feat(commands): add /sidenote to park a thought without derailing the current task

README.md

@@ -20,7 +20,7 @@
 
 > Built and maintained by [Clawnify](https://clawnify.com) — a managed platform that provisions AI agents with WhatsApp / Telegram / Email and browser capabilities for non-technical users.
 
-A single `CLAUDE.md` file to improve AI coding-agent behavior, derived from [Andrej Karpathy's observations](https://x.com/karpathy/status/2015883857489522876) on LLM coding pitfalls, plus three sections we added for the AI-assisted-coding era. Ships with two runnable [meta-skills](#skills-skillify-dry--mece-resolvers), the [`/scalable`](#the-scalable-command) decision command, and a [one-command installer](#install) that fans it all out to every AI coding agent you use.
+A single `CLAUDE.md` file to improve AI coding-agent behavior, derived from [Andrej Karpathy's observations](https://x.com/karpathy/status/2015883857489522876) on LLM coding pitfalls, plus three sections we added for the AI-assisted-coding era. Ships with two runnable [meta-skills](#skills-skillify-dry--mece-resolvers), the [`/scalable`](#the-scalable-command) decision command, the [`/sidenote`](#the-sidenote-command) park-a-thought command, and a [one-command installer](#install) that fans it all out to every AI coding agent you use.
 
 ## The Problems
 
@@ -194,6 +194,22 @@ cp commands/scalable.md ~/.claude/commands/      # personal, all projects
 
 Then `/scalable` (tests the current direction) or `/scalable <a specific decision>`.
 
+## The `/sidenote` command
+
+You're mid-way through a big task and a passing thought hits — *"the retry logic probably has the same bug", "remind me to check the pricing later"* — something you don't want to forget. Drop it in the chat as-is and the agent reads it as a new request: it rushes the current task to "get to" your note, and the big task pays for it.
+
+[`commands/sidenote.md`](./commands/sidenote.md) reframes that thought as a **parked later-task, not a now-task**. The agent logs it verbatim to `.claude/sidenotes.md` (durable across compaction and session end), gives a one-line ack, and resumes *exactly* where it was — same scope, same pace, no cutting corners to reach the note. A bare `/sidenote` flushes the list back to you.
+
+```bash
+mkdir -p ~/.claude/commands
+cp commands/sidenote.md ~/.claude/commands/      # personal, all projects
+# or: .claude/commands/  for one project
+```
+
+Then `/sidenote <the thought>` to park one, or `/sidenote` to see what's parked. The notes land in `.claude/sidenotes.md` — add it to `.gitignore` if you'd rather not track it.
+
+> **No slash commands?** For agents that read a rule file but have no `/` commands (Cursor, Codex, Copilot…), the same contract works as a plain-text convention: prefix the message with `SIDENOTE:` and the agent parks it instead of acting. Add one line to your rule file so it's honored reliably — see [`commands/sidenote.md`](./commands/sidenote.md) for the exact contract.
+
 ## Install
 
 **One command — every agent on your machine:**

bin/install.js

@@ -130,12 +130,14 @@ function installClaude(dir, un) {
     removePath(path.join(dir, 'skills', 'skillify'));
     removePath(path.join(dir, 'skills', 'check-resolvable'));
     removePath(path.join(dir, 'commands', 'scalable.md'));
+    removePath(path.join(dir, 'commands', 'sidenote.md'));
     return;
   }
   fenceInto(path.join(dir, 'CLAUDE.md'), PRINCIPLES);
   copyDir(path.join(PKG, 'skills', 'skillify'), path.join(dir, 'skills', 'skillify'));
   copyDir(path.join(PKG, 'skills', 'check-resolvable'), path.join(dir, 'skills', 'check-resolvable'));
   writeFile(path.join(dir, 'commands', 'scalable.md'), fs.readFileSync(path.join(PKG, 'commands', 'scalable.md'), 'utf8'));
+  writeFile(path.join(dir, 'commands', 'sidenote.md'), fs.readFileSync(path.join(PKG, 'commands', 'sidenote.md'), 'utf8'));
 }
 
 function applyProvider(p, un) {

commands/sidenote.md

@@ -0,0 +1,21 @@
+---
+description: Park a passing thought as a later-task without derailing the current one — logged, not acted on.
+argument-hint: [thought to park — optional]
+---
+
+Park this thought — **$ARGUMENTS** — as a sidenote. A sidenote is a *later-task*, not a *now-task*. Your job is to record it and keep going, nothing more.
+
+**The contract — hold it exactly:**
+
+- **Do not act on it.** Don't investigate it, don't open the files it mentions, don't add it to your current plan, don't answer the question it poses. It is parked, not pending.
+- **Do not let it touch the current task.** Its scope, plan, priorities, and *pace* stay exactly as they were. In particular: **do not speed up or cut corners to "get to" the note.** The whole point of parking it is that it costs the current work nothing.
+- **Urgency doesn't override the contract.** If the note reads as urgent ("prod is down", "this is broken"), that's the wrong channel — a real emergency is a normal interruption, not a sidenote. Still just log it and resume; the human will escalate directly if they meant to.
+
+**Persist it so it survives this session** (context gets compacted; memory doesn't count as "logged"):
+
+1. Append one bullet to `.claude/sidenotes.md` at the project root — create the file (and `.claude/`) if missing.
+2. Format: `- [<today's date, YYYY-MM-DD>] <the thought, captured verbatim>`. Don't paraphrase or "improve" it — capture what was said.
+
+Then: **one-line acknowledgement** (e.g. `Parked in .claude/sidenotes.md — continuing.`) and **resume exactly where you left off**, as if the note had never arrived.
+
+**If `$ARGUMENTS` is empty** (a bare `/sidenote`), there's nothing to park — treat it as a *flush*: read `.claude/sidenotes.md` and list the currently-open sidenotes back to me so I can decide what to pick up. Change nothing, act on nothing, then resume.