@@ -30,7 +30,7 @@
 </p>
 
 <p align="center">
-  <strong>~54% less code (up to 94%) &middot; ~20% cheaper &middot; ~27% faster &middot; 100% safe</strong><br>
+  <strong>~54% less code (up to 94% on one task) &middot; ~20% cheaper &middot; ~27% faster &middot; safe in 20/20 adversarial runs</strong><br>
   <sub>Real Claude Code sessions editing a real FastAPI + React repo, the same agent with and without the skill (12 feature tasks, Haiku 4.5, n=4). <a href="#numbers">Details</a>.</sub>
 </p>
 
@@ -81,7 +81,7 @@ codex plugin marketplace add DietrichGebert/ponytail
 codex plugin add ponytail@ponytail
 ```
 
-Then open `/hooks` in Codex, trust its two lifecycle hooks, and start a new thread.
+Then open `/hooks` in Codex, trust its lifecycle hooks, and start a new thread.
 
 **Any other agent:** copy [`AGENTS.md`](AGENTS.md) into your project, or ask your agent to install [`skills/ponytail/SKILL.md`](skills/ponytail/SKILL.md) as a skill. Step by step for Copilot, Cursor, OpenCode, Gemini and the rest: **[INSTALL.md](INSTALL.md)**.
 
@@ -133,14 +133,14 @@ Lazy, not negligent: trust-boundary validation, data-loss handling, security, an
 | `/ponytail-gain` | Show the measured impact scoreboard (less code, less cost, more speed) from the benchmark. |
 | `/ponytail-help` | Quick reference for the commands above. |
 
-Commands need a skill-capable host (Claude Code, Codex, Devin CLI, OpenCode, Gemini, pi, Hermes Agent, Qoder, Grok Build). In Codex CLI and the IDE extension they're skills under the plugin's namespace; invoke with `$ponytail:ponytail-review`. Cursor with the [hooks](INSTALL.md#cursor) gets `/ponytail` level switching only, typed as a plain message. The instruction-only adapters (Cursor's rule file, Windsurf, Cline, Copilot, Kiro, Antigravity) load the always-on ruleset without the commands.
+Commands need a skill-capable host (Claude Code, Codex, Devin CLI, OpenCode, Gemini, pi, Hermes Agent, Qoder, Grok Build, Kimi Code, Goose). In Codex CLI and the IDE extension they're skills under the plugin's namespace; invoke with `$ponytail:ponytail-review`. Cursor with the [hooks](INSTALL.md#cursor) gets `/ponytail` level switching only, typed as a plain message. The instruction-only adapters (Cursor's rule file, Windsurf, Cline, Copilot, Kiro, Antigravity) load the always-on ruleset without the commands.
 
 ## Numbers
 
 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.
 
 <p align="center">
-  <img src="assets/benchmark-agentic.svg" width="860" alt="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%.">
+  <img src="assets/benchmark-agentic.svg" width="860" alt="Each arm as a percent of the no-skill baseline across LOC, tokens, cost and time (Haiku 4.5). ponytail is lowest on LOC and tokens (LOC 46%, tokens 78%, cost 80%, time 73%), the YAGNI one-liner prompt slightly lower on cost and time; 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%.">
 </p>
 
 | vs no-skill baseline | LOC | tokens | cost | time | safe |
@@ -149,7 +149,7 @@ The honest measurement is a real agent doing real work: a headless Claude Code s
 | caveman (terse-prose control) | -20% | +7% | +3% | +2% | 100% |
 | "YAGNI + one-liners" prompt | -33% | -14% | -21% | -30% | 95% |
 
-ponytail is the only arm that cuts every metric, and the only one that stays fully safe while doing it. The cut is biggest where there is a real over-build trap (date picker 404 to 23 lines, color picker 287 to 23, because it reaches for a native `<input>` instead of a component) and near zero on code that is already minimal. Full method, per-task tables, and limitations: [benchmarks/results/2026-06-18-agentic.md](benchmarks/results/2026-06-18-agentic.md).
+ponytail makes by far the biggest code cut, and it is the only arm that cuts every metric while staying fully safe: the "YAGNI + one-liners" prompt is slightly cheaper and faster, but cuts less code and dropped a path-traversal guard in 1 of 20 safety runs. The cut is biggest where there is a real over-build trap (date picker 404 to 23 lines, color picker 287 to 23, because it reaches for a native `<input>` instead of a component) and near zero on code that is already minimal. Full method, per-task tables, and limitations: [benchmarks/results/2026-06-18-agentic.md](benchmarks/results/2026-06-18-agentic.md).
 
 <details>
 <summary><strong>Older single-shot numbers (isolated generation)</strong></summary>
 
@@ -173,8 +173,8 @@ Negative is less code / cheaper / faster.
 
 Reading it:
 
-- **ponytail is the only arm that cuts every metric** on the feature tasks, and the only large code
-  cut (−54%). caveman writes less code but spends *more* tokens (+7%), terse output, same
+- **ponytail cuts every metric** on the feature tasks and makes the only large code cut (−54%);
+  yagni-oneliner also cuts every metric, slightly more on cost and time. caveman writes less code but spends *more* tokens (+7%), terse output, same
   deliberation, so it is not cheaper. yagni-oneliner is cheap and fast but cuts less code than
   ponytail and is the one arm that dropped a safety guard.
 - The **−54% LOC is the across-task aggregate**; per task it runs from ~0% (irreducible backend