simple

simple is a skill for Claude Code, Codex from Kevin-Liu-01/Agent-Machines. It costs 0 tokens per session (1,493 once invoked), scanned A, a copy of simple, MIT.

A five-part structure for explaining a technical problem: the cause, evidence, proposed fix, how the fix works, and how to test it.

In plain words
What is it for?
Use it for root-cause explanations, debugging write-ups, and fix proposals. It is also triggered by requests to explain why something is wrong or how to test a fix.
Why use it?
It helps turn a vague explanation into a reproducible diagnosis. The evidence and test steps make it easier to check whether the proposed cause is correct.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

Good fit Use it for root-cause explanations, debugging write-ups, and fix proposals. It is also triggered by requests to explain why something is wrong or how to test a fix.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/kevin-liu-01/agent-machines/simple
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 Kevin-Liu-01/Agent-Machines --skill simple
Clone the repo
git clone --depth 1 https://github.com/Kevin-Liu-01/Agent-Machines

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 simple

README.md
[![agentmods](https://agentmods.dev/badge/skills/kevin-liu-01/agent-machines/simple/github.svg)](https://agentmods.dev/skills/kevin-liu-01/agent-machines/simple)
Your own site
<a href="https://agentmods.dev/skills/kevin-liu-01/agent-machines/simple"><img src="https://agentmods.dev/badge/skills/kevin-liu-01/agent-machines/simple/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 simple

Your own site · 80×15
<a href="https://agentmods.dev/skills/kevin-liu-01/agent-machines/simple"><img src="https://agentmods.dev/badge/skills/kevin-liu-01/agent-machines/simple.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 0 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,493 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 100% copy Near-identical to another mod 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 $0.00000 $0.01493
Opus 5 $0.00000 $0.00746
Sonnet 5 $0.00000 $0.00299
Haiku 4.5 $0.00000 $0.00149

Measured 9d ago against content hash 87f174e607e1, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

simple 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.

Origin

This is a copy

100% identical to simple — 0 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.

knowledge/skills/simple/SKILL.md · 90 lines

How it starts

The opening of the file, as written. The whole thing — 90 lines — stays where its author put it; the contents beside it link to each section on GitHub.


name: simple description: Frame any technical answer as a reproducible five-part diagnosis. Use when the user asks for a root-cause explanation, a fix proposal, a debugging write-up, or says "explain why", "what's the problem", "propose a fix", or invokes /simple. Forces the answer into: problem, evidence, proposal, mechanism, test methodology.

Simple

A single reasoning template. Every answer has the same five parts in the same order. No headers. No bullets. No preamble. The shape itself teaches whoever reads it to think in cause and effect.

Contract

Respond in exactly five sentences or short paragraphs, in this order:

  1. X is the problem. State the root cause in one sentence. Name the actual thing, not a symptom. If the cause is "the code is slow", you have not finished diagnosing.
  2. We know this because Y. Cite the evidence. Measurements, strace output, log lines, code paths, invariants, benchmarks. Numbers beat adjectives. If you cannot cite evidence, you are guessing and should stop.
  3. I propose we use Z to fix this. Name the fix. One concrete intervention, not a list of options. Be specific enough that a reader could act on it without asking a follow-up.
  4. This is because Z does {mechanism} that helps this problem. Explain how the fix acts on the cause. The reader should be able to predict the fix's behavior from first principles, not take your word for it.
  5. We can test and reproduce this by {methodology}. Give the experiment. A command, a benchmark, a pjdfstest run, a targeted reproducer. The experiment must be able to falsify the proposal, not just confirm it.

End with a single line: Give it a try.

Rules

  • One cause per answer. If there are two causes, write two /simple answers.
  • No hedging. "This might be the problem" means you don't know. Go measure.
  • No options menu. Picking between alternatives is a separate kind of answer. /simple proposes one fix.
  • Mechanism before methodology. If you can't explain how the fix works, your test plan is cargo-culted.
  • Falsifiable test. The methodology must be capable of showing the proposal is wrong, not just showing some improvement.
  • Evidence is load-bearing. Never skip part 2. If you don't have numbers or a code pointer, go get them before writing the answer.

Read the full file on GitHub · 90 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. 9d ago First seen · 90 lines · 0 tokens per session scan A 87f174e607e1

Subscribe to this mod's changes

simple is a skill published in the GitHub repository Kevin-Liu-01/Agent-Machines (29 stars, last pushed today), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,493 tokens. A static security scan graded it A with 0 findings. It is 100% identical to simple, differing in 0 lines, and is treated as a copy.

Related

Other skills, from other repositories