{"id":51250401,"url":"https://github.com/dietrichgebert/ponytail","last_synced_at":"2026-06-29T07:00:42.154Z","repository":{"id":364186587,"uuid":"1266797999","full_name":"DietrichGebert/ponytail","owner":"DietrichGebert","description":"Makes your AI agent think like the laziest senior dev in the room. The best code is the code you never wrote.","archived":false,"fork":false,"pushed_at":"2026-06-26T01:28:09.000Z","size":1984,"stargazers_count":64488,"open_issues_count":128,"forks_count":3331,"subscribers_count":143,"default_branch":"main","last_synced_at":"2026-06-29T01:26:18.641Z","etag":null,"topics":["agent-skills","ai-agents","claude","claude-code","claude-code-plugin","cursor-rules","developer-tools","llm","prompt-engineering","yagni"],"latest_commit_sha":null,"homepage":"https://ponytail.dev","language":"JavaScript","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"mit","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/DietrichGebert.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":null,"funding":null,"license":"LICENSE","code_of_conduct":null,"threat_model":null,"audit":null,"citation":null,"codeowners":null,"security":null,"support":null,"governance":null,"roadmap":null,"authors":null,"dei":null,"publiccode":null,"codemeta":null,"zenodo":null,"notice":null,"maintainers":null,"copyright":null,"agents":"AGENTS.md","dco":null,"cla":null}},"created_at":"2026-06-12T00:52:37.000Z","updated_at":"2026-06-29T01:25:56.000Z","dependencies_parsed_at":null,"dependency_job_id":null,"html_url":"https://github.com/DietrichGebert/ponytail","commit_stats":null,"previous_names":["dietrichgebert/ponytail"],"tags_count":1,"template":false,"template_full_name":null,"purl":"pkg:github/DietrichGebert/ponytail","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/DietrichGebert%2Fponytail","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/DietrichGebert%2Fponytail/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/DietrichGebert%2Fponytail/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/DietrichGebert%2Fponytail/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/DietrichGebert","download_url":"https://codeload.github.com/DietrichGebert/ponytail/tar.gz/refs/heads/main","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/DietrichGebert%2Fponytail/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":286080680,"owners_count":34916411,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2026-05-26T15:22:16.424Z","status":"online","status_checked_at":"2026-06-29T02:00:05.398Z","response_time":58,"last_error":null,"robots_txt_status":"success","robots_txt_updated_at":"2025-07-24T06:49:26.215Z","robots_txt_url":"https://github.com/robots.txt","online":true,"can_crawl_api":true,"host_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub","repositories_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories","repository_names_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repository_names","owners_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners"}},"keywords":["agent-skills","ai-agents","claude","claude-code","claude-code-plugin","cursor-rules","developer-tools","llm","prompt-engineering","yagni"],"created_at":"2026-06-29T07:00:22.992Z","updated_at":"2026-06-29T07:00:42.148Z","avatar_url":"https://github.com/DietrichGebert.png","language":"JavaScript","funding_links":[],"categories":[],"sub_categories":[],"readme":"\u003cp align=\"center\"\u003e\n  \u003cpicture\u003e\n    \u003csource media=\"(prefers-color-scheme: dark)\" srcset=\"assets/logo-dark.png\"\u003e\n    \u003cimg src=\"assets/logo.png\" width=\"220\" alt=\"Ponytail, the lazy senior dev\"\u003e\n  \u003c/picture\u003e\n\u003c/p\u003e\n\n\u003ch1 align=\"center\"\u003ePonytail\u003c/h1\u003e\n\n\u003cp align=\"center\"\u003e\n  \u003cem\u003eHe says nothing. He writes one line. It works.\u003c/em\u003e\n\u003c/p\u003e\n\n\u003cp align=\"center\"\u003e\n  \u003cimg src=\"https://img.shields.io/github/stars/DietrichGebert/ponytail?style=flat-square\u0026color=111111\u0026label=stars\" alt=\"Stars\"\u003e\n  \u003cimg src=\"https://img.shields.io/github/v/release/DietrichGebert/ponytail?style=flat-square\u0026color=111111\u0026label=release\" alt=\"Release\"\u003e\n  \u003cimg src=\"https://img.shields.io/badge/works%20with-14%20agents-111111?style=flat-square\" alt=\"Works with 14 agents\"\u003e\n  \u003cimg src=\"https://img.shields.io/badge/license-MIT-111111?style=flat-square\" alt=\"MIT license\"\u003e\n\u003c/p\u003e\n\n\u003cp align=\"center\"\u003e\n  \u003cstrong\u003e~54% less code (up to 94%) \u0026middot; ~20% cheaper \u0026middot; ~27% faster \u0026middot; 100% safe\u003c/strong\u003e\u003cbr\u003e\n  \u003csub\u003eMeasured on real Claude Code sessions editing a real open-source repo (FastAPI + React), against the same agent with no skill. ~54% is the mean across 12 feature tasks (Haiku 4.5, n=4); it reaches 94% where an agent over-builds (a date picker) and is near zero where the code is already minimal. ponytail keeps every safety guard while a bare \"write one-liners\" prompt drops one. (The earlier single-shot benchmark reported 80-94% as a flat figure; against a fair agentic baseline that is the per-task ceiling, not the average.) \u003ca href=\"benchmarks/results/2026-06-18-agentic.md\"\u003eFull writeup\u003c/a\u003e \u0026middot; \u003ca href=\"benchmarks/\"\u003ereproduce it\u003c/a\u003e.\u003c/sub\u003e\n\u003c/p\u003e\n\n\u003cp align=\"center\"\u003e\n  \u003csub\u003e\u003ca href=\"README.es.md\"\u003eEspañol\u003c/a\u003e\u003c/sub\u003e\n\u003c/p\u003e\n\n---\n\nYou know him. Long ponytail. Oval glasses. Has been at the company longer than the version control. You show him fifty lines; he looks at them, says nothing, and replaces them with one.\n\nPonytail puts him inside your AI agent.\n\n## Before / after\n\nYou ask for a date picker. Your agent installs flatpickr, writes a wrapper component, adds a stylesheet, and starts a discussion about timezones.\n\nWith ponytail:\n\n```html\n\u003c!-- ponytail: browser has one --\u003e\n\u003cinput type=\"date\"\u003e\n```\n\nMore survivors in [examples/](examples/).\n\n## Numbers\n\nThe 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.\n\n\u003cp align=\"center\"\u003e\n  \u003cimg 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%.\"\u003e\n\u003c/p\u003e\n\n| vs no-skill baseline | LOC | tokens | cost | time | safe |\n|---|--:|--:|--:|--:|--:|\n| **ponytail** | **-54%** | **-22%** | **-20%** | **-27%** | **100%** |\n| caveman (terse-prose control) | -20% | +7% | +3% | +2% | 100% |\n| \"YAGNI + one-liners\" prompt | -33% | -14% | -21% | -30% | 95% |\n\nponytail 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 `\u003cinput\u003e` 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).\n\n\u003cdetails\u003e\n\u003csummary\u003e\u003cstrong\u003eOlder single-shot numbers (isolated generation)\u003c/strong\u003e\u003c/summary\u003e\n\nFive everyday tasks, three models, three arms (no skill, [caveman](https://github.com/JuliusBrussee/caveman), ponytail), ten runs, median reported. One prompt, one completion, counting lines of the answer:\n\n\u003cp align=\"center\"\u003e\n  \u003cimg src=\"assets/benchmark-3model.svg\" width=\"860\" alt=\"Median lines of code per arm across Haiku, Sonnet and Opus\"\u003e\n\u003c/p\u003e\n\nThis showed **80-94% less code**. [#126](https://github.com/DietrichGebert/ponytail/issues/126) fairly pointed out that the bare-model baseline pads its answer with prose and options, so that gap is partly a conversational-baseline artifact. The agentic numbers above are the corrected, defensible version. Reproduce the single-shot run with `npx promptfoo eval -c benchmarks/promptfooconfig.yaml`.\n\n\u003c/details\u003e\n\n**The rule was never \"fewest tokens.\"** It is: write only what the task needs, and never cut validation, error handling, security, or accessibility. The code ends up small because it is necessary, not golfed. Lower cost and latency are a side effect on the models that follow the ladder; a terse reasoning model that spends thinking tokens deliberating the rungs can go the other way (on GPT-5.5 it does).\n\n## How it works\n\nBefore writing code, the agent stops at the first rung that holds:\n\n```\n1. Does this need to exist?   → no: skip it (YAGNI)\n2. Stdlib does it?            → use it\n3. Native platform feature?   → use it\n4. Installed dependency?      → use it\n5. One line?                  → one line\n6. Only then: the minimum that works\n```\n\nLazy, not negligent: trust-boundary validation, data-loss handling, security, and accessibility are never on the chopping block.\n\n## Install\n\nThe most effort ponytail will ever ask of you:\n\nThe Claude Code and Codex plugins run two tiny Node.js lifecycle hooks, so `node` needs to be on your PATH (note for Nix/nvm users: it must be on the non-interactive shell's PATH). If it isn't, the skills still work, the always-on activation just stays quiet instead of erroring on every prompt.\n\n### Claude Code\n\n```\n/plugin marketplace add DietrichGebert/ponytail\n/plugin install ponytail@ponytail\n```\n\nThe desktop app has no `/plugin` command. Install it from the UI instead: Customize, the + by personal plugins, Create plugin and add marketplace, Add from repository, then enter the repo URL (thanks @NiklasDHahn, #98).\n\n### Codex\n\n```bash\ncodex plugin marketplace add DietrichGebert/ponytail\ncodex\n```\n\nOpen `/plugins`, select the Ponytail marketplace, and install Ponytail. Then\nopen `/hooks`, review and trust its two lifecycle hooks, and start a new thread.\n\nThis same install also covers the Codex desktop app: restart the app after installing and it picks up the plugin.\n\n### GitHub Copilot CLI\n\n```bash\ncopilot plugin marketplace add DietrichGebert/ponytail\ncopilot plugin install ponytail@ponytail\n```\n\nIn an interactive Copilot CLI session, use the slash equivalents:\n\n```\n/plugin marketplace add DietrichGebert/ponytail\n/plugin install ponytail@ponytail\n```\n\nCopilot CLI namespaces plugin commands by plugin name. For example:\n\n```text\n/ponytail:ponytail ultra\n/ponytail:ponytail-review\n```\n\n### Pi agent harness\n\n```\npi install git:github.com/DietrichGebert/ponytail\n```\n\n### OpenCode\n\nRun OpenCode from a checkout of this repo (the plugin reuses its `hooks/` and `skills/`), and add to `opencode.json`:\n\n```json\n{ \"plugin\": [\"./.opencode/plugins/ponytail.mjs\"] }\n```\n\nInjects the ruleset every turn at the active level; adds the `/ponytail` commands (see [Commands](#commands)). OpenCode also auto-loads this repo's `AGENTS.md`, so the rules hold even without the plugin. The plugin adds the `lite/full/ultra/off` levels.\n\nThe `./` path resolves against your project's `opencode.json`; to share one checkout across projects, point it at the absolute path of the `.mjs` instead (it finds its `hooks/` and `skills/` relative to its own file).\n\nThe plugin path loads the ruleset everywhere, but the `/ponytail` commands are separate files in `.opencode/command/` that OpenCode only discovers from your project or the global commands dir. To use them outside this checkout, link them once: `ln -sf /absolute/path/to/ponytail/.opencode/command/* ~/.config/opencode/command/`.\n\n### Gemini CLI\n\n```bash\ngemini extensions install https://github.com/DietrichGebert/ponytail\n```\n\nLoads the ruleset as always-on context every session and registers the `/ponytail` commands; the `skills/` ship too, activated when a task needs them.\nThe Gemini adapter intentionally does not ship a root `hooks/hooks.json`: Gemini auto-loads that path, while Ponytail's lifecycle hooks use Claude/Codex event names.\n\n### Antigravity CLI\n\nGoogle is renaming Gemini CLI to Antigravity CLI (the `agy` binary); the same extension installs there:\n\n```bash\nagy plugin install https://github.com/DietrichGebert/ponytail\n```\n\nIt reuses this repo's `gemini-extension.json`. One difference: Antigravity converts the `/ponytail` commands into skills, so you type them into the chat (e.g. `/ponytail-review` as a message) instead of picking them from a slash menu. Until the migration completes (around June 18, 2026), `gemini extensions install` still works too. To run it as an always-on rule instead, drop the ruleset into `.agents/rules/`.\n\n### CodeWhale\n\nReads `AGENTS.md` from the project root, zero setup. Copy [`AGENTS.md`](AGENTS.md) to your project, or run `codewhale` from a checkout of this repo. That's it.\n\n### OpenClaw\n\n```bash\nclawhub install ponytail\n```\n\nInstalls ponytail as an OpenClaw skill from ClawHub; the review, audit, debt, gain, and help skills install the same way (`clawhub install ponytail-review`, and so on). OpenClaw applies it on coding tasks and also exposes it as a `/ponytail` command. Without ClawHub, copy [`.openclaw/skills/ponytail`](.openclaw/skills/) into `~/.openclaw/skills/`.\n\nThat was it. He'd be proud. He won't say it.\n\nActive every session, with a handful of commands (see [Commands](#commands)). `/ponytail ultra` exists for when the codebase has wronged you personally. Startup and mode-change text shows the current mode.\n\nSet the level for every new session with the `PONYTAIL_DEFAULT_MODE` env var (`lite`/`full`/`ultra`/`off`), or a `defaultMode` field in `~/.config/ponytail/config.json` (`%APPDATA%\\ponytail\\config.json` on Windows). The default is `full`.\n\nCursor, Windsurf, Cline, GitHub Copilot (editor), Aider, Kiro, Zed, CodeWhale: copy the matching rules file from this repo ([`.cursor/rules/`](.cursor/rules/), [`.windsurf/rules/`](.windsurf/rules/), [`.clinerules/`](.clinerules/), [`.github/copilot-instructions.md`](.github/copilot-instructions.md), [`AGENTS.md`](AGENTS.md), [`.kiro/steering/`](.kiro/steering/)).\n\nKiro: copy `.kiro/steering/ponytail.md` to `~/.kiro/steering/` (global) or `.kiro/steering/` in your project.\n\nGitHub Copilot CLI fallback (instruction-only mode): it reads `AGENTS.md` and `.github/copilot-instructions.md` in a project, or copy the rules into `~/.copilot/copilot-instructions.md` to run ponytail in every project. This path keeps always-on guidance, but does not add plugin mode switches or hooks.\n\nVS Code with the Codex extension reads `AGENTS.md`, which this repo ships, so it works from the repo root with no setup (`~/.codex/AGENTS.md` makes Codex global).\n\nWhich files map to which agent: [Agent portability](docs/agent-portability.md).\n\n## Commands\n\n| Command | What it does |\n|---------|--------------|\n| `/ponytail [lite \\| full \\| ultra \\| off]` | Set the intensity, or turn it off. No argument reports the current level. |\n| `/ponytail-review` | Review the current diff for over-engineering, hands back a delete-list. |\n| `/ponytail-audit` | Audit the whole repo for over-engineering, not just the diff. |\n| `/ponytail-debt` | Harvest the `ponytail:` shortcuts you've deferred into a ledger, so \"later\" doesn't become \"never\". |\n| `/ponytail-gain` | Show the measured impact scoreboard (less code, less cost, more speed) from the benchmark. |\n| `/ponytail-help` | Quick reference for the commands above. |\n\nCommands need a skill-capable host (Claude Code, Codex, OpenCode, Gemini, pi). In Codex they're skills, invoke with `@` (`@ponytail-review`). The instruction-only adapters (Cursor, Windsurf, Cline, Copilot, Kiro, Antigravity) load the always-on ruleset without the commands.\n\n## Development\n\nWhen changing the compact rule text, keep the agent copies aligned:\n\n```bash\nnode scripts/check-rule-copies.js\nnpm test\n```\n\nThe OpenClaw skill package (`.openclaw/skills/`) is generated from `skills/`; rerun `node scripts/build-openclaw-skills.js` after changing a skill, the test suite fails if it is stale.\n\nThe correctness benchmark spawns Python for email and CSV checks; `python3` is tried before `python`. CSV checks need `pandas` installed locally.\n\n## FAQ\n\n**Does it need a config file?**\nNo. An optional `~/.config/ponytail/config.json` or `PONYTAIL_DEFAULT_MODE` env var can set the default level, but nothing is required.\n\n**What if I really need the 120-line cache class?**\nYou don't. Insist anyway and he'll build it. Slowly. Correctly. While looking at you.\n\n**Does it scale?**\nThe code you never wrote scales infinitely. Zero bugs, zero CVEs, 100% uptime since forever.\n\n**Why \"ponytail\"?**\nYou know exactly why.\n\n## License\n\n[MIT](LICENSE). The shortest license that works.\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fdietrichgebert%2Fponytail","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fdietrichgebert%2Fponytail","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fdietrichgebert%2Fponytail/lists"}