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 jonZlotnik/how-to-agent --skill lead-with-the-pointgit clone --depth 1 https://github.com/jonZlotnik/how-to-agentWrote 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/jonzlotnik/how-to-agent/lead-with-the-point)<a href="https://agentmods.dev/skills/jonzlotnik/how-to-agent/lead-with-the-point"><img src="https://agentmods.dev/badge/skills/jonzlotnik/how-to-agent/lead-with-the-point/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/jonzlotnik/how-to-agent/lead-with-the-point"><img src="https://agentmods.dev/badge/skills/jonzlotnik/how-to-agent/lead-with-the-point.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.00050 | $0.00521 |
| Opus 5 | $0.00025 | $0.00260 |
| Sonnet 5 | $0.00010 | $0.00104 |
| Haiku 4.5 | $0.00005 | $0.00052 |
Grade A, and why
lead-with-the-point 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 11d 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 — 43 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Lead With the Point
Readers decide in the first sentence whether to keep reading. Put the conclusion there: what changed, what to do, or what is true. Background, reasoning, and caveats come after, ordered so the reader can stop at any paragraph and lose only detail, never the message.
When to use
- A commit message, PR description, or reply opens with background instead of the change
- A doc section makes the reader scroll to learn what it concludes
- A comment explains history before stating what the code does
- You catch yourself writing "First, some context"
Protocol
- Write the point in one sentence. What changed, what to do, or what is true. Put it first. Derive it from the content — the diff, the data, the document — not from what you expect it to say.
- Order the rest by decreasing importance. Reasons, then evidence, then caveats, then history. Each paragraph should matter less than the one before it.
- Apply the rule per section. In multi-section documents, the first sentence of each section states that section's conclusion.
- Test by first sentences. Read only the first sentence of each paragraph. If the message does not come through, restructure and test again.
Example
Before: While investigating the login timeouts we noticed the pool was
misconfigured, and after discussion we decided to raise the size.
After: Raise the connection pool size from 10 to 50. Login requests
were timing out because the pool was exhausted under load.
Red flags (rationalizations to reject)
- "The reader needs context first." — The point is the context for everything else. Lead with it.
- "The conclusion needs its caveats." — State the conclusion, then the caveats. Never bury the verdict inside them.
- "It feels blunt." — Blunt is a feature in technical prose. The reader came for the point.
Composes with
- [[one-idea-per-sentence]] — a clear lead sentence carries exactly one idea.
- [[omit-needless-words]] — throat-clearing openings are needless words in front of the point.
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.
- 11d ago First seen · 43 lines · 50 tokens per session scan A 685a6665d452
lead-with-the-point is a skill published in the GitHub repository jonZlotnik/how-to-agent (2 stars, last pushed 1mo ago), licensed MIT. It adds 50 tokens to every session and 521 once invoked, about $0.0003 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…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…
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…