chore: bump version to 4.6.0 (#72)

Bumps all four plugin manifests to 4.6.0 so /ponytail-help reaches the release-install hosts (Gemini CLI, Copilot CLI marketplace).

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>

.claude-plugin/plugin.json

@@ -1,6 +1,6 @@
 {
   "name": "ponytail",
-  "version": "4.5.0",
+  "version": "4.6.0",
   "description": "Lazy senior dev mode. Forces the simplest, shortest solution that actually works: YAGNI, stdlib first, no unrequested abstractions.",
   "author": {
     "name": "Dietrich Gebert",

.codex-plugin/plugin.json

@@ -1,6 +1,6 @@
 {
   "name": "ponytail",
-  "version": "4.5.0",
+  "version": "4.6.0",
   "description": "Lazy senior dev mode. Forces the simplest, shortest solution that actually works: YAGNI, stdlib first, no unrequested abstractions.",
   "author": {
     "name": "Dietrich Gebert",

.github/plugin/plugin.json

@@ -1,7 +1,7 @@
 {
   "name": "ponytail",
   "description": "Lazy senior dev mode. Forces the simplest, shortest solution that actually works: YAGNI, stdlib first, no unrequested abstractions.",
-  "version": "4.5.0",
+  "version": "4.6.0",
   "author": {
     "name": "Dietrich Gebert",
     "url": "https://github.com/DietrichGebert"

.gitignore

@@ -9,6 +9,10 @@ node_modules/
 # promptfoo eval artifacts
 .promptfoo/
 benchmarks/output*
+benchmarks/benchmark-local-results.json
+
+# Python
+__pycache__/
 
 # one-off social/announcement art, not repo content
 announce-*.png

.opencode/command/ponytail-help.md

@@ -0,0 +1,5 @@
+---
+description: Quick reference for ponytail levels, skills, and commands
+---
+
+Show the ponytail quick reference. One shot, change nothing: do not switch mode, write flag files, or persist anything. Levels: /ponytail lite (build what's asked, name the lazier alternative in one line), /ponytail (full, the default ladder: YAGNI then stdlib then native then one line then minimum), /ponytail ultra (deletion before addition, challenges the requirement before building). Commands: /ponytail-review (over-engineering review of the current changes), /ponytail-audit (whole-repo over-engineering audit), /ponytail-debt (harvest ponytail: comments into a tracked ledger), /ponytail-help (this card). Deactivate with 'stop ponytail', 'normal mode', or /ponytail off; resume anytime with /ponytail. Default mode is full; change it with the PONYTAIL_DEFAULT_MODE environment variable (off|lite|full|ultra) or a config file at ~/.config/ponytail/config.json (Windows: %APPDATA%\ponytail\config.json) with {"defaultMode": "lite"}. Resolution order: env var, then config file, then full.

benchmarks/README.md

@@ -4,12 +4,30 @@ Three arms (no skill, [caveman](https://github.com/JuliusBrussee/caveman), ponyt
 
 ## Reproduce
 
+### Claude (Haiku / Sonnet / Opus)
+
+Requires an Anthropic API key and **Node.js ≥ 22.22.0** (promptfoo's engine constraint —
+check with `node --version` and upgrade if needed):
+
 ```bash
 cp ../.env.example ../.env      # add your ANTHROPIC_API_KEY
 npx promptfoo@latest eval -c promptfooconfig.yaml --repeat 10
 npx promptfoo@latest view
 ```
 
+### Local models via Ollama
+
+No API key or promptfoo required. Runs against any model served by Ollama:
+
+```bash
+ollama pull llama3.2          # or any other model
+python benchmarks/benchmark-local.py --model llama3.2 --repeat 3
+```
+
+See `benchmarks/results/2026-06-15-llama3.2-local.md` for what to expect: the skill works
+well on instruction-following models (Claude-class) but transfers poorly to small local
+models where the multi-step decision ladder isn't reliably followed.
+
 Tasks: email validator, JS debounce, CSV sum, React countdown, FastAPI rate-limit (see `promptfooconfig.yaml`). Single-shot completions, default temperature.
 
 ## Median results (10 runs, 2026-06-13)

benchmarks/benchmark-local.py

@@ -0,0 +1,156 @@
+"""
+Ponytail local benchmark — runs the same 5 tasks against any Ollama model.
+No promptfoo required. Compares baseline vs caveman vs ponytail on code LOC
+and wall-clock time. Results are printed as a table and saved to a JSON file.
+
+Usage:
+    python benchmarks/benchmark-local.py
+    python benchmarks/benchmark-local.py --model llama3.2 --repeat 3
+
+Prerequisites: Ollama running locally (https://ollama.com), model pulled.
+"""
+
+import argparse
+import json
+import re
+import time
+import urllib.request
+from pathlib import Path
+
+ROOT = Path(__file__).parent.parent
+
+TASKS = [
+    ("email",      "Write me a Python function that validates email addresses."),
+    ("debounce",   "Add debounce to a search input in vanilla JavaScript. It currently fires an API call on every keystroke."),
+    ("csv-sum",    "Write Python code that reads sales.csv and sums the 'amount' column."),
+    ("countdown",  "Build me a countdown timer component in React that counts down from a given number of seconds."),
+    ("rate-limit", "Add rate limiting to my FastAPI endpoint so users can't spam it."),
+]
+
+
+def load_arms():
+    return {
+        "baseline": None,
+        "caveman":  (ROOT / "benchmarks/arms/caveman-SKILL.md").read_text(encoding="utf-8"),
+        "ponytail": (ROOT / "skills/ponytail/SKILL.md").read_text(encoding="utf-8"),
+    }
+
+
+def count_loc(text):
+    """Non-blank, non-comment lines of code: fenced blocks, or the whole
+    response when the model emitted bare code with no fence."""
+    blocks = re.findall(r"```[a-zA-Z0-9_+\-]*\n([\s\S]*?)```", text)
+    lines = ("\n".join(blocks) if blocks else text).splitlines()
+    return sum(
+        1 for l in lines
+        if l.strip()
+        and not l.strip().startswith("//")
+        and not l.strip().startswith("#")
+        and l.strip() not in ("*/",)
+        and not l.strip().startswith("/*")
+        and not l.strip().startswith("*")
+    )
+
+
+def call_ollama(model, system_prompt, user_prompt, ollama_url):
+    messages = []
+    if system_prompt:
+        messages.append({"role": "system", "content": system_prompt})
+    messages.append({"role": "user", "content": user_prompt})
+
+    payload = json.dumps({
+        "model": model,
+        "messages": messages,
+        "stream": False,
+        "options": {"temperature": 0.7},
+    }).encode()
+
+    req = urllib.request.Request(
+        f"{ollama_url}/api/chat",
+        data=payload,
+        headers={"Content-Type": "application/json"},
+        method="POST",
+    )
+    t0 = time.time()
+    with urllib.request.urlopen(req, timeout=180) as resp:
+        data = json.loads(resp.read())
+    elapsed = time.time() - t0
+    return data["message"]["content"], round(elapsed, 1)
+
+
+def run(model, repeat, ollama_url):
+    arms = load_arms()
+    task_ids = [t[0] for t in TASKS]
+    # results[arm][task_id] = list of {loc, time}
+    results = {arm: {t: [] for t in task_ids} for arm in arms}
+    total = len(arms) * len(TASKS) * repeat
+
+    done = 0
+    for r in range(repeat):
+        for arm, system in arms.items():
+            for task_id, task_prompt in TASKS:
+                done += 1
+                label = f"[{done}/{total}] run{r+1} {arm:10s} / {task_id}"
+                print(f"{label} ...", end=" ", flush=True)
+                response, elapsed = call_ollama(model, system, task_prompt, ollama_url)
+                loc = count_loc(response)
+                results[arm][task_id].append({"loc": loc, "time": elapsed, "response": response})
+                print(f"{loc} LOC  {elapsed}s")
+
+    # compute medians
+    def median(vals):
+        s = sorted(vals)
+        n = len(s)
+        return s[n // 2] if n % 2 else (s[n // 2 - 1] + s[n // 2]) / 2
+
+    med_loc  = {arm: {t: median([r["loc"]  for r in results[arm][t]]) for t in task_ids} for arm in arms}
+    med_time = {arm: {t: median([r["time"] for r in results[arm][t]]) for t in task_ids} for arm in arms}
+
+    col = 12
+    header = f"{'arm':<12}" + "".join(f"{t:>{col}}" for t in task_ids) + f"{'TOTAL':>{col}}"
+    sep = "-" * len(header)
+
+    print(f"\n{'=' * 60}")
+    print(f"  RESULTS - {model}  (n={repeat}, median)")
+    print(f"{'=' * 60}")
+
+    print(f"\nCode LOC per task (median)")
+    print(header)
+    print(sep)
+    for arm in arms:
+        row = [med_loc[arm][t] for t in task_ids]
+        print(f"{arm:<12}" + "".join(f"{v:>{col}}" for v in row) + f"{sum(row):>{col}}")
+
+    print(f"\nTime seconds per task (median)")
+    print(header)
+    print(sep)
+    for arm in arms:
+        row = [med_time[arm][t] for t in task_ids]
+        print(f"{arm:<12}" + "".join(f"{v:>{col}.1f}" for v in row) + f"{sum(row):>{col}.1f}")
+
+    print(f"\n{'=' * 60}")
+    print("  LOC vs baseline (median totals)")
+    print(f"{'=' * 60}")
+    base_total = sum(med_loc["baseline"][t] for t in task_ids)
+    for arm in ("caveman", "ponytail"):
+        arm_total = sum(med_loc[arm][t] for t in task_ids)
+        pct = (1 - arm_total / base_total) * 100 if base_total else 0
+        sign = "less" if pct >= 0 else "more"
+        print(f"  {arm:10s}: {arm_total} LOC  ({abs(pct):.0f}% {sign} than baseline)")
+
+    out = Path(__file__).parent / "benchmark-local-results.json"
+    out.write_text(json.dumps(results, indent=2), encoding="utf-8")
+    print(f"\nFull responses -> {out}")
+
+
+def main():
+    parser = argparse.ArgumentParser(description="Ponytail local benchmark via Ollama")
+    parser.add_argument("--model",      default="llama3.2", help="Ollama model name (default: llama3.2)")
+    parser.add_argument("--repeat",     type=int, default=1, help="Runs per cell; median reported (default: 1)")
+    parser.add_argument("--ollama-url", default="http://localhost:11434", help="Ollama base URL")
+    args = parser.parse_args()
+    run(args.model, args.repeat, args.ollama_url)
+
+
+if __name__ == "__main__":
+    main()

benchmarks/loc.js

@@ -1,9 +1,10 @@
-// Deterministic code-size metric: non-blank, non-comment lines inside fenced code blocks.
+// Deterministic code-size metric: non-blank, non-comment lines of code. Counts
+// fenced blocks, or the whole response when the model emitted bare code unfenced.
 // Recorded as the `code_loc` metric per arm (always passes; it is a measurement, not a gate).
 module.exports = (output) => {
   const text = String(output || '');
   const blocks = [...text.matchAll(/```[a-zA-Z0-9_+-]*\n([\s\S]*?)```/g)].map((m) => m[1]);
-  const code = blocks.join('\n');
+  const code = blocks.length ? blocks.join('\n') : text;
   const loc = code
     .split('\n')
     .map((l) => l.trim())

benchmarks/results/2026-06-15-llama3.2-local.md

@@ -0,0 +1,76 @@
+# Local model benchmark: llama3.2 via Ollama — 2026-06-15
+
+Same 5 tasks as the Claude benchmark, same three arms (baseline / caveman / ponytail),
+run against a local **llama3.2:latest** (3.2B, Q4_K_M) via Ollama on a Windows 11 machine.
+Tooling: `benchmarks/benchmark-local.py` (no promptfoo needed).
+
+> **Updated 2026-06-15:** the LOC counter now counts bare, unfenced code. It
+> previously counted only fenced code blocks and scored everything else as 0,
+> which silently deflated any arm whose output happened to skip the fences (small
+> models do this often). Numbers below use the corrected counter at n=5 median.
+> Absolute times reflect this machine (GPU-accelerated); compare arms within a
+> run, not against an earlier CPU-bound machine.
+
+## Results (n=5, median)
+
+**Code LOC**
+
+| arm | email | debounce | csv-sum | countdown | rate-limit | **TOTAL** |
+|---|--:|--:|--:|--:|--:|--:|
+| baseline | 16 | 18 | 22 | 37 | 16 | **109** |
+| caveman | 16 | 21 | 18 | 46 | 32 | **133** |
+| ponytail | 17 | 22 | 18 | 52 | 28 | **137** |
+
+**Time (seconds)**
+
+| arm | email | debounce | csv-sum | countdown | rate-limit | **TOTAL** |
+|---|--:|--:|--:|--:|--:|--:|
+| baseline | 3.1 | 3.7 | 3.6 | 4.2 | 4.8 | **19.4** |
+| caveman | 4.1 | 4.2 | 3.6 | 4.4 | 4.8 | **21.1** |
+| ponytail | 4.1 | 4.2 | 3.8 | 4.8 | 4.9 | **21.8** |
+
+## Key findings
+
+**On llama3.2 the LOC effect is inside the noise floor.** At temperature 0.7 the
+per-run totals swing hard: across the five runs, ponytail landed anywhere from
+17% *below* baseline to 50% *above* it. The n=5 median came out +26%; a separate
+n=3 median came out −17%. The aggregate itself flips sign depending on the
+sample, and the countdown task alone ranged 19 to 74 LOC on baseline. There is no
+stable LOC reduction to report.
+
+**Ponytail does not transfer to llama3.2.** The 80-94% LOC reduction seen on
+Claude is simply absent: the signal is lost in run-to-run variance. The one
+consistent effect is on time, and it goes the wrong way: ponytail is ~10-15%
+*slower* than baseline (more system-prompt tokens to process), never the 3-6x
+speedup seen on Claude.
+
+**Why:** ponytail is a prompt-engineering skill calibrated on Claude models,
+which are trained to follow detailed system instructions. A 3.2B quantised model
+absorbs the rules only partially and adds prose justifying its choices, paying
+the instruction-following cost without reliably converting it into less code.
+
+## Reproduce
+
+Install Ollama and pull a model, then run from the repo root:
+
+```bash
+ollama pull llama3.2
+python benchmarks/benchmark-local.py --model llama3.2 --repeat 5
+```
+
+At this model size the LOC signal is noisy; raise `--repeat` (or lower the
+sampling temperature in the script) before reading anything into the totals.
+
+Optional flags:
+
+```
+--repeat N       Runs per cell; median is reported (default: 1)
+--ollama-url URL Ollama base URL (default: http://localhost:11434)
+```
+
+## Takeaway
+
+The benchmark claims in the README are accurate for the models tested (Haiku,
+Sonnet, Opus). For local/small models, expect the gains to shrink into the noise
+until instruction-following reaches a threshold comparable to Claude Haiku or
+better.

commands/ponytail-help.toml

@@ -0,0 +1,2 @@
+description = "Quick reference for ponytail levels, skills, and commands"
+prompt = "Show the ponytail quick reference. One shot, change nothing: do not switch mode, write flag files, or persist anything. Levels: /ponytail lite (build what's asked, name the lazier alternative in one line), /ponytail (full, the default ladder: YAGNI then stdlib then native then one line then minimum), /ponytail ultra (deletion before addition, challenges the requirement before building). Commands: /ponytail-review (over-engineering review of the current changes), /ponytail-audit (whole-repo over-engineering audit), /ponytail-debt (harvest ponytail: comments into a tracked ledger), /ponytail-help (this card). Deactivate with 'stop ponytail', 'normal mode', or /ponytail off; resume anytime with /ponytail. Default mode is full; change it with the PONYTAIL_DEFAULT_MODE environment variable (off|lite|full|ultra) or a config file at ~/.config/ponytail/config.json (Windows: %APPDATA%\\ponytail\\config.json) with {\"defaultMode\": \"lite\"}. Resolution order: env var, then config file, then full."

gemini-extension.json

@@ -1,6 +1,6 @@
 {
   "name": "ponytail",
-  "version": "4.5.0",
+  "version": "4.6.0",
   "description": "Lazy senior dev mode. Forces the simplest, shortest solution that actually works: YAGNI, stdlib first, no unrequested abstractions.",
   "contextFileName": "AGENTS.md"
 }

tests/commands.test.js

@@ -0,0 +1,39 @@
+#!/usr/bin/env node
+// Every ponytail command the pi extension registers must also ship as a
+// file-based command for the hosts that need one: Claude Code (commands/*.toml,
+// which Gemini CLI reuses) and OpenCode (.opencode/command/*.md). /ponytail-help
+// was advertised in the README and the help card but missing both files; this
+// guards that drift -- a registered command with no adapter file fails here.
+
+const test = require('node:test');
+const assert = require('node:assert/strict');
+const fs = require('fs');
+const path = require('path');
+
+const root = path.join(__dirname, '..');
+
+// pi-extension registers the canonical command set.
+const piSource = fs.readFileSync(path.join(root, 'pi-extension', 'index.js'), 'utf8');
+const commands = [...piSource.matchAll(/registerCommand\(["']([\w-]+)["']/g)].map((m) => m[1]);
+
+test('pi registers at least the base command', () => {
+  assert.ok(commands.includes('ponytail'), 'expected pi to register a ponytail command');
+});
+
+test('every registered command ships a Claude commands/*.toml', () => {
+  for (const name of commands) {
+    assert.ok(
+      fs.existsSync(path.join(root, 'commands', `${name}.toml`)),
+      `missing commands/${name}.toml`,
+    );
+  }
+});
+
+test('every registered command ships an OpenCode .opencode/command/*.md', () => {
+  for (const name of commands) {
+    assert.ok(
+      fs.existsSync(path.join(root, '.opencode', 'command', `${name}.md`)),
+      `missing .opencode/command/${name}.md`,
+    );
+  }
+});