Borrowing it
Nothing to install: this file belongs to XuanRanL/loamwright-SEO-Skill. 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/XuanRanL/loamwright-SEO-Skill/main/CLAUDE.mdgit clone --depth 1 https://github.com/XuanRanL/loamwright-SEO-SkillWrote 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/instructions/xuanranl/loamwright-seo-skill/claude-md)<a href="https://agentmods.dev/instructions/xuanranl/loamwright-seo-skill/claude-md"><img src="https://agentmods.dev/badge/instructions/xuanranl/loamwright-seo-skill/claude-md/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/instructions/xuanranl/loamwright-seo-skill/claude-md"><img src="https://agentmods.dev/badge/instructions/xuanranl/loamwright-seo-skill/claude-md.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 | $0.14447 | $0.14447 |
| Opus 5 | $0.07223 | $0.07223 |
| Sonnet 5 | $0.02889 | $0.02889 |
| Haiku 4.5 | $0.01445 | $0.01445 |
Grade B, and why
loamwright-SEO-Skill CLAUDE.md scanned grade B with 1 finding 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 9d 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.
Reads agent configuration directoriesmediumAgent snooping
.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.
After any install, confirm the cache is what you think it is — `cat ~/.claude/plugins/cache/.../xuanran-seo-blog-writer/*/VERSION`. A stale cache mimics "the fix didn't work": on 2026-08-05 the installed plugin sat at 3. How it starts
The opening of the file, as written. The whole thing — 832 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Project: Xuanran SEO Blog Writer (Claude Code Plugin)
This file gives Claude Code instances working ON this codebase the project conventions.
What this is
A Claude Code Plugin that orchestrates SEO + GEO content creation. Not the runtime instructions—those live in skills/, subskills/, agents/.
This file is for developers building the plugin itself — but the HARD RULES below also apply when running the pipeline directly from this dev directory (before the plugin is installed via /plugin install).
HARD RULES — apply unconditionally when running the article pipeline
These rules came from production failures on 2026-05-20. Memory entries cover the full reasoning; this section is the short-form enforceable contract that the plugin-source CLAUDE.md auto-loads. Per-skill copies of these rules also live in skills/seo-blog/SKILL.md and skills/phase-publish/SKILL.md, but the cache split means those only take effect after /plugin install. This root file is auto-loaded for any session opened in the plugin source dir, so it's the durable enforcement point during dev.
Rule 1 — Exact-keyword fidelity (never silently dedupe variants)
When the user supplies a search term for a new article — including typos, plurals, grammatical variants, alternate spellings, or terms "similar to" existing content — that term IS the SEO target. Default = new keyword = new article. Never silently treat the new keyword as already-served by a near-neighbor existing article.
- Before reusing/canonicalizing/redirecting to existing content, ask the user explicitly.
- If genuine cannibalization risk exists, the answer is differentiation by angle/format/persona — not skipping the work.
- Per project, consult
projects/{slug}/CLAUDE.mdfor an inventory of live articles so the differentiation analysis is informed, not guessed. - Full reasoning: see auto-memory
feedback_exact_keyword_fidelity.md.
Rule 2 — Project article CSS injection is mandatory at publish
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.
- 9d ago First seen · 832 lines · 14,447 tokens per session scan B a9f72c3bf8c0
loamwright-SEO-Skill CLAUDE.md is an instructions file published in the GitHub repository XuanRanL/loamwright-SEO-Skill (47 stars, last pushed 22d ago), licensed Apache-2.0. It adds 14,447 tokens to every session, about $0.0722 per session on Opus 5. A static security scan graded it B with 1 finding (reads agent configuration directories). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other instructions, from other repositories
next.js AGENTS.md
AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.
codex AGENTS.md
AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.
vscode buildNext.instructions.md
Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).
langchain AGENTS.md
AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.
deepseek-harness AGENTS.md
AGENTS.md instructions for deepseek-ai/deepseek-harness, covering agents.md, pre-stable apis and released session data, repository layout, commands and host sandbox failures.