From b106f71e5feddfc9d997ccf6b8adb96a49855df0 Mon Sep 17 00:00:00 2001 From: rutkowskij <13108942+rutkowskij@users.noreply.github.com> Date: Fri, 13 Nov 2026 09:38:36 +0100 Subject: [PATCH] fix(pstack): make the bug-fix playbook fix every site of the same fault When a report names one symptom, the agent often finds the same fault at other sites and leaves it out to keep the change narrow. The playbook now says those sites are part of the fix. The Claude Code tree is regenerated. --- .../pstack/claude-code/skills/poteto-mode/playbooks/bug-fix.md | 2 +- pstack/skills/poteto-mode/playbooks/bug-fix.md | 2 +- 2 files changed, 2 insertions(+), 2 deletions(-) diff --git a/harness/pstack/claude-code/skills/poteto-mode/playbooks/bug-fix.md b/harness/pstack/claude-code/skills/poteto-mode/playbooks/bug-fix.md index b5de0bfa63..03ea7db58f 100644 --- a/harness/pstack/claude-code/skills/poteto-mode/playbooks/bug-fix.md +++ b/harness/pstack/claude-code/skills/poteto-mode/playbooks/bug-fix.md @@ -2,7 +2,7 @@ **You own this task. Plan, review, verify.** Delegate investigation and the fix to subagents, stay in the lead. Pick each subagent's reasoning level and fast or standard speed for the job, per the Subagents section. -Be scientific. Every shipped line traces to runtime evidence. Belt-and-suspenders that "might help" is a hypothesis, not a fix. It does not ship. When evidence refutes a hypothesis, revert what it motivated. The smallest change the evidence justifies ships, nothing more. +Be scientific. Every shipped line traces to runtime evidence. Belt-and-suspenders that "might help" is a hypothesis, not a fix. It does not ship. When evidence refutes a hypothesis, revert what it motivated. The smallest change the evidence justifies ships, nothing more. The same fault at sites the report did not name is part of the fix: fix them all, not only the reported one. 1. Reproduce it yourself on the matching surface via the control skill (Non-negotiables), even when a debug or instrumentation protocol says to ask the user to reproduce. Ask the user only with a stated, specific reason the control surface cannot reach the target, and only after driving it as far as it goes. If it won't reproduce directly, synthesize the trigger, tighten conditions, or instrument until it fires. 2. Binary-search the cause. Form the candidate hypotheses, then rule them out until one survives. Seed them with `how` over the affected subsystem and the **why** skill for regression history. Each pass, take the split that cuts the most remaining problem space, get runtime evidence, eliminate. When program state is unclear, add instrumentation or logging and read it as the code runs. Don't guess. Drive a long or stubborn hunt with Cursor's `/loop` command. Confirm the surviving *mechanism* with runtime evidence before the step-3 architect/interrogate fan-out. diff --git a/pstack/skills/poteto-mode/playbooks/bug-fix.md b/pstack/skills/poteto-mode/playbooks/bug-fix.md index b5de0bfa63..03ea7db58f 100644 --- a/pstack/skills/poteto-mode/playbooks/bug-fix.md +++ b/pstack/skills/poteto-mode/playbooks/bug-fix.md @@ -2,7 +2,7 @@ **You own this task. Plan, review, verify.** Delegate investigation and the fix to subagents, stay in the lead. Pick each subagent's reasoning level and fast or standard speed for the job, per the Subagents section. -Be scientific. Every shipped line traces to runtime evidence. Belt-and-suspenders that "might help" is a hypothesis, not a fix. It does not ship. When evidence refutes a hypothesis, revert what it motivated. The smallest change the evidence justifies ships, nothing more. +Be scientific. Every shipped line traces to runtime evidence. Belt-and-suspenders that "might help" is a hypothesis, not a fix. It does not ship. When evidence refutes a hypothesis, revert what it motivated. The smallest change the evidence justifies ships, nothing more. The same fault at sites the report did not name is part of the fix: fix them all, not only the reported one. 1. Reproduce it yourself on the matching surface via the control skill (Non-negotiables), even when a debug or instrumentation protocol says to ask the user to reproduce. Ask the user only with a stated, specific reason the control surface cannot reach the target, and only after driving it as far as it goes. If it won't reproduce directly, synthesize the trigger, tighten conditions, or instrument until it fires. 2. Binary-search the cause. Form the candidate hypotheses, then rule them out until one survives. Seed them with `how` over the affected subsystem and the **why** skill for regression history. Each pass, take the split that cuts the most remaining problem space, get runtime evidence, eliminate. When program state is unclear, add instrumentation or logging and read it as the code runs. Don't guess. Drive a long or stubborn hunt with Cursor's `/loop` command. Confirm the surviving *mechanism* with runtime evidence before the step-3 architect/interrogate fan-out.