Borrowing it
Nothing to install: this file belongs to lynx-family/lynx-website. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/lynx-family/lynx-website/main/.agents/skills/doc-description-governance/SKILL.mdgit clone --depth 1 https://github.com/lynx-family/lynx-websiteWrote 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/lynx-family/lynx-website/doc-description-governance)<a href="https://agentmods.dev/skills/lynx-family/lynx-website/doc-description-governance"><img src="https://agentmods.dev/badge/skills/lynx-family/lynx-website/doc-description-governance/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/lynx-family/lynx-website/doc-description-governance"><img src="https://agentmods.dev/badge/skills/lynx-family/lynx-website/doc-description-governance.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 | $0.00104 | $0.01571 |
| Opus 5 | $0.00052 | $0.00785 |
| Sonnet 5 | $0.00021 | $0.00314 |
| Haiku 4.5 | $0.00010 | $0.00157 |
Grade A, and why
doc-description-governance 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 — 141 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Documentation Page Description Governance
This skill helps you audit and optimize frontmatter description fields across documentation pages. Well-governed descriptions keep generated outputs (like llms.txt) compact and meaningful, and also improve SEO and link previews.
Why This Matters
Pages without explicit description frontmatter fall back to their first paragraph — often hundreds of tokens of prose, unresolved MDX variables, JSX tags, or import statements. This bloats any consumer of the description (llms.txt, meta tags, link previews). The goal is to ensure every page has a deliberate, concise description that stays within a token budget (typically 30 tokens as measured by tiktoken gpt-4o).
Workflow
1. Audit Current State
Use the built llms.txt as a detection surface — it exposes every page's effective description in one file. Identify entries exceeding the token budget:
import { encodingForModel } from 'js-tiktoken';
import fs from 'node:fs/promises';
const enc = encodingForModel('gpt-4o');
const TOKEN_LIMIT = 30;
const llmsTxt = await fs.readFile('doc_build/llms.txt', 'utf-8');
const appendixStart = llmsTxt.indexOf('## 98. Appendix: Links');
const appendixContent = llmsTxt.slice(appendixStart);
const lines = appendixContent.split('\n').filter((l) => l.startsWith('* ['));
for (const line of lines) {
const match = line.match(/^\* \[([^\]]*)\]\(([^)]+)\): (.+)$/);
if (!match) continue;
const [, title, url, desc] = match;
const tokens = enc.encode(desc).length;
if (tokens > TOKEN_LIMIT) {
console.log(`${tokens} tokens: ${url} | ${desc.slice(0, 80)}`);
}
}
Count tokens with tiktoken, not word count. Word-splitting (split(/\s+/)) severely undercounts Chinese/Japanese text where each character is 1-2 tokens.
2. Classify Each Overlong Entry
For each entry exceeding the budget, determine the fix strategy:
| Situation | Fix |
|---|---|
| File has no frontmatter description | Add description field to frontmatter |
| File already has a frontmatter description that's too long | Do NOT modify the source — rely on postprocess truncation |
Description contains unresolved MDX variables ({someVar['key']}) |
Add a proper description frontmatter to override |
| Description contains JSX/import leakage | Add a proper description frontmatter to override |
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 · 141 lines · 104 tokens per session scan A 0808054a8a66
doc-description-governance is a skill published in the GitHub repository lynx-family/lynx-website (130 stars, last pushed yesterday), licensed Apache-2.0. It adds 104 tokens to every session and 1,571 once invoked, about $0.0005 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
deepchat-cli
Use DeepChat's bundled CLI control plane for model inference, image/video/speech generation, transcription, OCR, artifact inspection, public configuration, Skills, and MCP operations. Activate when a user asks to invoke DeepChat capabilities that are not already exposed as a more specific tool, compare models, run a…
git-commit
Generate well-formatted git commit messages following conventional commit standards.
doc-coauthoring
Guide users through a structured workflow for co-authoring documentation. Use when user wants to write documentation, proposals, technical specs, decision docs, or similar structured content. This workflow helps users efficiently transfer context, refine content through iteration, and verify the doc works for readers.…
computer-use
Drive native desktop apps through DeepChat's built-in Computer Use tools. Use when the user asks to operate, inspect, automate, or perform a GUI task in a real desktop application.
gonavi-cli
Operate databases through the GoNavi headless CLI — the gonavi executable shipped in verified GitHub Release archives. Covers listing/adding/importing saved connections, running SQL queries against saved connections or ad-hoc connection files, exporting result sets to csv/json/md/html/xlsx, batch-executing SQL files…
memory-management
Guide the agent to recall, remember, and route durable learning into Memory, Skills, Scheduled Tasks, or Tape.