link: Skill for Claude Code

.claude/skills/lanes-writing/SKILL.md

lanes-writing is a skill for Claude Code from lanes-sh/link. It costs 54 tokens per session (2,001 once invoked), scanned A, original, Apache-2.0.

A writing guide for Lanes documentation, README files, marketing copy, use cases, comparisons, and release posts. It sets the expected tone, page structure, and rules for keeping each sentence useful to a reader in a hurry.

In plain words
What is it for?
Writing or editing Lanes documentation, quickstarts, README files, comparison pages, use cases, and release announcements.
Why use it?
It keeps related pages consistent and prevents unnecessary explanation from getting in the way of setup or decision-making. It also helps writers choose between quick instructions, layered explanations, and product-focused copy.

Skill for Claude Code

Written for Claude Code: installed under .claude/. Also seen: reads .claude/ paths.

This is lanes-sh/link's own configuration. It tells Claude Code how to work on link itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything link configures →

Reuse

Borrowing it

Nothing to install: this file belongs to lanes-sh/link. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/lanes-sh/link/develop/.claude/skills/lanes-writing/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/lanes-sh/link

Made for: Claude Code.

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 lanes-writing

README.md
[![agentmods](https://agentmods.dev/badge/skills/lanes-sh/link/lanes-writing/github.svg)](https://agentmods.dev/skills/lanes-sh/link/lanes-writing)
Your own site
<a href="https://agentmods.dev/skills/lanes-sh/link/lanes-writing"><img src="https://agentmods.dev/badge/skills/lanes-sh/link/lanes-writing/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 lanes-writing

Your own site · 80×15
<a href="https://agentmods.dev/skills/lanes-sh/link/lanes-writing"><img src="https://agentmods.dev/badge/skills/lanes-sh/link/lanes-writing.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 54 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,001 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. Third-party audits
  • NVIDIA SkillSpector warn 7 Sept 2026
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 Agent Snooping · line 8
    Skill enumerates or reads other installed skills. Access to other skills' SKILL.md files or the skills directory reveals prompt instructions, capabilities, and secrets that should be invisible to peer skills.
    Fix: Remove all code or instructions that list or read other skills' files or directories. Skills should operate independently; cross-skill access is a privilege escalation.
How audits are shown
Origin original No closer match found 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 $0.00054 $0.02001
Opus 5 $0.00027 $0.01001
Sonnet 5 $0.00011 $0.00400
Haiku 4.5 $0.00005 $0.00200

Measured 2d ago against content hash 38c84b36fd4e, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

lanes-writing 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 2d 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.

.claude/skills/lanes-writing/SKILL.md · 186 lines

How it starts

The opening of the file, as written. The whole thing — 186 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Writing for Lanes

Canonical copy lives in lanes-sh/web at .claude/skills/lanes-writing/SKILL.md. The copies in lanes-sh/link and lanes-sh/core follow it; edit the canonical one.

The reader

One person, in a hurry, who wants the thing running. They did not come to admire the architecture. Every sentence between them and a working setup is a cost, and the only justification for that cost is that the sentence saves them more than it spends.

Step 1: pick the register

Three registers. Which one a page gets depends on what success means for its reader.

Register Reader's success Shape
Quickstart "It is running." Prerequisite line, numbered commands, one line of result, one link out. Reasoning goes in a Notes block at the foot
Layered "I understand this well enough to decide." What it is, what you do about it, then why it works this way. In that order, never interleaved
Site voice "I know whether this is for me." A claim, then the proof. Benefit-first subheads, second person, short paragraphs

Look the page up rather than deciding by feel:

Page type Register
Quickstart, install, connect, deploy, "add it to your agent" Quickstart
Per-feature how-to (worktrees, loops, gateway, sessions, issue board) Quickstart, plus one sentence on a step with a real gotcha
Concept and explainer (architecture, security, scopes, identity, capabilities) Layered
Reference (commands, settings, shortcuts, providers, errors, API) Tables only. One row per thing, no prose between rows
README, first screen Site voice
README, everything below install Quickstart
Index and overview (/docs, /docs/mcp, src/content/pages/*.md) Site voice
Use case, comparison Site voice
Blog Leave the voice alone. Correct facts only
Terms, privacy, GDPR, cookies Plain legal English. Accuracy beats brevity. No register change

Step 2: make every heading name an outcome

Read the full file on GitHub · 186 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. 2d ago Changed · -1 lines 38c84b36fd4e
  2. 5d ago First seen · 187 lines · 54 tokens per session scan A 4d2aa7fe4b35

Subscribe to this mod's changes

lanes-writing is a skill published in the GitHub repository lanes-sh/link (34 stars, last pushed yesterday), licensed Apache-2.0. It adds 54 tokens to every session and 2,001 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 2026-09-05.