@codegiveness/kernel-prompt 0.4.0 → 0.4.1

package/CHANGELOG.md

@@ -1,5 +1,13 @@
 # Kernel Prompt
 
+## [0.4.1] - 2026-10-10
+
+### Changed
+
+- Deliver the improved prompt inside a fenced code block, ready to copy and send, instead of as plain text; a prompt that itself contains triple backticks is wrapped in a four-backtick fence. Update the README's description of the delivery format.
+- Document the release workflow in `RELEASING.md` (issue, worktree branch, pull request, squash-merge, tag, GitHub release, and staged npm publish approved by the maintainer with two-factor authentication) and link it from the README. `AGENTS.md` now requires every update to follow it and npm releases to be staged, never published directly.
+- Add a pull request template and issue forms for bug reports and change requests.
+
 ## [0.4.0] - 2026-10-10
 
 ### Changed

package/README.md

@@ -13,7 +13,7 @@ Use kernel-prompt to improve this request:
 [your goal or draft, with relevant context and constraints]
 ```
 
-Expect one round of two to five questions before any draft, each led by a recommended answer and using the harness's question tool when one exists. Say "no questions" or "just write it" to skip them. A further round comes only for decisions your answers opened. The reply is the prompt alone, as plain text ready to send, followed by at most three assumptions you did not confirm; decisions you left unsettled are delegated to the agent or marked open in the prompt, never guessed.
+Expect one round of two to five questions before any draft, each led by a recommended answer and using the harness's question tool when one exists. Say "no questions" or "just write it" to skip them. A further round comes only for decisions your answers opened. The reply is the prompt alone, inside a fenced code block ready to copy and send (a four-backtick fence when the prompt itself contains triple backticks), followed by at most three assumptions you did not confirm; decisions you left unsettled are delegated to the agent or marked open in the prompt, never guessed.
 
 Invoking the skill with text that reads as a task—"fix the failing login test"—yields a prompt for that task, not the fix. Files, skills, URLs, and repositories you mention are read as context for the prompt, not rewritten as the deliverable, unless you say that text is the prompt to improve. No files are created or edited unless you ask to save the prompt.
 
@@ -54,7 +54,7 @@ The skill is also published as [`@codegiveness/kernel-prompt`](https://www.npmjs
 npm install @codegiveness/kernel-prompt
 ```
 
-Then copy `node_modules/@codegiveness/kernel-prompt/skills/kernel-prompt/` into your harness's skill location. Releases are staged with `npm stage publish` and go live only after a maintainer approves them with two-factor authentication.
+Then copy `node_modules/@codegiveness/kernel-prompt/skills/kernel-prompt/` into your harness's skill location. Releases are staged with `npm stage publish` and go live only after a maintainer approves them with two-factor authentication; [RELEASING.md](RELEASING.md) lists the full release workflow.
 
 Versions 0.1.0 through 0.2.0 remain deprecated: they carry historical skill content, and 0.1.x also shipped an `install`/`update` CLI that no longer exists. Replace only your existing Kernel Prompt skill with the current `SKILL.md`, preserving local edits and unrelated instructions; deprecation does not remove installed files or update copied instructions.
 

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@codegiveness/kernel-prompt",
-  "version": "0.4.0",
+  "version": "0.4.1",
   "description": "Agent skill that turns rough requests and drafts into clear prompts for other agents, asking only the decisions that change the result.",
   "license": "MIT",
   "author": "codegiveness",

package/skills/kernel-prompt/SKILL.md

@@ -32,7 +32,7 @@ Turn the user's message into a better prompt they can give to an AI agent. You w
 - **L — Lay out the handoff.** Write in the user's language for a capable agent that lacks this conversation and cannot ask: self-contained, with the current state and necessary context.
 
 ## Deliver
-- Reply with the improved prompt as plain text, ready to copy and send. No intro, no analysis, no critique of the original, no change log.
+- Reply with the improved prompt inside a fenced code block, ready to copy and send; if the prompt itself contains triple backticks, use a four-backtick fence. No intro, no analysis, no critique of the original, no change log.
 - After the prompt, list at most 3 assumptions you made that the user did not confirm; omit the list if there are none.
 
 ## Example