rename /scalable command to /pressure-test

.claude-plugin/marketplace.json

@@ -1,15 +1,15 @@
 {
   "$schema": "https://anthropic.com/claude-code/marketplace.schema.json",
   "name": "greybeard",
-  "description": "Greybeard — Karpathy-inspired coding-agent guidelines, the skillify / check-resolvable meta-skills, and the /scalable decision test.",
+  "description": "Greybeard — Karpathy-inspired coding-agent guidelines, the skillify / check-resolvable meta-skills, and the /pressure-test decision test.",
   "owner": {
     "name": "Clawnify",
     "url": "https://github.com/clawnify"
   },
   "plugins": [
     {
       "name": "greybeard",
-      "description": "skillify + check-resolvable skills and the /scalable command. Pair with the npx installer for the always-on guidelines.",
+      "description": "skillify + check-resolvable skills and the /pressure-test command. Pair with the npx installer for the always-on guidelines.",
       "source": "./",
       "category": "productivity"
     }

.claude-plugin/plugin.json

@@ -1,6 +1,6 @@
 {
   "name": "greybeard",
-  "description": "Karpathy-inspired coding-agent skills: skillify (capture repeated work), check-resolvable (keep skills DRY + MECE), and the /scalable decision test.",
+  "description": "Karpathy-inspired coding-agent skills: skillify (capture repeated work), check-resolvable (keep skills DRY + MECE), and the /pressure-test decision test.",
   "author": {
     "name": "Clawnify",
     "url": "https://github.com/clawnify"

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, 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.
+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), its two main commands — [`/pressure-test`](#the-pressure-test-command), the decision test, and [`/sidenote`](#the-sidenote-command), park-a-thought — and a [one-command installer](#install) that fans it all out to every AI coding agent you use.
 
 ## The Problems
 
@@ -182,17 +182,21 @@ The principle above ships as two runnable meta-skills in [`skills/`](./skills) 
 
 They're standard [Claude Code Agent Skills](https://code.claude.com/docs/en/skills) (portable to Cursor, Codex, OpenClaw). Install and usage: [`skills/README.md`](./skills/README.md).
 
-## The `/scalable` command
+## The two main commands
 
-[`commands/scalable.md`](./commands/scalable.md) is a Claude Code slash command that runs the §5 decision test on demand: pressure-test the approach on the table against **scalable / long-term / efficient** — *whatever is scalable, long term, and cannot be done in a more efficient way* — and get one decisive recommendation, with stale-time-budget shortcuts called out.
+Greybeard's two flagship slash commands are **`/pressure-test`** and **`/sidenote`** — one guards the *quality* of a decision, the other guards your *focus* while you make it. The skills and always-on guidelines back them up, but these are the two you'll reach for by hand.
+
+## The `/pressure-test` command
+
+[`commands/pressure-test.md`](./commands/pressure-test.md) is a Claude Code slash command that runs the §5 decision test on demand: pressure-test the approach on the table against **scalable / long-term / efficient** — *whatever is scalable, long term, and cannot be done in a more efficient way* — and get one decisive recommendation, with stale-time-budget shortcuts called out.
 
 ```bash
 mkdir -p ~/.claude/commands
-cp commands/scalable.md ~/.claude/commands/      # personal, all projects
+cp commands/pressure-test.md ~/.claude/commands/      # personal, all projects
 # or: .claude/commands/  for one project
 ```
 
-Then `/scalable` (tests the current direction) or `/scalable <a specific decision>`.
+Then `/pressure-test` (tests the current direction) or `/pressure-test <a specific decision>`.
 
 ## The `/sidenote` command
 
@@ -218,7 +222,7 @@ Then `/sidenote <the thought>` to park one, or `/sidenote` to see what's parked.
 npx @clawnify/greybeard
 ```
 
-It detects the AI coding agents you actually use and installs the right files for each: the seven guidelines into the rule file each one reads (`CLAUDE.md`, `AGENTS.md`, `GEMINI.md`, `.cursor/rules/`, `.windsurf/rules/`, `.clinerules/`, `.github/copilot-instructions.md`), plus the `skillify` / `check-resolvable` skills and the `/scalable` command for Claude Code and OpenClaw. Shared files are edited between markers, so re-running is a safe no-op and your own content is preserved.
+It detects the AI coding agents you actually use and installs the right files for each: the seven guidelines into the rule file each one reads (`CLAUDE.md`, `AGENTS.md`, `GEMINI.md`, `.cursor/rules/`, `.windsurf/rules/`, `.clinerules/`, `.github/copilot-instructions.md`), plus the `skillify` / `check-resolvable` skills and the `/pressure-test` command for Claude Code and OpenClaw. Shared files are edited between markers, so re-running is a safe no-op and your own content is preserved.
 
 ```bash
 npx @clawnify/greybeard --list        # show detected agents
@@ -230,14 +234,14 @@ npx @clawnify/greybeard --uninstall   # remove what it added
 
 Supported: **Claude Code, Cursor, Windsurf, Cline, GitHub Copilot, Codex, Gemini CLI, OpenClaw** — and any agent that reads `CLAUDE.md` / `AGENTS.md`.
 
-**Claude Code plugin marketplace** (the skills + `/scalable` + always-on guidelines):
+**Claude Code plugin marketplace** (the skills + `/pressure-test` + always-on guidelines):
 
 ```
 /plugin marketplace add clawnify/greybeard
 /plugin install greybeard
 ```
 
-The plugin ships a `SessionStart` / `SubagentStart` hook that injects the three-pillars decision test (scalable / long term / efficient — the core of `/scalable`) into every session automatically — installing the plugin is enough, no per-project `npx` run needed. It's careful not to double up: if the full guidelines are already in your `~/.claude/CLAUDE.md` or a project's `CLAUDE.md` / `AGENTS.md` (via the npx installer or a hand-merge), the hook detects them and stays silent. To turn injection off without uninstalling, set `GREYBEARD=off` in your environment.
+The plugin ships a `SessionStart` / `SubagentStart` hook that injects the three-pillars decision test (scalable / long term / efficient — the core of `/pressure-test`) into every session automatically — installing the plugin is enough, no per-project `npx` run needed. It's careful not to double up: if the full guidelines are already in your `~/.claude/CLAUDE.md` or a project's `CLAUDE.md` / `AGENTS.md` (via the npx installer or a hand-merge), the hook detects them and stays silent. To turn injection off without uninstalling, set `GREYBEARD=off` in your environment.
 
 **Manual** (just the guidelines, one file — no Node):
 

bin/install.js

@@ -4,7 +4,7 @@
 // greybeard — cross-platform installer.
 //
 // Detects the AI coding agents on your machine / in this project and installs
-// the Karpathy-inspired guidelines (+ Claude Code skills and the /scalable
+// the Karpathy-inspired guidelines (+ Claude Code skills and the /pressure-test
 // command) into each one's rule location. Pure Node stdlib, zero runtime deps.
 //
 //   npx @clawnify/greybeard            # install for every detected agent
@@ -144,14 +144,16 @@ function installClaude(dir, un) {
     removeFenceFrom(path.join(dir, 'CLAUDE.md'));
     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', 'scalable.md')); // legacy name, pre-rename
+    removePath(path.join(dir, 'commands', 'pressure-test.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'));
+  removePath(path.join(dir, 'commands', 'scalable.md')); // clean up the pre-rename command from prior installs
+  writeFile(path.join(dir, 'commands', 'pressure-test.md'), fs.readFileSync(path.join(PKG, 'commands', 'pressure-test.md'), 'utf8'));
   writeFile(path.join(dir, 'commands', 'sidenote.md'), fs.readFileSync(path.join(PKG, 'commands', 'sidenote.md'), 'utf8'));
 }
 

hooks/greybeard-activate.js

@@ -4,7 +4,7 @@
 // greybeard — SessionStart / SubagentStart hook.
 //
 // Injects the three-pillars decision test (scalable / long term / efficient —
-// the core of the /scalable command) as hidden context so installing the
+// the core of the /pressure-test command) as hidden context so installing the
 // plugin is enough — no per-project `npx @clawnify/greybeard` needed.
 // Skips injection when the full guidelines are already loaded another way:
 //
@@ -48,7 +48,7 @@ function alreadyLoaded(cwd) {
   return false;
 }
 
-// The three pillars, condensed from commands/scalable.md — the single
+// The three pillars, condensed from commands/pressure-test.md — the single
 // question that governs every decision. Keep wording in sync with that file.
 const PILLARS = `GREYBEARD ACTIVE — judge every decision against the three pillars: whatever is **scalable**, **long term**, and **cannot be done in a more efficient way**.
 
@@ -62,7 +62,7 @@ If the pillars aren't concrete for the decision at hand, define them first: name
 
 "No time to do it properly" is usually a stale pre-AI estimate; the proper version often fits this session. If it genuinely doesn't, say so and let the user decide — don't silently downgrade to the shortcut. When a shortcut is right, mark it inline with its ceiling and upgrade trigger.
 
-For contested decisions, run the /scalable command (greybeard:scalable) to pressure-test the approach.`;
+For contested decisions, run the /pressure-test command (greybeard:pressure-test) to pressure-test the approach.`;
 
 function main() {
   if ((process.env.GREYBEARD || '').trim().toLowerCase() === 'off') return;

package.json

@@ -1,7 +1,7 @@
 {
   "name": "@clawnify/greybeard",
   "version": "0.1.0",
-  "description": "Greybeard — Karpathy-inspired guardrails that make your AI coding agent behave like a principled senior engineer. Guidelines + skillify / check-resolvable skills + the /scalable decision test, installable across every AI coding agent.",
+  "description": "Greybeard — Karpathy-inspired guardrails that make your AI coding agent behave like a principled senior engineer. Guidelines + skillify / check-resolvable skills + the /pressure-test decision test, installable across every AI coding agent.",
   "license": "MIT",
   "homepage": "https://github.com/clawnify/greybeard",
   "repository": {