when the report or receipt looked truncated or
couldn't be located, re-running the suite felt cheaper than re-reading —
evidence got regenerated instead of read. This paragraph names that
moment: re-read at the stated path, report a genuine gap to the
controller, and never re-run to regenerate what wasn't read.

Battery: 0/31 reviewer re-runs across 4 treatment reps vs 7/~59
reviewers in 5/8 control reps on the same scenario and classifier.

Claude-Session: https://claude.ai/code/session_0185AJr98gHx5EmwqNeft4Sy
This commit is contained in:
Jesse Vincent
2026-08-04 18:24:10 -07:00
parent 05c2393b82
commit 80b82abd8d
1 changed files with 7 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files

7
skills/subagent-driven-development/task-reviewer-prompt.md
View File

@@ -84,6 +84,13 @@ Subagent (general-purpose):
Warnings or other noise in the implementer's reported test output are Warnings or other noise in the implementer's reported test output are
findings — test output should be pristine. findings — test output should be pristine.
Evidence you cannot see is not evidence that doesn't exist. If the
report or its test evidence looks truncated, or you cannot locate the
results it claims, re-read the file at its stated path — and if it is
genuinely missing or garbled, report that as a gap for the controller.
Re-running the suite to regenerate what you failed to read is not
verification; illegibility of the evidence is not invalidation of it.
## Part 1: Spec Compliance ## Part 1: Spec Compliance
Compare the diff against What Was Requested: Compare the diff against What Was Requested: