agentmods.dev

ponytail-audit-lite

ponytail-audit-lite is a skill for Claude Code, Codex from mushroomTW/MushroomTW-Skills. It costs 24 tokens per session (555 once invoked), scanned A, original, MIT.

A repository-wide audit that looks for code and configuration that can be removed or shortened. A repository is the version-controlled project folder containing the code.

In plain words
What is it for?
Use it to review an entire codebase and produce a ranked table of simplification findings, suggested replacements, file paths, and line-count changes.
Why use it?
It identifies dead code, unnecessary abstractions, duplicate platform features, and unused configuration that make a project harder to maintain.

Skill for Claude CodeCodex

Written for Claude Code and Codex: disable-model-invocation in frontmatter, but also agents/openai.yaml present.

not rated 0repo changed 1mo ago A scan 24 tokens original MIT

Good fit Use it to review an entire codebase and produce a ranked table of simplification findings, suggested replacements, file paths, and line-count changes.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/mushroomtw/mushroomtw-skills/ponytail-audit-lite
View source ↗ mushroomTW/MushroomTW-Skills
Install

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.

Any agent
npx skills add mushroomTW/MushroomTW-Skills --skill ponytail-audit-lite
Clone the repo
git clone --depth 1 https://github.com/mushroomTW/MushroomTW-Skills

Made for: Claude Code, Codex.

Wrote 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.

agentmods badge for ponytail-audit-lite

README.md
[![agentmods](https://agentmods.dev/badge/skills/mushroomtw/mushroomtw-skills/ponytail-audit-lite/github.svg)](https://agentmods.dev/skills/mushroomtw/mushroomtw-skills/ponytail-audit-lite)
Your own site
<a href="https://agentmods.dev/skills/mushroomtw/mushroomtw-skills/ponytail-audit-lite"><img src="https://agentmods.dev/badge/skills/mushroomtw/mushroomtw-skills/ponytail-audit-lite/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.

agentmods 80×15 button for ponytail-audit-lite

Your own site · 80×15
<a href="https://agentmods.dev/skills/mushroomtw/mushroomtw-skills/ponytail-audit-lite"><img src="https://agentmods.dev/badge/skills/mushroomtw/mushroomtw-skills/ponytail-audit-lite.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 24 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 555 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00024 $0.00555
Opus 5.5 $0.00010 $0.00222
Sonnet 5.5 $0.00005 $0.00111
Haiku 4.5 $0.00002 $0.00056

Measured 1mo ago against content hash c4e1ddf9ca6f, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

ponytail-audit-lite 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 1mo 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.

ponytail-audit-lite/SKILL.md · 54 lines

How it starts

The opening of the file, as written. The whole thing — 54 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Repo-wide. Scan the whole tree instead of a diff. Rank findings biggest cut first. Skip generated, vendored, and dependency directories (node_modules/, vendor/, build output) and anything .gitignore excludes.

Tags

  • delete: dead code, unused flexibility, speculative feature. Replacement: nothing.
  • stdlib: hand-rolled thing the standard library ships. Name the function.
  • native: dependency or code doing what the platform already does. Name the feature.
  • yagni: abstraction with one implementation, config nobody sets, layer with one caller.
  • shrink: same logic, fewer lines. Show the shorter form.

Hunt

Deps the stdlib or platform already ships, single-implementation interfaces, factories with one product, wrappers that only delegate, files exporting one thing, dead flags and config, hand-rolled stdlib.

Before tagging anything delete: or yagni:, search the whole tree for references, including string names, config, and build files. Code reached by reflection, dependency injection, framework conventions, an entry point, or a published library's public API is not dead: leave it out.

Output

A Markdown table, one row per finding, ranked biggest cut first:

| # | Tag | Cut | Replacement | Path |
|---|-----|-----|-------------|------|
| 1 | `yagni:` | <what to cut> | <replacement> | `<path>` |

Escape | inside cells as \|. Keep every cell to one line: a shrink: row says shorter form in #<n> in Replacement, and the shorter form goes below the table as a fenced code block headed #<n>. Past 20 findings, keep the 20 biggest and say how many were left out. Then end with net: -<N> lines, -<M> deps possible. N is the sum of the lines every finding removes, the ones left out of the table included, counted from the files, not guessed; M counts the dependencies they remove. Nothing to cut: no table, just Lean already. Ship.

Boundaries

Scope: over-engineering and complexity only. Correctness bugs, security holes, and performance are explicitly out of scope. Route them to a normal review pass. Lists findings, applies nothing. One-shot.

Read the full file on GitHub · 54 lines

Files

What ships with it

2 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.

Changes

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.

  1. 1mo ago Changed · +10 lines c4e1ddf9ca6f
  2. 1mo ago First seen · 44 lines · 24 tokens per session scan A 03ec5282fcc9

Subscribe to this mod's changes

ponytail-audit-lite is a skill published in the GitHub repository mushroomTW/MushroomTW-Skills (0 stars, last pushed today), licensed MIT. It adds 24 tokens to every session and 555 once invoked, about $0.0001 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 2026-09-24.

Claude CodeCode reviewProductivityagent-skillsai-agentscode-qualitycodex
Related

ponytail-audit-lite compared with skills from other repositories

ponytail-audit-lite next to 6 skills from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
ponytail-audit-litemushroomTW/MushroomTW-SkillsSkill0todayMITA24Claude Code, Codex
ai-development-guideshinpr/claude-code-workflowsSkill7122d agoMITA44Claude Code
recipe-front-reviewshinpr/claude-code-workflowsSkill7122d agoMITA29Claude Code
recipe-reviewshinpr/claude-code-workflowsSkill7122d agoMITA26Claude Code
coding-principlesshinpr/claude-code-workflowsSkill7122d agoMITA34Claude Code
ring:generating-release-guidesLerianStudio/ringSkill2187d agoApache-2.0A85Cursor
handoffreidemeister94/development-skillsSkill127d agoMITA29Claude Code