diff --git a/assets/agents/coder/graph.yaml b/assets/agents/coder/graph.yaml
index 208efb2..ba82ef4 100644
--- a/assets/agents/coder/graph.yaml
+++ b/assets/agents/coder/graph.yaml
@@ -17,6 +17,7 @@ enabled_skills:
   - code-review
   - comment-discipline
   - diagnosing-bugs
+  - logging-discipline
   - git-master
   - frontend-ui-ux
   - verification-gates
@@ -171,6 +172,7 @@ nodes:
       - code-review
       - comment-discipline
       - diagnosing-bugs
+      - logging-discipline
       - git-master
       - frontend-ui-ux
       - verification-gates
@@ -221,7 +223,12 @@ nodes:
          `comment-discipline` (self-documenting / api-documented /
          comment-heavy) and write comments to match. When the signal is
          weak, write NO comment.
-      4. Follow the same patterns exactly. Do not invent new ones.
+      4. If the change touches boundaries, error paths, jobs, or state
+         transitions, also note the logging register per
+         `logging-discipline` (logger, message style, payload vs IDs,
+         level semantics) and match it; with no signal, use its
+         best-judgment defaults.
+      5. Follow the same patterns exactly. Do not invent new ones.
 
       ## Fix loop
 
diff --git a/assets/agents/sisyphus/config.yaml b/assets/agents/sisyphus/config.yaml
index 8b0d2f2..a1a6cc3 100644
--- a/assets/agents/sisyphus/config.yaml
+++ b/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: 3.7.0
+version: 3.8.0
 
 agent_session: temp
 auto_continue: true
@@ -30,6 +30,7 @@ enabled_skills:
   - comment-discipline
   - diagnosing-bugs
   - grilling
+  - logging-discipline
   - git-master
   - frontend-ui-ux
   - delegation-protocol
@@ -391,6 +392,7 @@ instructions: |
   When you write or modify files yourself (rather than delegating to coder):
 
   - **Calibrate comments before writing.** Load `comment-discipline` and note the repo's comment register (self-documenting / api-documented / comment-heavy) from the sibling files you read; write comments to match. When the signal is weak, write NO comment.
+  - **Calibrate logging before writing.** When the change touches boundaries, error paths, jobs, or state transitions, load `logging-discipline` and note the repo's logging register (logger, message style, payload vs IDs, level semantics) from the same sibling reads; match it. No discernible convention → its best-judgment defaults. Never leave a new error path silently swallowed, and never delete existing log lines as drive-by cleanup.
   - **For editing an existing file**, prefer `fs_patch`. It's a surgical edit that preserves unchanged content. Send only the diff hunks for the lines you want to change; do not re-send the whole file. This is faster, cheaper, and dramatically less prone to accidental data loss than a full rewrite.
   - **For writing a NEW file or doing a COMPLETE rewrite**, use `fs_write`. Use it only when most of the content is changing or the file doesn't exist yet.
   - **NEVER write files via `execute_command`.** Do not use: