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 Kevin-Liu-01/Agent-Machines --skill simple-diagnosis-templategit clone --depth 1 https://github.com/Kevin-Liu-01/Agent-MachinesWrote 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/kevin-liu-01/agent-machines/simple-diagnosis-template)<a href="https://agentmods.dev/skills/kevin-liu-01/agent-machines/simple-diagnosis-template"><img src="https://agentmods.dev/badge/skills/kevin-liu-01/agent-machines/simple-diagnosis-template/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.
<a href="https://agentmods.dev/skills/kevin-liu-01/agent-machines/simple-diagnosis-template"><img src="https://agentmods.dev/badge/skills/kevin-liu-01/agent-machines/simple-diagnosis-template.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium Excessive Agency · line 16 Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
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 | $0.00000 | $0.01493 |
| Opus 5 | $0.00000 | $0.00746 |
| Sonnet 5 | $0.00000 | $0.00299 |
| Haiku 4.5 | $0.00000 | $0.00149 |
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.
Copies of this mod
1 near-identical copy found in the catalogue:
- simple — 100% identical, 0 lines differ
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.
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:
- 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.
- 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.
- 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.
- 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.
- 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
/simpleanswers. - 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.
/simpleproposes 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.
When to use
- A user asks "why is X slow" / "why does Y fail" / "what's causing Z".
- You have just completed a diagnostic investigation and need to report it.
- The user says "explain the problem" or "propose a fix".
- The user invokes
/simple.
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.
- 9d ago First seen · 90 lines · 0 tokens per session scan A 87f174e607e1
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. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-03.
Other skills, from other repositories
opik-explain
Root-cause a specific Opik trace, or a pattern across traces, and return a grounded explanation. Uses the hosted Opik MCP when it is connected, and falls back to SDK scripting otherwise. Returns the root cause, the evidence spans as clickable Opik UI links, and one suggested next step. Use for "why did this trace…
hermes-plugin-development
Use when: creating, debugging, or integrating Hermes Agent plugins, including Python backend plugins (tools, hooks, routers, middleware) and JavaScript Hermes Desktop runtime plugins.
problem-management
Manage ServiceNow problems — create from linked incidents, proactive pattern detection, RCA with 5-Whys, knownerror workarounds (KEDB), KEDB search by CI/category/keywords, and permanent-fix linkage to changes.
node-inspect-debugger
Debug Node.js with node inspect, inspector attach, breakpoints, Chrome DevTools Protocol, heap snapshots, and CPU profiles.
holix-cron
Schedule recurring agent tasks via Holix built-in gateway cron (not crontab or custom scripts).
blazemeter-troubleshooting
Comprehensive troubleshooting guide for BlazeMeter, covering API Monitoring, Performance Testing, general issues, integrations, and security. Use when troubleshooting for (1) API Monitoring issues (Radar Agent auth, SSL certificates, debug tests), (2) Performance Testing issues (high response time, 500 errors, partial…