Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx agentmods add skills/bartoszarendt/agenticloop/ponytailnpx skills add bartoszarendt/agenticloop --skill ponytailgit clone --depth 1 https://github.com/bartoszarendt/agenticloopWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/bartoszarendt/agenticloop/ponytail)<a href="https://agentmods.dev/skills/bartoszarendt/agenticloop/ponytail"><img src="https://agentmods.dev/badge/skills/bartoszarendt/agenticloop/ponytail.svg" alt="Measured on agentmods" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5 | $0.00137 | $0.01982 |
| Opus 5 | $0.00068 | $0.00991 |
| Sonnet 5 | $0.00027 | $0.00396 |
| Haiku 4.5 | $0.00014 | $0.00198 |
Grade A, and why
ponytail scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 3d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 162 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Ponytail
Purpose
Ponytail is an opt-in minimalism discipline for maintainer and engineer work. It pushes for the least code, fewest files, and smallest accepted change that still satisfies the current task record.
Lazy means efficient, not careless. The cost being avoided is the over-engineered codebase and the 3am page for behavior nobody needed. Prefer boring over clever: clever is what someone has to decode under pressure later.
Ponytail is necessity-driven reduction, not clever terseness. Do not pick a flimsier algorithm just because it is shorter. Boring, correct, readable code beats clever one-liners. Minimalism must not remove validation, error handling that prevents data loss, security, accessibility, required checks, or explicit requirements.
When to use
- Only when the current role is maintainer or engineer.
- When the human explicitly asks for ponytail, lazy mode, YAGNI, the simplest solution, the minimal solution, the shortest path, or similar minimalist discipline; or when the active task record sets
minimalism: lite,minimalism: full, orminimalism: ultra; or when the maintainer is selecting the task-recordminimalismlevel during task creation. - Task-record
minimalismselects intensity:lite,full, orultraas set in the task record. Omitted orminimalism: nonedoes not activate Ponytail. ultrafrom a task record is valid only with explicit human request or authorization. Maintainers must not auto-selectultra.- Use it to reduce over-building inside accepted scope, not to argue away required work after the fact.
- Default intensity is
full.
Intensity
lite: build what was asked, then briefly mention the lazier alternative.full(default): enforce the ladder within the accepted task scope and ship the shortest working solution.ultra: aggressively challenge unnecessary work or accumulated complexity, but only through the allowed Agentic Loop gates. Ultra may recommend descoping or push back on incidental complexity that has crept in. Ultra must not silently drop any task-record criterion. If a criterion seems unnecessary, route it through [[change-request-gate]] when it changes a locked decision, or [[blocked-state]] withneeds_contextwhen the task record needs human clarification. Ultra never bypasses task-record criteria; it questions whether the criteria serve the accepted outcome.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 3d ago First seen · 162 lines · 0 tokens per session scan A a0e024a83d35
ponytail is a skill published in the GitHub repository bartoszarendt/agenticloop (2 stars, last pushed 14d ago), licensed MIT. It adds 137 tokens to every session and 1,982 once invoked, about $0.0007 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
skill-creator
Create new skills, modify and improve existing skills, and measure skill performance. Use when users want to create a skill from scratch, edit, or optimize an existing skill, run evals to test a skill, benchmark skill performance with variance analysis, or optimize a skill's description for better triggering accuracy.
consulting-analysis
Use this skill when the user requests to generate, create, or write professional research reports including but not limited to market analysis, consumer insights, brand analysis, financial analysis, industry research, competitive intelligence, investment due diligence, or any consulting-grade analytical report. This…
ppt-generation
Use this skill when the user requests to generate, create, or make presentations (PPT/PPTX). Creates visually rich slides by generating images for each slide and composing them into a PowerPoint file.
deerflow-maintainer-orchestrator
Use when a DeerFlow maintainer needs comment-only GitHub issue or PR handling: resolve issue/PR scopes with gh, analyze issues, post or draft issue comments, perform PR review comments, review PR or issue batches, compare competing PRs that target the same issue, give fix strategy, risk classification, and validation…
systematic-literature-review
Use this skill when the user wants a systematic literature review, survey, or synthesis across multiple academic papers on a topic. Also covers annotated bibliographies and cross-paper comparisons. Searches arXiv and outputs reports in APA, IEEE, or BibTeX format. Not for single-paper tasks — use academic-paper-review…
academic-paper-review
Use this skill when the user requests to review, analyze, critique, or summarize academic papers, research articles, preprints, or scientific publications. Supports comprehensive structured reviews covering methodology assessment, contribution evaluation, literature positioning, and constructive feedback generation.…