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 agentmods add skills/lolay/nowline/optimize-docsnpx skills add lolay/nowline --skill optimize-docsgit clone --depth 1 https://github.com/lolay/nowlineWhat 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 | $0.00081 | $0.01147 |
| Opus 5 | $0.00041 | $0.00574 |
| Sonnet 5 | $0.00016 | $0.00229 |
| Haiku 4.5 | $0.00008 | $0.00115 |
Grade A, and why
optimize-docs 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 yesterday.
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 — 68 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Optimize Docs
Adapted from prior art: imsanchez/agents-md-skill (read → fetch best practices → decide updates workflow), markoblogo/AGENTS.md_generator (marker-based in-place edits), anthropics/skills (structure patterns). Authoritative sources: agents.md spec, Diataxis framework, llms.txt convention.
Human vs agent docs
| Audience | Files | Purpose |
|---|---|---|
| Humans | README.md, CONTRIBUTING.md, specs/, ops/, CHANGELOG.md |
Quick start, rationale, contribution workflow, product/engineering decisions |
| Agents | AGENTS.md (+ nested AGENTS.md in subdirs if needed) |
Exact commands, conventions, never-touch boundaries, non-obvious patterns |
Must: never duplicate content across the two audiences. Link instead of copy. The Makefile is the single source of truth for build/test/lint/deploy command strings — docs must match make help, not raw tool invocations.
Workflow
- Inventory — list every doc file in scope (see "Docs in this repo" below). Note line count and obvious duplication.
- Classify — tag each section as human-only, agent-only, or shared (shared → pick one home, link from the other).
- Trim — remove content inferable from code, manifests (
package.json,go.mod,versions.tf), or linter config. Remove stale commands, time-sensitive notes, and README content pasted into AGENTS.md. - Verify commands — every command in docs must be copy-pasteable and match a
make <target>. Prefermake pre-commitfor the local gate (alias ofmake ci). - Structure — keep AGENTS.md lean (target under 150–200 lines). Use tables, lists, explicit Must/Recommend labels, and good-vs-bad examples. Human docs follow Diataxis: tutorials, how-to, reference, explanation — each doc has one job.
- Cross-link — replace duplication with relative links. AGENTS.md points to CONTRIBUTING.md for full workflow; CONTRIBUTING.md points to AGENTS.md for agent-specific rules.
- Verify — run the checklist below before finishing.
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.
- yesterday First seen · 68 lines · 81 tokens per session scan A 1c069fed5db5
optimize-docs is a skill published in the GitHub repository lolay/nowline (0 stars, last pushed 4d ago), licensed Apache-2.0. It adds 81 tokens to every session and 1,147 once invoked, about $0.0004 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
meta-tags-optimizer
Optimize title tags, meta descriptions, Open Graph, and Twitter cards for maximum click-through rate. Generates multiple A/B test variations with character counting and SERP preview. Use when asked to "optimize title tag", "write meta description", "improve CTR", "Open Graph tags", "fix my meta tags", "social media…
setup-cms
Connect a CMS to notfair SEO tools. Guides users through configuring WordPress, Strapi, Contentful, or Ghost — tests the connection, and writes credentials to .env.local. Once set up, seo-analysis automatically cross- references CMS content against Google Search Console data. Use whenever the user says "connect my…
broken-link-checker
Scans a website to find broken links (404s, 500s). Crawls internal pages, identifies broken outbound links, and reports source pages for easy fixing. Use this when the user asks to "check for broken links", "find 404s", "audit my links", or "is my site healthy".
google-ads-audit
Google Ads account audit and business context setup. Run this first — it gathers business information, analyzes account health, and saves context that all other ads skills reuse. Trigger on "audit my ads", "ads audit", "set up my ads", "onboard", "account overview", "how's my account", "ads health check", "what should…
hreflang-international
International / multilingual SEO audit focused on hreflang correctness. Detects and diagnoses the most common (and ranking-damaging) hreflang mistakes: missing or broken return tags, wrong language/region codes, missing x-default, self-referencing errors, conflicts between hreflang and canonical, and inconsistent…
paid-ads-linkedin
Audit, diagnose, plan, and safely operate connected LinkedIn Ads accounts through the NotFair MCP, with an export-based fallback. Use for LinkedIn advertising, sponsored content, lead-generation forms, job-title or company targeting, campaign groups, creatives, conversions, lead quality, budgets, bids, or approved…