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 tomzx/agents --skill compare-skillsgit clone --depth 1 https://github.com/tomzx/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/skills/tomzx/agents/compare-skills)<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>- NVIDIA SkillSpector pass
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 | $0.00042 | $0.03029 |
| Opus 5 | $0.00021 | $0.01515 |
| Sonnet 5 | $0.00008 | $0.00606 |
| Haiku 4.5 | $0.00004 | $0.00303 |
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.
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.mdfiles 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) |
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.
- 7d ago First seen · 316 lines · 42 tokens per session scan A 0c3b6cb3d894
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.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
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…
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…
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…
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…
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…