bloated-skill

bloated-skill is a skill for Claude Code, Codex from EpochTX/skillbench. It costs 22 tokens per session (345 once invoked), scanned A, original, MIT.

A release checklist for publishing a TypeScript package. It covers versioning, exports, generated type declarations, tests, package contents, documentation, licensing, and unexplained working-tree changes.

In plain words
What is it for?
Use it before releasing a TypeScript package to verify its code, metadata, tarball, README, license, supported Node versions, and repository state.
Why use it?
It helps catch packaging or publication problems before users receive a new version. It also records commands and evidence so another maintainer can repeat the review.

Skill for Claude CodeCodex

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.

agentmods
npx agentmods add skills/epochtx/skillbench/bloated-skill
Any agent
npx skills add EpochTX/skillbench --skill bloated-skill
Clone the repo
git clone --depth 1 https://github.com/EpochTX/skillbench

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 bloated-skill

README.md
[![agentmods](https://agentmods.dev/badge/skills/epochtx/skillbench/bloated-skill.svg)](https://agentmods.dev/skills/epochtx/skillbench/bloated-skill)
Your own site
<a href="https://agentmods.dev/skills/epochtx/skillbench/bloated-skill"><img src="https://agentmods.dev/badge/skills/epochtx/skillbench/bloated-skill.svg" alt="Measured on agentmods" height="20"></a>
Per session 22 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 345 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00022 $0.00345
Opus 5 $0.00011 $0.00172
Sonnet 5 $0.00004 $0.00069
Haiku 4.5 $0.00002 $0.00034

Measured 4d ago against content hash 6fad5eae1686, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

bloated-skill 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 4d 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.

tests/fixtures/bloated-skill/SKILL.md · 27 lines

What it actually says

Release checklist

Purpose

Create a release checklist that covers versioning, tests, documentation, package contents, and publication readiness for a TypeScript package.

First copy

Before publishing, verify that the package version matches the changelog, every public entry point is exported, generated declarations are present, tests pass on supported Node versions, the tarball contains only intended files, the readme installation command is accurate, the license is included, and the working tree has no unexplained changes. Record each result with the command used and a short piece of evidence so another maintainer can reproduce the review.

Second copy

Before publishing, verify that the package version matches the changelog, every public entry point is exported, generated declarations are present, tests pass on supported Node versions, the tarball contains only intended files, the readme installation command is accurate, the license is included, and the working tree has no unexplained changes. Record each result with the command used and a short piece of evidence so another maintainer can reproduce the review.

Third copy

Before publishing, verify that the package version matches the changelog, every public entry point is exported, generated declarations are present, tests pass on supported Node versions, the tarball contains only intended files, the readme installation command is accurate, the license is included, and the working tree has no unexplained changes. Record each result with the command used and a short piece of evidence so another maintainer can reproduce the review.

Output

Return a Markdown checklist with pass, fail, and not-applicable states.

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. 4d ago First seen · 27 lines · 22 tokens per session scan A 6fad5eae1686

Subscribe to this mod's changes

bloated-skill is a skill published in the GitHub repository EpochTX/skillbench (1 stars, last pushed 3d ago), licensed MIT. It adds 22 tokens to every session and 345 once invoked, about $0.0001 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.