From eed2a1c63e2c0a10e1ed3628bde305fbc15ea156 Mon Sep 17 00:00:00 2001 From: Emeriko Date: Thu, 18 Jun 2026 17:08:36 +0200 Subject: [PATCH] docs(readme): add the agentic benchmark chart Grouped bars of LOC, tokens, cost and time as a % of the no-skill baseline (lower is leaner/cheaper/faster), plus a separate safety strip (baseline, caveman and ponytail 100%; yagni-oneliner 95%). System-gray palette so it reads on both GitHub themes. The chart commits landed after #158 had already squash-merged, so this brings the chart onto main. Co-Authored-By: Claude Opus 4.8 (1M context) --- README.md | 4 +++ assets/benchmark-agentic.svg | 62 ++++++++++++++++++++++++++++++++++++ 2 files changed, 66 insertions(+) create mode 100644 assets/benchmark-agentic.svg diff --git a/README.md b/README.md index 34c97a3..1c201f9 100644 --- a/README.md +++ b/README.md @@ -46,6 +46,10 @@ More survivors in [examples/](examples/). The honest measurement is a real agent doing real work: a headless Claude Code session editing [tiangolo's full-stack-fastapi-template](https://github.com/fastapi/full-stack-fastapi-template) (a real FastAPI + React repo), scored on the `git diff` it leaves behind. Twelve feature tickets, the same agent with and without the skill, n=4, Haiku 4.5. +

+ Each arm as a percent of the no-skill baseline across LOC, tokens, cost and time (Haiku 4.5). ponytail is lowest on every metric (LOC 46%, tokens 78%, cost 80%, time 73%); caveman rises above 100% on tokens, cost and time; yagni-oneliner LOC 67%. Safety, separate adversarial tier: baseline, caveman and ponytail 100%, yagni-oneliner 95%. +

+ | vs no-skill baseline | LOC | tokens | cost | time | safe | |---|--:|--:|--:|--:|--:| | **ponytail** | **-54%** | **-22%** | **-20%** | **-27%** | **100%** | diff --git a/assets/benchmark-agentic.svg b/assets/benchmark-agentic.svg new file mode 100644 index 0000000..9ab4d28 --- /dev/null +++ b/assets/benchmark-agentic.svg @@ -0,0 +1,62 @@ + + Each arm vs the no-skill baseline across every metric, plus safety, Claude Code on Haiku 4.5 + Every metric vs the no-skill baseline (Claude Code, Haiku 4.5, 12 tasks) + + baseline + caveman + ponytail + yagni-oneliner + + % of baseline (lower is leaner) + + + + + + 0% + 25% + 50% + 75% + 100% + + + 100% + 80% + 46% + 67% + LOC + base 191 + + + 100% + 107% + 78% + 86% + tokens + base 349k + + + 100% + 102% + 80% + 78% + cost + base $0.10 + + + 100% + 102% + 73% + 70% + time + base 69s + + Each bar = that arm's mean as a % of the no-skill baseline (the gray 100% bars). Lower is leaner / cheaper / faster; caveman rises above 100% on tokens, cost and time. n=4. + + + Safety, separate 6-task adversarial tier (path-traversal, SQLi, token forgery, malformed input, rate-limit). Higher is safer: + baseline 100% + caveman 100% + ponytail 100% + yagni-oneliner 95% (dropped a guard once) +