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.
git clone --depth 1 https://github.com/kok-o/koko-contextos-agentsWrote 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/rules/kok-o/koko-contextos-agents/ponytail-mindset)<a href="https://agentmods.dev/rules/kok-o/koko-contextos-agents/ponytail-mindset"><img src="https://agentmods.dev/badge/rules/kok-o/koko-contextos-agents/ponytail-mindset.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 5.1 | $0.01562 | $0.01562 |
| Opus 5 | $0.00781 | $0.00781 |
| Sonnet 5 | $0.00312 | $0.00312 |
| Haiku 4.5 | $0.00156 | $0.00156 |
Grade A, and why
ponytail-mindset 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 2d 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 — 195 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Skill: ponytail-mindset
ponytail-mindset
Overview
Minimalist engineering discipline that eliminates over-engineering and premature abstraction while maintaining 100% of required validation, type safety, error boundaries, and security invariants.
When to Use
Activate on all BUILD phases to prevent bloated implementations and enforce concise, focused solutions.
Rules & Patterns
Based on DietrichGebert/ponytail.
He says nothing. He writes one line. It works.
Benchmark: 54% less code on average. 94% less in over-build scenarios. 100% safe (validation, error handling, security: never cut).
Core Principle
The best code is code you don't write.
Write only what the task strictly needs. Lazy about the solution, never about reading and understanding.
The 7-Rung Decision Ladder
Before writing ANY code, stop and check each rung in order. Stop at the first rung that holds:
1. Does this need to exist?
→ No: YAGNI — skip it entirely. Don't build for "future use."
2. Already in this codebase or component library?
→ Yes: Reuse it. Don't rewrite. Call the existing function/component/module.
→ For UI: Check shadcn/ui FIRST. Before building a complex UI element from scratch, check if it exists in the component library. If yes, generate the install command: npx shadcn@latest add dialog — never manually rewrite what shadcn already provides.
3. Standard library does it?
→ Yes: Use it. Don't write formatDate() — use Intl.DateTimeFormat or dayjs.
4. Native platform feature?
→ Yes: Use it. Don't install flatpickr when <input type="date"> exists.
→ Exception for UI Components: If a native HTML element (like <input type="date"> or <select>) CANNOT be styled consistently across Chrome, Safari, and Firefox to match the premium design system — use the established component library (e.g., shadcn/ui <DatePicker>, <Select>) instead. Cross-browser inconsistency is a legitimate reason to NOT use native.
5. Already-installed dependency?
→ Yes: Use it. Don't install a new library to do what an existing one can.
6. Can it be done in one line?
→ Yes: One line. No abstraction layer needed.
7. Only then: write the MINIMUM that works.
→ No classes when a function works. No module when an inline does.
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.
- 2d ago Changed · -86 lines · -431 tokens per session 5a324e425f2b
- 7d ago First seen · 281 lines · 1,993 tokens per session scan A 22f41701a393
ponytail-mindset is a cursor rule published in the GitHub repository kok-o/koko-contextos-agents (2 stars, last pushed 3d ago), licensed MIT. It adds 1,562 tokens to every session, about $0.0078 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 cursor rules, from other repositories
deepen-architecture
Find deepening opportunities in a codebase, informed by the domain language in specs/tech-architecture/tech-stack.md and the decisions in specs/adr/. Use when the user wants to improve architecture, find refactoring opportunities, consolidate tightly-coupled modules, or make a codebase more testable and AI-navigable.
craft-skill
Create new bigpowers skills with proper structure, progressive disclosure, and bundled resources. Use when user wants to create, write, or build a new skill for the bigpowers lifecycle.
grill-me
Interactive assumption-surfacing Q&A that stress-tests a plan through relentless questioning until every decision is resolved. Use when user wants to challenge a plan, validate decisions from conversation/context, or mentions "grill me". For doc-grounded variant, use grill-with-docs.
run-planning
DISCOVER-PHASE ADVANCER — Drive the discover-phase checklist (specs/planning-status.yaml) through survey-context → scope-work → research-first → elaborate-spec → plan-release → slice-tasks. NOT a duplicate of plan-work or the planning spine; it orchestrates the pre-coding discover phase only.
slice-tasks
PLANNING SPINE STEP 2 of 3 — Slice the work: break a scoped PRD into vertical-slice stories in specs/epics/. Use after scope-work (step 1), before plan-work (step 3). Not a substitute for scope-work or plan-work.
terse-mode
Fallback ultra-compressed communication mode. Cuts token usage 75% by dropping filler, articles, and pleasantries while keeping full technical accuracy. Use ONLY when context is critically long and compressing output is necessary to continue. Not a strategy — token discipline comes from code shape (small functions…