feat: add a feedback-loop-first diagnosing-bugs skill to the coding suite

Ultraworked with [Sisyphus](https://github.com/code-yeongyu/oh-my-openagent)

Co-authored-by: Sisyphus <clio-agent@sisyphuslabs.ai>

assets/agents/coder/graph.yaml

@@ -16,6 +16,7 @@ enabled_skills:
   - ai-slop-remover
   - code-review
   - comment-discipline
+  - diagnosing-bugs
   - git-master
   - frontend-ui-ux
   - verification-gates
@@ -169,6 +170,7 @@ nodes:
       - ai-slop-remover
       - code-review
       - comment-discipline
+      - diagnosing-bugs
       - git-master
       - frontend-ui-ux
       - verification-gates
@@ -227,6 +229,11 @@ nodes:
       the previous attempt failed verification. Read the error, identify
       the minimal fix, apply it. Do not refactor while fixing.
 
+      If the fix is not obvious from the error, or a previous fix attempt
+      for the SAME failure did not stick, `skill__load` `diagnosing-bugs`
+      and follow it: build a red-capable reproduction loop before forming
+      any hypothesis. Do not spend a second attempt on a blind retry.
+
       ## Rules
 
       1. Match existing patterns - read examples first.

assets/agents/sisyphus/config.yaml

@@ -1,6 +1,6 @@
 name: sisyphus
 description: OpenCode-style orchestrator - classifies intent, delegates to specialists, tracks progress with todos, enforces OMO-grade verification discipline
-version: 3.4.0
+version: 3.5.0
 
 agent_session: temp
 auto_continue: true
@@ -27,6 +27,7 @@ enabled_skills:
   - ai-slop-remover
   - code-review
   - comment-discipline
+  - diagnosing-bugs
   - git-master
   - frontend-ui-ux
   - delegation-protocol
@@ -404,6 +405,10 @@ instructions: |
 
   ## Phase 7 - Failure Recovery
 
+  ### Hard bugs: load `diagnosing-bugs` BEFORE strike 2
+
+  A first fix attempt may go on the error message alone. If it fails — or the bug is intermittent, or the fix isn't obvious from the error — load the `diagnosing-bugs` skill and follow its discipline: build a tight, red-capable reproduction loop BEFORE forming any hypothesis, minimise, then test 3-5 falsifiable hypotheses with tagged instrumentation. Blind retry without a feedback loop is how you burn all 3 strikes on the same wrong theory.
+
   ### 3-strike rule
 
   After 3 consecutive failed fix attempts on the same problem: