compare-skills

compare-skills is a skill for Claude Code from tomzx/agents. It costs 42 tokens per session (3,029 once invoked), scanned A, original, MIT.

A comparison of two folders containing reusable instruction sets for coding agents. It looks at how the instructions are organized and what practices one folder has that the other lacks.

In plain words
What is it for?
Use it to create a prioritized improvement list covering structure, clarity, reuse, completeness, safety, and logging guidance.
Why use it?
It helps find gaps and inconsistencies without having to compare every instruction file manually.

Skill for Claude Code

Written for Claude Code: allowed-tools in frontmatter. Also seen: positional $N argument; mentions AGENTS.md; mentions OpenCode.

Good fit Use it to create a prioritized improvement list covering structure, clarity, reuse, completeness, safety, and logging guidance.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/tomzx/agents/compare-skills
View source ↗ tomzx/agents
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 tomzx/agents --skill compare-skills
Clone the repo
git clone --depth 1 https://github.com/tomzx/agents

Made for: Claude Code.

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 compare-skills

README.md
[![agentmods](https://agentmods.dev/badge/skills/tomzx/agents/compare-skills.svg)](https://agentmods.dev/skills/tomzx/agents/compare-skills)
Your own site
<a href="https://agentmods.dev/skills/tomzx/agents/compare-skills"><img src="https://agentmods.dev/badge/skills/tomzx/agents/compare-skills.svg" alt="Measured on agentmods" height="20"></a>
Per session 42 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 3,029 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. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
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 $0.00042 $0.03029
Opus 5 $0.00021 $0.01515
Sonnet 5 $0.00008 $0.00606
Haiku 4.5 $0.00004 $0.00303

Measured 7d ago against content hash 0c3b6cb3d894, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

compare-skills 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 7d 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.

skills/compare-skills/SKILL.md · 316 lines

How it starts

The opening of the file, as written. The whole thing — 316 lines — stays where its author put it; the contents beside it link to each section on GitHub.

TODAY=!date +%Y-%m-%d

Compare Skills

Compares the skill libraries in two directories, identifies best practices present in "theirs" but missing or weaker in "mine", and produces a prioritized adoption plan.

Prerequisites

  • Two directories containing skill libraries, each with SKILL.md files in subdirectories
  • <mine-dir> — your skill directory (the one to improve)
  • <theirs-dir> — the reference skill directory (the one to learn from)

What Counts as a Best Practice

Category What to Look For
Structural patterns Consistent frontmatter fields, section ordering, standard sections (Prerequisites, Steps, Output Format, Examples)
Instruction quality Specificity of steps, use of code blocks, error handling guidance, edge case coverage
Reusability Parameterization via arguments or environment variables, ! template syntax for dynamic values
Completeness Prerequisites section, example usage scenarios, useful commands reference, next steps
Safety Guardrails, validation steps, rollback guidance, confirmation prompts before destructive actions
Observability Logging guidance, output formatting, status reporting
Tool usage allowed-tools frontmatter, appropriate tool constraints, tool-specific tips

What Counts as a Removal Candidate

Patterns in "mine" that "theirs" has evolved away from or that are demonstrably harmful:

Category Signals
Over-constraint Instructions that micromanage the agent (e.g., prescribing exact phrasing, mandating specific library versions in prose) where theirs delegates judgement
Redundancy Instructions duplicated across sections, or content repeated in multiple skills that theirs consolidates
Stale assumptions Hardcoded paths, version pins, or tool names that may be outdated; theirs uses dynamic values or omits them
Vague handwaving Steps like "handle errors appropriately" or "do the right thing" with no specificity; theirs either removes these or makes them concrete
Boilderplate noise Large copy-pasted blocks that add no instructional value (license headers, repeated disclaimers, decorative formatting)
Premature optimization Instructions that optimize for edge cases the agent handles naturally, bloating the skill without benefit
Anti-patterns from theirs Patterns present in mine that theirs explicitly avoids (e.g., mine uses cd && chains, theirs uses workdir; mine hardcodes values, theirs uses ! syntax)

Read the full file on GitHub · 316 lines

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. 7d ago First seen · 316 lines · 42 tokens per session scan A 0c3b6cb3d894

Subscribe to this mod's changes

compare-skills is a skill published in the GitHub repository tomzx/agents (6 stars, last pushed 3d ago), licensed MIT. It adds 42 tokens to every session and 3,029 once invoked, about $0.0002 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.

Related

Other skills, from other repositories

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

local-ai-agents

Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…

microsoft/ai-agents-for-beginners · 200 tokens

next-cache-components-adoption

Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…

vercel/next.js · 95 tokens

next-partial-prefetching-adoption

Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…

vercel/next.js · 103 tokens

chronicle

Analyze Copilot session history for standup reports, usage tips, session search, and session reindexing. Use when the user asks for a standup, daily summary, usage tips, workflow recommendations, wants to search or find past sessions by keyword/file/PR, wants to reindex their session store, or asks about deleting…

microsoft/vscode · 72 tokens

babysit-pr

Babysit a GitHub pull request after creation by continuously polling review comments, CI checks/workflow runs, and mergeability state until the PR is merged/closed or user help is required. Diagnose failures, retry likely flaky failures up to 3 times, auto-fix/push branch-related issues when appropriate, and keep…

openai/codex · 114 tokens