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 kalyvask/winning-writing --skill pick-a-lanegit clone --depth 1 https://github.com/kalyvask/winning-writingWrote 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/kalyvask/winning-writing/pick-a-lane)<a href="https://agentmods.dev/skills/kalyvask/winning-writing/pick-a-lane"><img src="https://agentmods.dev/badge/skills/kalyvask/winning-writing/pick-a-lane/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/kalyvask/winning-writing/pick-a-lane"><img src="https://agentmods.dev/badge/skills/kalyvask/winning-writing/pick-a-lane.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00150 | $0.02156 |
| Opus 5 | $0.00075 | $0.01078 |
| Sonnet 5 | $0.00030 | $0.00431 |
| Haiku 4.5 | $0.00015 | $0.00216 |
Grade A, and why
pick-a-lane 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 12d 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 — 165 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Pick a lane
Source: Konrad's rule 7 from Winning Writing, Adam Bryant's Corner Office column (NYT) on what CEOs look for in candidates, and a before/after rewrite pattern taught in Kramon's class.
The premise
Most personal writing fails not because the writer lacks material but because the writer has too much of it and won't choose. Five accomplishments mentioned in 200 words means each one gets 40 words. None lands.
Pick a lane. Tell one story in full. Trust that the reader who wants the rest can find your LinkedIn.
"Pick a lane, and stay in it. Don't stray all over the highway by regurgitating your resume. Stay on that story and tell it right." — Adam Bryant (via Glenn Kramon's class)
This is distinct from compression. Compression cuts adverbs and throat-clearing. Pick-a-lane cuts whole biographical episodes. They run different surgeries.
What "all over the highway" looks like
Three failure shapes. All three can fit in one paragraph.
1. The career-arc dump
"I started in management consulting, then went to a Series B startup, then moved to private equity, then co-founded a company, then came to GSB."
Five jobs in one sentence. The reader learns nothing about any of them. This is what your LinkedIn header is for.
2. The skill-collection dump
"I have led teams of 5–50, built ML systems from scratch, raised capital from top-tier VCs, written code in seven languages, and managed P&Ls of $100M+."
Five claims, zero evidence for any of them. Reads as bragging because each line is a label without proof.
3. The story-soup
"In high school I won the state debate championship. In college I founded a tutoring nonprofit. At my first job I led a $50M product launch. At my second job I rebuilt the data platform. At Stanford I'm exploring AI agents and writing a Substack."
Five stories, each two sentences. None of them is told. The reader doesn't know what you actually did or why it mattered.
What "stay in your lane" looks like
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.
- 12d ago First seen · 165 lines · 150 tokens per session scan A f19fc7626f89
pick-a-lane is a skill published in the GitHub repository kalyvask/winning-writing (13 stars, last pushed 6d ago), licensed MIT. It adds 150 tokens to every session and 2,156 once invoked, about $0.0007 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 2026-08-30.
Other skills, from other repositories
spark-engineer
Use when writing Spark jobs, debugging performance issues, or configuring cluster settings for Apache Spark applications, distributed data processing pipelines, or big data workloads. Invoke to write DataFrame transformations, optimize Spark SQL queries, implement RDD pipelines, tune shuffle operations, configure…
debugging-wizard
Parses error messages, traces execution flow through stack traces, correlates log entries to identify failure points, and applies systematic hypothesis-driven methodology to isolate and resolve bugs. Use when investigating errors, analyzing stack traces, finding root causes of unexpected behavior, troubleshooting…
Reverse Engineering & Binary Analysis
Binary analysis, assembly interpretation, disassembly, decompilation, firmware RE, and protocol reverse engineering.
perf-profiler
A performance investigation guide that uses repeatable measurements and profiling evidence to find where software spends time or resources. Profiling records runtime activity such as CPU use, memory use, database work, or network delays.
log-analyzer
A log-analysis helper that reads application and system logs to find unusual patterns and likely causes. Logs are records of events such as errors, requests, warnings, and service activity.
lcx-report-bug
Create a high-signal bug issue or PR in the repo that owns the defect. Use this whenever the user asks to report, file, open, or triage a LazyCodex, lazycodex-ai, omo-codex, Codex plugin, or upstream Codex CLI bug, especially when they need source-backed root cause, reproduction steps, fix guidance, and GitHub routing.