diff --git a/.claude-plugin/marketplace.json b/.claude-plugin/marketplace.json
index 3bc4a3e..32eb604 100644
--- a/.claude-plugin/marketplace.json
+++ b/.claude-plugin/marketplace.json
@@ -18,7 +18,7 @@
         "delegation",
         "orchestration"
       ],
-      "version": "0.3.0"
+      "version": "0.3.1"
     }
   ]
 }
diff --git a/.claude-plugin/plugin.json b/.claude-plugin/plugin.json
index dd8d352..a94d5b3 100644
--- a/.claude-plugin/plugin.json
+++ b/.claude-plugin/plugin.json
@@ -1,6 +1,6 @@
 {
   "name": "codex-headless",
-  "version": "0.3.0",
+  "version": "0.3.1",
   "description": "Delegate implementation work to OpenAI Codex running headless, with Claude scoping the task and verifying the result. Defaults to the most capable model available and streams codex's progress live.",
   "author": {
     "name": "Gauransh Mathur",
diff --git a/.release-please-manifest.json b/.release-please-manifest.json
index 0ee8c01..816df2d 100644
--- a/.release-please-manifest.json
+++ b/.release-please-manifest.json
@@ -1,3 +1,3 @@
 {
-  ".": "0.3.0"
+  ".": "0.3.1"
 }
diff --git a/CHANGELOG.md b/CHANGELOG.md
index 79b5c50..c64e0f6 100644
--- a/CHANGELOG.md
+++ b/CHANGELOG.md
@@ -1,5 +1,12 @@
 # Changelog
 
+## [0.3.1](https://github.com/GauranshMathur/codex-headless-skill/compare/v0.3.0...v0.3.1) (2026-10-01)
+
+
+### Bug Fixes
+
+* **ci:** stop the release merge step failing when nothing is released ([#23](https://github.com/GauranshMathur/codex-headless-skill/issues/23)) ([c484a52](https://github.com/GauranshMathur/codex-headless-skill/commit/c484a521e3d2e0c4b8c4a117755772c5df3665c9))
+
 ## [0.3.0](https://github.com/GauranshMathur/codex-headless-skill/compare/v0.2.0...v0.3.0) (2026-10-01)
 
 
diff --git a/skills/advise/SKILL.md b/skills/advise/SKILL.md
index 310a017..0b6d13c 100644
--- a/skills/advise/SKILL.md
+++ b/skills/advise/SKILL.md
@@ -2,7 +2,7 @@
 name: advise
 description: Get a second opinion from two independent advisors at once, Codex (read-only via `codex exec`) and a Fable 5.1 subagent, then merge their verdicts. Use it only when the user asks for it, for example "get a second opinion", "ask codex and fable", "have codex and fable review this", or "multi-advisor". A run sends the brief and the repository files Codex reads to OpenAI through the user's Codex login, so never start it on your own initiative, however large or risky the task looks.
 argument-hint: "[plan|done] <what you want reviewed>"
-version: 0.3.0 # x-release-please-version
+version: 0.3.1 # x-release-please-version
 allowed-tools:
   - Read
   - Glob
diff --git a/skills/exec/SKILL.md b/skills/exec/SKILL.md
index e2b0199..b1946ae 100644
--- a/skills/exec/SKILL.md
+++ b/skills/exec/SKILL.md
@@ -2,7 +2,7 @@
 name: exec
 description: Delegate implementation work to OpenAI Codex running headless via `codex exec`. Claude scopes the task and verifies the result; codex writes all the code. Use this whenever the user says "have codex do this", "delegate this to codex", "get codex to implement/fix/refactor X", "run this through codex", mentions codex headless or `codex exec`, or asks for work to be handed to another agent while Claude supervises. Also use it when the user wants a large implementation done without spending Claude's context on writing the code. Do NOT use it for questions you can answer directly, one-line edits, or when the user asked you specifically to make the change yourself.
 argument-hint: "[--model SLUG] [--effort high|max] <what codex should build>"
-version: 0.3.0 # x-release-please-version
+version: 0.3.1 # x-release-please-version
 allowed-tools:
   - Read
   - Glob
diff --git a/version.txt b/version.txt
index 0d91a54..9e11b32 100644
--- a/version.txt
+++ b/version.txt
@@ -1 +1 @@
-0.3.0
+0.3.1