feat: add Factory Droid adapter, mode shortcuts, and custom skills

.factory-plugin/plugin.json

@@ -0,0 +1,10 @@
+{
+  "name": "ponytail",
+  "version": "4.8.3",
+  "description": "Lazy senior dev mode. Forces the simplest, shortest solution that actually works: YAGNI, stdlib first, no unrequested abstractions.",
+  "author": {
+    "name": "Dietrich Gebert",
+    "url": "https://github.com/DietrichGebert"
+  },
+  "hooks": "./hooks/factory-hooks.json"
+}

.openclaw/skills/ponytail-ask/SKILL.md

@@ -0,0 +1,8 @@
+---
+name: ponytail-ask
+description: "Clarify requirements and ask targeted questions to avoid spec building."
+homepage: https://github.com/DietrichGebert/ponytail
+license: MIT
+---
+
+Understand the user's requirements, clarify ambiguity, and ask targeted questions to refine the task before coding. Keep questions focused and concise, ensuring we only build what is actually requested and avoid speculative features.

.openclaw/skills/ponytail-help/SKILL.md

@@ -26,12 +26,15 @@ Level sticks until changed or session end.
 |-------|---------|--------------|
 | **ponytail** | `/ponytail` | Lazy mode itself. Simplest solution that works. |
 | **ponytail-review** | `/ponytail-review` | Over-engineering review: `L42: yagni: factory, one product. Inline.` |
+| **ponytail-audit** | `/ponytail-audit` | Whole-repo audit for over-engineering, ranked list of what to delete. |
+| **ponytail-debt** | `/ponytail-debt` | Harvest every ponytail: shortcut comment into one debt ledger. |
 | **ponytail-gain** | `/ponytail-gain` | Measured-impact scoreboard: less code, less cost, more speed. |
+| **ponytail-jedi** | `/ponytail-jedi` | SOTA research: search, rank, clone, modify, reuse trusted repos. |
+| **ponytail-plan** | `/ponytail-plan` | Create or simplify implementation plans to be clean, simple, and minimal. |
+| **ponytail-ask** | `/ponytail-ask` | Clarify requirements and ask targeted questions to avoid spec building. |
 | **ponytail-help** | `/ponytail-help` | This card. |
 
-Codex uses `@ponytail`, `@ponytail-review`, and `@ponytail-help`; Claude Code
-and OpenCode use the slash-command forms above (OpenCode ships `/ponytail` and
-`/ponytail-review`).
+Codex uses `@ponytail`, `@ponytail-review`, etc.; Claude Code, OpenCode, and Droid use the slash-command forms.
 
 ## Deactivate
 

.openclaw/skills/ponytail-jedi/SKILL.md

@@ -0,0 +1,8 @@
+---
+name: ponytail-jedi
+description: "SOTA research: search, rank, clone, modify, reuse trusted repos."
+homepage: https://github.com/DietrichGebert/ponytail
+license: MIT
+---
+
+Perform deep open-source SOTA (State of the Art) research for the given task. Do not start from scratch: search, rank, clone, modify, extract, or connect to world-class trusted repositories that can do part or all of the work. Find and reuse existing high-quality, trusted open-source code rather than reinventing the wheel.

.openclaw/skills/ponytail-plan/SKILL.md

@@ -0,0 +1,8 @@
+---
+name: ponytail-plan
+description: "Create or simplify implementation plans to be clean, simple, and minimal."
+homepage: https://github.com/DietrichGebert/ponytail
+license: MIT
+---
+
+Understand the user's task and create a clean, simple, and minimal implementation plan. Break down the task into component-level items and simplify the approach to avoid unnecessary abstractions, layers, or dependencies. If the user already has a plan, audit and simplify it to be clean and minimal.

.opencode/command/ponytail-ask.md

@@ -0,0 +1,5 @@
+---
+description: Clarify requirements and ask targeted questions to refine tasks before coding
+---
+
+Understand the user's requirements, clarify ambiguity, and ask targeted questions to refine the task before coding. Keep questions focused and concise, ensuring we only build what is actually requested and avoid speculative features.

.opencode/command/ponytail-jedi.md

@@ -0,0 +1,5 @@
+---
+description: Research SOTA open source solutions instead of starting from scratch
+---
+
+Perform deep open-source SOTA (State of the Art) research for the given task. Do not start from scratch: search, rank, clone, modify, extract, or connect to world-class trusted repositories that can do part or all of the work. Find and reuse existing high-quality, trusted open-source code rather than reinventing the wheel.

.opencode/command/ponytail-lightsaber.md

@@ -0,0 +1,5 @@
+---
+description: Research SOTA open source solutions instead of starting from scratch
+---
+
+Perform deep open-source SOTA (State of the Art) research for the given task. Do not start from scratch: search, rank, clone, modify, extract, or connect to world-class trusted repositories that can do part or all of the work. Find and reuse existing high-quality, trusted open-source code rather than reinventing the wheel.

.opencode/command/ponytail-plan.md

@@ -0,0 +1,5 @@
+---
+description: Create or simplify implementation plans to be clean, simple, and minimal
+---
+
+Understand the user's task and create a clean, simple, and minimal implementation plan. Break down the task into component-level items and simplify the approach to avoid unnecessary abstractions, layers, or dependencies. If the user already has a plan, audit and simplify it to be clean and minimal.

commands/ponytail-ask.toml

@@ -0,0 +1,2 @@
+description = "Clarify requirements and ask targeted questions to refine tasks before coding"
+prompt = "Understand the user's requirements, clarify ambiguity, and ask targeted questions to refine the task before coding. Keep questions focused and concise, ensuring we only build what is actually requested and avoid speculative features."

commands/ponytail-jedi.toml

@@ -0,0 +1,2 @@
+description = "Research SOTA open source solutions instead of starting from scratch"
+prompt = "Perform deep open-source SOTA (State of the Art) research for the given task. Do not start from scratch: search, rank, clone, modify, extract, or connect to world-class trusted repositories that can do part or all of the work. Find and reuse existing high-quality, trusted open-source code rather than reinventing the wheel."

commands/ponytail-lightsaber.toml

@@ -0,0 +1,2 @@
+description = "Research SOTA open source solutions instead of starting from scratch"
+prompt = "Perform deep open-source SOTA (State of the Art) research for the given task. Do not start from scratch: search, rank, clone, modify, extract, or connect to world-class trusted repositories that can do part or all of the work. Find and reuse existing high-quality, trusted open-source code rather than reinventing the wheel."

commands/ponytail-plan.toml

@@ -0,0 +1,2 @@
+description = "Create or simplify implementation plans to be clean, simple, and minimal"
+prompt = "Understand the user's task and create a clean, simple, and minimal implementation plan. Break down the task into component-level items and simplify the approach to avoid unnecessary abstractions, layers, or dependencies. If the user already has a plan, audit and simplify it to be clean and minimal."

docs/agent-portability.md

@@ -19,6 +19,7 @@ to load in a given agent.
 | Cline | `.clinerules/ponytail.md` | Project rule. |
 | GitHub Copilot | `.github/copilot-instructions.md` | Repository instruction file. |
 | GitHub Copilot CLI | `.github/plugin/`, `AGENTS.md`, `.github/copilot-instructions.md`, `~/.copilot/copilot-instructions.md` | Plugin-supported (`copilot plugin marketplace add DietrichGebert/ponytail` + `copilot plugin install ponytail@ponytail`). Fallback instruction mode remains: per-project from `AGENTS.md` or `.github/copilot-instructions.md`, or globally from `~/.copilot/copilot-instructions.md` (instruction-tier, no `/ponytail` levels or hooks). |
+| Factory Droid | `.factory-plugin/plugin.json`, `hooks/factory-hooks.json`, `skills/`, `hooks/`, `AGENTS.md` | Plugin install with session activation, mode tracking, and commands. Fallback instruction mode: copy `AGENTS.md` + `skills/` to `~/.factory/` or repo root. |
 | Antigravity | `AGENTS.md` | Reads `AGENTS.md` at the repo root as always-on rules (like `.cursorrules`/`CLAUDE.md`); `.agents/rules/` also works for workspace rules. Instruction-tier. |
 | CodeWhale | `AGENTS.md` | Reads `AGENTS.md` from the repo root as project instructions; also reads `CLAUDE.md` and `.claude/instructions.md` as fallbacks. Instruction-tier. |
 | Swival | `.swival/skills/`, `AGENTS.md` | `swival skills add https://github.com/DietrichGebert/ponytail` installs the six skills straight into `.swival/skills/`. Add `--global` to stage them in the library (`~/.config/swival/library`) first, then `swival skills add ponytail` (or `--global ponytail`) to activate per-project or everywhere. Also reads `AGENTS.md` from the repo root and `~/.config/swival/AGENTS.md` globally as instruction-tier fallback. |

hooks/factory-hooks.json

@@ -0,0 +1,44 @@
+{
+  "hooks": {
+    "SessionStart": [
+      {
+        "matcher": "startup|resume|clear|compact",
+        "hooks": [
+          {
+            "type": "command",
+            "command": "node \"${DROID_PLUGIN_ROOT}/hooks/ponytail-activate.js\"; exit 0",
+            "commandWindows": "if (Get-Command node -ErrorAction SilentlyContinue) { node \"$env:DROID_PLUGIN_ROOT\\hooks\\ponytail-activate.js\" }",
+            "timeout": 5,
+            "statusMessage": "Loading ponytail mode..."
+          }
+        ]
+      }
+    ],
+    "SubagentStart": [
+      {
+        "hooks": [
+          {
+            "type": "command",
+            "command": "node \"${DROID_PLUGIN_ROOT}/hooks/ponytail-subagent.js\"; exit 0",
+            "commandWindows": "if (Get-Command node -ErrorAction SilentlyContinue) { node \"$env:DROID_PLUGIN_ROOT\\hooks\\ponytail-subagent.js\" }",
+            "timeout": 5,
+            "statusMessage": "Loading ponytail mode..."
+          }
+        ]
+      }
+    ],
+    "UserPromptSubmit": [
+      {
+        "hooks": [
+          {
+            "type": "command",
+            "command": "node \"${DROID_PLUGIN_ROOT}/hooks/ponytail-mode-tracker.js\"; exit 0",
+            "commandWindows": "if (Get-Command node -ErrorAction SilentlyContinue) { node \"$env:DROID_PLUGIN_ROOT\\hooks\\ponytail-mode-tracker.js\" }",
+            "timeout": 5,
+            "statusMessage": "Tracking ponytail mode..."
+          }
+        ]
+      }
+    ]
+  }
+}

hooks/ponytail-activate.js

@@ -14,6 +14,7 @@ const {
   clearMode,
   isCodex,
   isCopilot,
+  isDroid,
   setMode,
   writeHookOutput,
 } = require('./ponytail-runtime');
@@ -42,7 +43,7 @@ try {
 let output = getPonytailInstructions(mode);
 
 // 3. Detect missing statusline config — nudge Claude to help set it up
-if (!isCodex && !isCopilot) try {
+if (!isCodex && !isCopilot && !isDroid) try {
   let hasStatusline = false;
   if (fs.existsSync(settingsPath)) {
     // Strip UTF-8 BOM some editors prepend on Windows (breaks JSON.parse)

hooks/ponytail-runtime.js

@@ -1,14 +1,17 @@
 const fs = require('fs');
 const path = require('path');
+const os = require('os');
 const { getClaudeDir } = require('./ponytail-config');
 
 const STATE_FILE = '.ponytail-active';
 const isCopilot = Boolean(process.env.COPILOT_PLUGIN_DATA);
 const isCodex = !isCopilot && Boolean(process.env.PLUGIN_DATA);
+const isDroid = !isCopilot && !isCodex && Boolean(process.env.DROID_PLUGIN_ROOT);
 
 let stateDir = getClaudeDir();
 if (isCodex) stateDir = process.env.PLUGIN_DATA;
 if (isCopilot) stateDir = process.env.COPILOT_PLUGIN_DATA;
+if (isDroid) stateDir = process.env.DROID_CONFIG_DIR || path.join(os.homedir(), '.factory');
 
 const statePath = path.join(stateDir, STATE_FILE);
 
@@ -37,7 +40,7 @@ function writeHookOutput(event, mode, context = '') {
       event === 'SessionStart' && context ? { additionalContext: context } : {}));
     return;
   }
-  if (isCodex) {
+  if (isCodex || isDroid) {
     const output = { systemMessage: `PONYTAIL:${mode.toUpperCase()}` };
     if (context) {
       output.hookSpecificOutput = {
@@ -62,6 +65,7 @@ module.exports = {
   clearMode,
   isCodex,
   isCopilot,
+  isDroid,
   readMode,
   setMode,
   writeHookOutput,

pi-extension/index.js

@@ -155,6 +155,63 @@ export default function ponytailExtension(pi) {
     handler: (_args, ctx) => sendAlias("/skill:ponytail-help", "", ctx),
   });
 
+  pi.registerCommand("ponytail-jedi", {
+    description: "Run /skill:ponytail-jedi",
+    handler: (_args, ctx) => sendAlias("/skill:ponytail-jedi", "", ctx),
+  });
+
+  pi.registerCommand("ponytail-lightsaber", {
+    description: "Run /skill:ponytail-jedi (research)",
+    handler: (_args, ctx) => sendAlias("/skill:ponytail-jedi", "", ctx),
+  });
+
+  pi.registerCommand("ponytail-plan", {
+    description: "Run /skill:ponytail-plan",
+    handler: (_args, ctx) => sendAlias("/skill:ponytail-plan", "", ctx),
+  });
+
+  pi.registerCommand("ponytail-ask", {
+    description: "Run /skill:ponytail-ask",
+    handler: (_args, ctx) => sendAlias("/skill:ponytail-ask", "", ctx),
+  });
+
+  pi.registerShortcut("ponytail:cycleMode", {
+    description: "Cycle ponytail modes (off -> lite -> full -> ultra -> off)",
+    handler: async (ctx) => {
+      const nextModes = { off: "lite", lite: "full", full: "ultra", ultra: "off" };
+      const nextMode = nextModes[currentMode] || "full";
+      setMode(nextMode, ctx);
+    },
+  });
+
+  pi.registerShortcut("ponytail:modeLite", {
+    description: "Set ponytail mode to lite",
+    handler: async (ctx) => {
+      setMode("lite", ctx);
+    },
+  });
+
+  pi.registerShortcut("ponytail:modeFull", {
+    description: "Set ponytail mode to full",
+    handler: async (ctx) => {
+      setMode("full", ctx);
+    },
+  });
+
+  pi.registerShortcut("ponytail:modeUltra", {
+    description: "Set ponytail mode to ultra",
+    handler: async (ctx) => {
+      setMode("ultra", ctx);
+    },
+  });
+
+  pi.registerShortcut("ponytail:modeOff", {
+    description: "Turn ponytail mode off",
+    handler: async (ctx) => {
+      setMode("off", ctx);
+    },
+  });
+
   pi.on("input", async (event) => {
     if (event?.source === "extension") return;
 

pi-extension/test/extension.test.js

@@ -9,6 +9,7 @@ import ponytailExtension from "../index.js";
 function createPiHarness() {
   const events = new Map();
   const commands = new Map();
+  const shortcuts = new Map();
   const appendedEntries = [];
   const sentUserMessages = [];
 
@@ -19,6 +20,9 @@ function createPiHarness() {
     registerCommand(name, options) {
       commands.set(name, options);
     },
+    registerShortcut(keyId, options) {
+      shortcuts.set(keyId, options);
+    },
     appendEntry(customType, data) {
       appendedEntries.push({ customType, data });
     },
@@ -28,7 +32,7 @@ function createPiHarness() {
   };
 
   ponytailExtension(pi);
-  return { events, commands, appendedEntries, sentUserMessages };
+  return { events, commands, shortcuts, appendedEntries, sentUserMessages };
 }
 
 function createCommandContext(overrides = {}) {
@@ -57,7 +61,36 @@ function withTempConfig(fn) {
 test("extension registers Ponytail commands", () => {
   const { commands } = createPiHarness();
 
-  assert.deepEqual([...commands.keys()].sort(), ["ponytail", "ponytail-audit", "ponytail-debt", "ponytail-gain", "ponytail-help", "ponytail-review"]);
+  assert.deepEqual(
+    [...commands.keys()].sort(),
+    [
+      "ponytail",
+      "ponytail-ask",
+      "ponytail-audit",
+      "ponytail-debt",
+      "ponytail-gain",
+      "ponytail-help",
+      "ponytail-jedi",
+      "ponytail-lightsaber",
+      "ponytail-plan",
+      "ponytail-review",
+    ]
+  );
+});
+
+test("extension registers Ponytail shortcuts", () => {
+  const { shortcuts } = createPiHarness();
+
+  assert.deepEqual(
+    [...shortcuts.keys()].sort(),
+    [
+      "ponytail:cycleMode",
+      "ponytail:modeFull",
+      "ponytail:modeLite",
+      "ponytail:modeOff",
+      "ponytail:modeUltra",
+    ]
+  );
 });
 
 test("/ponytail updates session mode and injects instructions", async () => withTempConfig(async () => {

plugin.yaml

@@ -12,10 +12,17 @@ provides_commands:
   - ponytail-debt
   - ponytail-gain
   - ponytail-help
+  - ponytail-jedi
+  - ponytail-lightsaber
+  - ponytail-plan
+  - ponytail-ask
 provides_skills:
   - ponytail
   - ponytail-review
   - ponytail-audit
   - ponytail-debt
   - ponytail-gain
   - ponytail-help
+  - ponytail-jedi
+  - ponytail-plan
+  - ponytail-ask

scripts/build-openclaw-skills.js

@@ -23,6 +23,9 @@ const DESCRIPTIONS = {
   'ponytail-debt': 'Harvest every ponytail: shortcut comment into one debt ledger, so deferrals get tracked instead of forgotten. One-shot report.',
   'ponytail-gain': 'Show ponytail measured impact as a scoreboard: less code, less cost, more speed, from the benchmark medians. One-shot display.',
   'ponytail-help': "Quick reference for ponytail's modes, skills, and commands. One-shot display.",
+  'ponytail-jedi': 'SOTA research: search, rank, clone, modify, reuse trusted repos.',
+  'ponytail-plan': 'Create or simplify implementation plans to be clean, simple, and minimal.',
+  'ponytail-ask': 'Clarify requirements and ask targeted questions to avoid spec building.',
 };
 
 const NAMES = Object.keys(DESCRIPTIONS);

skills/ponytail-ask/SKILL.md

@@ -0,0 +1,9 @@
+---
+name: ponytail-ask
+description: >
+  Clarify requirements and ask targeted questions to refine tasks before writing code.
+  Ensures we only build what is requested. Use when the user says "ask questions",
+  "clarify requirements", "what is needed", or invokes /ponytail-ask.
+---
+
+Understand the user's requirements, clarify ambiguity, and ask targeted questions to refine the task before coding. Keep questions focused and concise, ensuring we only build what is actually requested and avoid speculative features.

skills/ponytail-help/SKILL.md

@@ -27,12 +27,15 @@ Level sticks until changed or session end.
 |-------|---------|--------------|
 | **ponytail** | `/ponytail` | Lazy mode itself. Simplest solution that works. |
 | **ponytail-review** | `/ponytail-review` | Over-engineering review: `L42: yagni: factory, one product. Inline.` |
+| **ponytail-audit** | `/ponytail-audit` | Whole-repo audit for over-engineering, ranked list of what to delete. |
+| **ponytail-debt** | `/ponytail-debt` | Harvest every ponytail: shortcut comment into one debt ledger. |
 | **ponytail-gain** | `/ponytail-gain` | Measured-impact scoreboard: less code, less cost, more speed. |
+| **ponytail-jedi** | `/ponytail-jedi` | SOTA research: search, rank, clone, modify, reuse trusted repos. |
+| **ponytail-plan** | `/ponytail-plan` | Create or simplify implementation plans to be clean, simple, and minimal. |
+| **ponytail-ask** | `/ponytail-ask` | Clarify requirements and ask targeted questions to avoid spec building. |
 | **ponytail-help** | `/ponytail-help` | This card. |
 
-Codex uses `@ponytail`, `@ponytail-review`, and `@ponytail-help`; Claude Code
-and OpenCode use the slash-command forms above (OpenCode ships `/ponytail` and
-`/ponytail-review`).
+Codex uses `@ponytail`, `@ponytail-review`, etc.; Claude Code, OpenCode, and Droid use the slash-command forms.
 
 ## Deactivate
 

skills/ponytail-jedi/SKILL.md

@@ -0,0 +1,10 @@
+---
+name: ponytail-jedi
+description: >
+  Search, rank, clone, modify, extract, or connect to world-class trusted open-source
+  repositories. SOTA research to avoid starting from scratch. Use when the user says
+  "research SOTA", "use open-source repos", "find a trusted repo", or invokes
+  /ponytail-jedi / /ponytail-lightsaber.
+---
+
+Perform deep open-source SOTA (State of the Art) research for the given task. Do not start from scratch: search, rank, clone, modify, extract, or connect to world-class trusted repositories that can do part or all of the work. Find and reuse existing high-quality, trusted open-source code rather than reinventing the wheel.