DietrichGebertandClaude Opus 4.8
45f7d2f83f
* docs: correct cost claim to 42-75% from 30-rep re-verification Re-ran the cost benchmark at 30 reps per cell on Claude (Haiku/Sonnet/Opus): ponytail is 42-75% cheaper than no-skill, not the previously published 47-77%. The direction holds, both ends came in a few points lower. Updates the README headline and body, the benchmark chart subtitle, and the benchmarks/README cost table, and adds a dated results doc with full method. Also adds the OpenAI (gpt-4.1-mini/gpt-5.4-mini/gpt-5.5) and Gemini configs. On OpenAI reasoning models ponytail costs more, not less, so the claim stays Claude-scoped. Gemini run pending a fresh-quota day. Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com> * docs: scope the body claim to Claude models "on every model" read as cross-provider, but the 30-rep verification shows the cost win reverses on OpenAI reasoning models. Match the caption and benchmarks/README, which already say Claude. Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com> * docs: reframe the pitch as the discipline, not token savings The cost/code/latency numbers vary by model and on some (terse reasoning models like GPT-5.5) ponytail costs more, so leading with them as a universal win was misleading. Adds model-variance to the headline caption and a paragraph making the stated point the mental model: write only what the task needs, safety kept, maintainable code. Savings are a model-dependent side effect. Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com> * docs: name the ladder's reasoning cost The ladder is a deliberation step: on reasoning models the agent spends thinking tokens working through the rungs before it saves any output, which together with the always-on ruleset can outweigh the shorter code. Makes the GPT-5.5 cost increase legible rather than just stating it. Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com> * docs: state the single-shot limitation honestly The benchmark is single-shot (one prompt, one completion); it does not measure a real multi-turn agent session, where the ruleset re-injects and the ladder deliberates every turn. Adds that caveat to the README, and corrects the benchmarks/README note that claimed caching widens the gap "in ponytail's favor" (unverified, and a measured agentic A/B in #121 found the opposite can happen). Per-session cost can land either way. Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com> * docs: fix run count in caption (cost is 30 runs, not 10) Cost was re-verified at 30 reps; code and latency are still the original 10. The headline caption said "10 runs" across the board, which undersold the cost verification. Now states the split, matching benchmarks/README. Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com> * fix(examples): replace hand-written examples with real benchmark output The examples/ before/after blocks were authored by hand, not produced by a model. Issue #127 correctly noted that nobody hand-rolls quicksort for "sort this array" - every model just calls .sort(). Regenerate all examples verbatim from a real benchmark run (Claude Haiku 4.5, no-skill arm vs ponytail arm, benchmarks/output.json) so the before/after is reproducible, not authored: email 75->3, debounce 116->10, csv 20->3, countdown 267->9, rate-limit 128->10 LOC - Delete sorting.md (pure strawman) plus the other hand-written caricatures (api-endpoint, caching, date-picker) - Add benchmarks/generate-examples.mjs to regenerate examples from any run - examples/README.md indexes the set and documents how to reproduce Closes #127 Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com> --------- Co-authored-by: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
Benchmark
Three arms (no skill, caveman, ponytail), three models, five everyday tasks, 10 runs per cell, median reported. Code LOC is counted from fenced code blocks; tokens, cost, and latency come straight from the API.
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):
cp ../.env.example ../.env # add your ANTHROPIC_API_KEY
npx promptfoo@latest eval -c promptfooconfig.yaml --env-file ../.env --repeat 10
npx promptfoo@latest view
--env-file ../.env is required because promptfoo reads .env from the current
directory (benchmarks/), not the repo root where the file lives.
Local models via Ollama
No API key or promptfoo required. Runs against any model served by Ollama:
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; cost re-verified at 30 runs, 2026-06-17)
Code (lines)
| arm | Haiku | Sonnet | Opus |
|---|---|---|---|
| baseline (no skill) | 518 | 693 | 256 |
| caveman | 116 | 120 | 67 |
| ponytail | 39 | 44 | 51 |
Cost (USD, 5 tasks; 30 runs, 2026-06-17)
| arm | Haiku | Sonnet | Opus |
|---|---|---|---|
| baseline (no skill) | 0.030 | 0.137 | 0.137 |
| caveman | 0.014 | 0.046 | 0.072 |
| ponytail | 0.011 | 0.035 | 0.079 |
Latency (seconds, 5 tasks)
| arm | Haiku | Sonnet | Opus |
|---|---|---|---|
| baseline (no skill) | 37.7 | 124.1 | 58.7 |
| caveman | 14.9 | 34.7 | 23.1 |
| ponytail | 9.9 | 20.1 | 18.0 |
Versus baseline, ponytail writes 80-94% less code, costs 42-75% less, and runs 3-6x faster, on every Claude model. Cost re-verified at 30 reps, with OpenAI and Gemini arms, in results/2026-06-17-cost-verification.md.
Metrics
| File | Metric | Behavior |
|---|---|---|
loc.js |
loc |
Measurement - always passes, records line count |
correctness.js |
correct |
Gate - fails if generated code doesn't work |
correctness.js extracts fenced code blocks and runs per-task checks (spawns Python/Node for email, debounce, CSV; structural regex for React and FastAPI). A broken one-liner that scores great on LOC will fail on correctness.
Note: The React countdown and FastAPI rate-limit checks are keyword/structural only (no runtime execution), so they verify plausible structure rather than full correctness. The email, debounce, and CSV checks execute the code.
Prerequisites
Running the benchmark requires Python 3, pandas, and Node.js (18+).
Notes
- Caveman is a prose-compression skill (it leaves code "normal"), so it lands between baseline and ponytail on code size and wins mainly on prose tokens.
- Cost reflects single-shot calls (one prompt, one completion), not real multi-turn agent sessions. In a session the ruleset re-injects and the ladder deliberates every turn across many turns, so per-session cost can come out higher or lower than these numbers. Prompt caching offsets some of the re-injection, but a measured agentic A/B (#121) found ponytail can also raise tool calls and cost on completion-forced tasks. Treat these as generation numbers, not a session-cost promise.
- These are everyday tasks. For production-grade specs, where an unconstrained agent bloats much harder, see the writeups in
results/.