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 skills add saski/arnesto --skill ponytailgit clone --depth 1 https://github.com/saski/arnestoWrote 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/saski/arnesto/ponytail)<a href="https://agentmods.dev/skills/saski/arnesto/ponytail"><img src="https://agentmods.dev/badge/skills/saski/arnesto/ponytail/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/saski/arnesto/ponytail"><img src="https://agentmods.dev/badge/skills/saski/arnesto/ponytail.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00079 | $0.00611 |
| Opus 5.5 | $0.00032 | $0.00244 |
| Sonnet 5.5 | $0.00016 | $0.00122 |
| Haiku 4.5 | $0.00008 | $0.00061 |
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 9d 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 — 64 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Ponytail
Choose the smallest maintainable implementation that meets the complete request. This is Arnesto's scoped adaptation of DietrichGebert/ponytail; see provenance for the pinned source and differences.
Establish the behavior
Read the relevant code, callers, tests, and project conventions first. Identify the acceptance criteria, boundaries, and failure cases. For a bug, trace its root cause before choosing where to change it. Scope this skill to the current task; extend it across turns only when the user asks for a persistent mode.
Choose an implementation
Stop at the first option that satisfies the acceptance criteria:
- Omit speculative work outside the request.
- Reuse an existing helper, type, component, or established project pattern.
- Use the language's standard library.
- Use a native platform feature that meets the actual requirements.
- Use an already installed dependency.
- Write the smallest clear implementation needed.
Read the candidate's behavior before reusing it. A native date input, a database constraint, or a standard cache is suitable only if its accessibility, data, concurrency, lifetime, and product behavior match the request. A short snippet that misses those requirements is not a solution. Add a dependency when its benefit justifies its cost; explain that concrete tradeoff briefly.
Preserve quality and scope
- Implement every requested acceptance criterion. Do not ship a reduced feature and ask the user to request the rest again.
- Prefer readable code over one-liners. Avoid speculative abstraction, clever compression, unrelated deletion, and invented future extension points.
- Keep validation at trust boundaries, security, accessibility, and error handling that protects data. Preserve documented compatibility constraints.
- Follow the repository's test tools and required validation. For behavior changes, use its existing TDD workflow when practical; do not impose a one-test limit or replace its suite with ad hoc assertions.
- Do not insert branded comments. Explain a non-obvious limitation only when the limitation matters to a maintainer.
What ships with it
3 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 9d ago First seen · 64 lines · 79 tokens per session scan A 8c8d7018316a
ponytail is a skill published in the GitHub repository saski/arnesto (5 stars, last pushed yesterday), licensed Unlicense. It adds 79 tokens to every session and 611 once invoked, about $0.0003 per session on Opus 5.5. 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 2026-10-08.
Other skills, from other repositories
readonly-review
Run a no-network read-only review practice with two explorer steps and one synthesis step.
repo-harness-assessment
Use when evaluating repository agent-readiness, mapping harness roles, choosing the next smallest improvement, or designing and reconciling agent entrypoints such as AGENTS.md, CLAUDE.md, GEMINI.md, Cursor rules, or GitHub instructions.
work-state-and-delivery
Use when designing or reconciling design docs, task boards, external trackers, execution plans, delivery records, handoffs, review evidence, task-to-change traceability, or repository commit-coupling policy.
repo-contracts-and-boundaries
Use when turning architecture, layering, ownership, dependency direction, schemas, structural metrics, quality thresholds, baselines, allowlists, or generated quality snapshots into repository checks.
runtime-evidence-and-tracing
Use when connecting observed behavior, logs, metrics, request IDs, run IDs, screenshots, traces, external dependency results, or artifacts into a runtime evidence loop.
validation-harness-design
Use when designing repository validation commands, doctor scripts, test matrices, JSON or JUnit outputs, CI gates, smoke checks, or harness command surfaces.