agentmods.dev

claude-blog: Instructions file for Claude Code

CLAUDE.md

claude-blog CLAUDE.md is an instructions file for Claude Code from AgriciDaniel/claude-blog. It costs 2,915 tokens per session, scanned A, original, MIT.

Project instructions for Claude Blog, a collection of tools for creating, improving, and managing blog content. It covers the project's structure, commands, writing rules, search visibility, and review process.

In plain words
What is it for?
Use it to create, optimize, review, translate, and manage blog posts within the Claude Blog project.
Why use it?
It helps an agent follow the repository's established workflow and quality checks when working on blog content.

Instructions file for Claude Code

Written for Claude Code: Claude Code plugin machinery. Also seen: mentions CLAUDE.md; mentions subagents; mentions Claude Code.

This is AgriciDaniel/claude-blog's own configuration. It tells Claude Code how to work on claude-blog 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 claude-blog configures →

not rated 2.1krepo +57 5d ago A scan 2,915 tokens original MIT
View source ↗ AgriciDaniel/claude-blog claude-blog.md
About the project

claude-blog is a Claude Code skill suite for planning, writing, optimizing, auditing, localizing, and refreshing blog content. It is for content and SEO workflows that produce articles and related publishing artifacts while checking drafts against defined delivery criteria. The catalogue entries provide the skills, agents, plugins, and instruction used by this workflow.

AgriciDaniel/claude-blog · 2,093 stars · on GitHub · claude-blog.md

Reuse

Borrowing it

Nothing to install: this file belongs to AgriciDaniel/claude-blog. 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/AgriciDaniel/claude-blog/main/CLAUDE.md
Clone the repo
git clone --depth 1 https://github.com/AgriciDaniel/claude-blog

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 claude-blog CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/agricidaniel/claude-blog/claude-md/github.svg)](https://agentmods.dev/instructions/agricidaniel/claude-blog/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/agricidaniel/claude-blog/claude-md"><img src="https://agentmods.dev/badge/instructions/agricidaniel/claude-blog/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.

agentmods 80×15 button for claude-blog CLAUDE.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/agricidaniel/claude-blog/claude-md"><img src="https://agentmods.dev/badge/instructions/agricidaniel/claude-blog/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 2,915 This file is loaded in full into every session.
When invoked 2,915 The same file — it is already loaded in full.
Security scan A 1 finding. A grade says what 26 rules found in the file — not that it is safe.
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 $0.02915 $0.02915
Opus 5 $0.01458 $0.01458
Sonnet 5 $0.00583 $0.00583
Haiku 4.5 $0.00292 $0.00292

Measured 9d ago against content hash 2327fda0f10e, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

claude-blog CLAUDE.md scanned grade A 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.

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

curl -fsSLo install.sh \
CLAUDE.md · 195 lines

How it starts

The opening of the file, as written. The whole thing — 195 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Claude Blog - Blog Creation & Optimization Skill

Project Overview

This repository contains Claude Blog, a Tier 4 Claude Code skill for blog content creation, optimization, and management. It follows the Agent Skills open standard and the 3-layer architecture (directive, orchestration, execution). 32 skill directories (1 orchestrator + 31 sub-skills), 30 user-facing /blog commands, 5 specialized subagents, 12 content templates, and 22 reference docs are dual-optimized for Google rankings (2026 core and spam update timeline, E-E-A-T) and AI citations (GEO/AEO). Includes FLOW framework integration, semantic topic-cluster planning + execution, multilingual publishing (Pro Hub Challenge v1.7.0), BRAND.md/VOICE.md/DISCOURSE.md project-root context auto-load (v1.8.0, fenced via scripts/load_untrusted_root.py with CSPRNG nonces, v1.8.3+), CI-enforced prose hygiene via scripts/lint_prose.py (v1.8.4+), and the 5-gate Blog Delivery Contract (v1.9.0, skills/blog/references/blog-delivery-contract.md) that runs blog_preflight.py

  • a BLOCKING blog-reviewer agent between every draft and the user.

Architecture

claude-blog/
  CLAUDE.md                          # Project instructions (this file)
  docs/CONTRIBUTORS.md               # Pro Hub Challenge attribution and integration decisions
  CHANGELOG.md                       # Keep a Changelog format
  .claude-plugin/plugin.json         # Plugin manifest (v2.2.0)
  .claude-plugin/marketplace.json    # Marketplace catalog for distribution
  .mcp.example.json                  # MCP config example (tracked; .mcp.json is gitignored)
  pyproject.toml                     # Python packaging (3.11+)
  brain/                             # Vendored self-contained evidence-gated Obsidian brain; not plugin payload; tooling stays under skills/
  scripts/analyze_blog.py            # 5-category quality scoring (stdlib)
  scripts/blog_preflight.py          # 5-gate delivery contract runner (v1.9.0)
  scripts/blog_render.py             # md -> html -> pdf renderer; XSS-safe JSON-LD (v1.9.0)
  scripts/blog_hygiene.py            # Optional deterministic hygiene: lazy-load imgs + auto-TOC (v1.11.0)
  scripts/cognitive_load.py          # Per-section concept-density analyzer (v1.8.0)
  scripts/discourse_research.py      # Discourse brief synthesis from SERP JSON (v1.8.0)
  scripts/generate_hero.py           # Hero image ladder: Banana -> Gemini -> stock -> Openverse (v1.9.0)
  scripts/load_untrusted_root.py     # Code-enforced fence helper for BRAND/VOICE/DISCOURSE (v1.8.3)
  scripts/lint_prose.py              # Fence-aware prose-hygiene linter (v1.8.4; CI-enforced)
  scripts/sync_flow.py               # Pulls FLOW references (stdlib, sandboxed)
  scripts/ai_citation_score.py       # AI citation readiness heuristic, 0-100
  scripts/content_decay.py           # GSC content-decay detector: 20%+ QoQ decline (v1.10.0)
  scripts/quality_gate.py            # Pre-commit gate: block posts scoring < 70 (v1.10.0)
  scripts/style_learn.py             # Author voice-profile learner from sample posts (v1.10.0)
  scripts/consistency_check.py       # Local reference + FLOW lock validation
  scripts/dependency_smoke.py        # Offline optional-runtime initialization checks
  scripts/validate_public_release.py # Read-only public worktree validation
  skills/                            # 32 skill directories (1 orchestrator + 31 sub-skills)
    blog/SKILL.md                   # Main orchestrator, routing, scoring
      references/                   # 22 on-demand knowledge files (5 in v1.8.0, 1 in v1.9.0)
      templates/                    # 12 content templates
      scripts/                     # Python analysis scripts
    blog-write/SKILL.md            # Write new articles from scratch
    blog-rewrite/SKILL.md         # Optimize existing blog posts
    blog-analyze/SKILL.md         # 5-category 100-point scoring
    blog-brief/SKILL.md           # Detailed content briefs
    blog-outline/SKILL.md         # SERP-informed outlines
    blog-calendar/SKILL.md        # Editorial calendars
    blog-strategy/SKILL.md        # Blog positioning and planning
    blog-seo-check/SKILL.md      # Post-writing SEO validation
    blog-schema/SKILL.md          # JSON-LD schema generation
    blog-chart/SKILL.md           # Inline SVG data visualizations
    blog-repurpose/SKILL.md       # Multi-platform repurposing
    blog-geo/SKILL.md             # AI citation optimization
    blog-audit/SKILL.md           # Full-site blog health assessment
    blog-image/                    # AI image generation via Gemini
      SKILL.md                    # Image generation sub-skill
      references/                 # 3 reference docs (models, tools, prompts)
      scripts/                    # MCP setup and validation scripts
    blog-cannibalization/SKILL.md # Keyword overlap detection
    blog-factcheck/SKILL.md       # Statistics verification
    blog-persona/SKILL.md         # Writing persona management
    blog-taxonomy/SKILL.md        # CMS taxonomy management
    blog-notebooklm/               # NotebookLM source-grounded research
      SKILL.md                    # NotebookLM query sub-skill
      references/                 # 2 reference docs (commands, troubleshooting)
      scripts/                    # 10 Python scripts + requirements.txt
    blog-audio/                    # Audio narration via Gemini TTS
      SKILL.md                    # Audio generation sub-skill
      references/                 # 1 reference doc (30 voice catalog)
      scripts/                    # 5 Python scripts + requirements.txt
    blog-google/                   # Google API integration
      SKILL.md                    # Google API sub-skill (13 commands, 4 tiers)
      references/                 # 3 reference docs (auth, API, quotas)
      scripts/                    # 11 Google API scripts + venv wrapper
      assets/templates/           # 3 report templates
    blog-cluster/                  # Semantic topic-cluster planning + execution (v1.7.0)
      SKILL.md                    # Cluster planning + execute orchestrator
      references/                 # 3 ref docs (semantic clustering, architecture, execution)
    blog-flow/                     # FLOW framework prompts (v1.7.0)
      SKILL.md                    # FLOW orchestrator (find/optimize/win/prompts/sync)
      references/                 # Synced from github.com/AgriciDaniel/flow (CC BY 4.0)
    blog-multilingual/             # One-command international publishing (v1.7.0)
      SKILL.md                    # Multilingual orchestrator
    blog-translate/                # SEO-optimized translation (v1.7.0)
      SKILL.md
      references/                 # Translation rules + cultural adaptation profiles
    blog-localize/                 # Cultural deep-adaptation (v1.7.0)
      SKILL.md
    blog-locale-audit/             # Multilingual content QA (v1.7.0)
      SKILL.md
    blog-brand/SKILL.md            # BRAND.md + VOICE.md context files (v1.8.0)
    blog-discourse/SKILL.md        # Last-30-days discourse research (v1.8.0)
    blog-style/SKILL.md            # Author voice-profile learner (v1.10.0)
    blog-decay/SKILL.md            # GSC content-decay detector (v1.10.0)
  agents/                            # 5 specialized subagents
    blog-researcher.md              # Statistics and source research
    blog-writer.md                  # Content generation
    blog-seo.md                     # SEO validation
    blog-reviewer.md                # Quality scoring (no Bash, post v1.7.0 hardening)
    blog-translator.md              # Multilingual translation (no Bash, v1.7.0)
  tests/                             # 250+ pytest checks incl. delivery-contract + security suites

Read the full file on GitHub · 195 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. 9d ago First seen · 195 lines · 2,915 tokens per session scan A 2327fda0f10e

Subscribe to this mod's changes

claude-blog CLAUDE.md is an instructions file published in the GitHub repository AgriciDaniel/claude-blog (2,093 stars, last pushed 5d ago), licensed MIT. It adds 2,915 tokens to every session, about $0.0146 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Claude CodeWriting and docsaiai-contentclaude-code-skillcontent-creationseo
Related

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.

vercel/next.js · 7,296 tokens

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.

openai/codex · 5,153 tokens

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).

microsoft/vscode · 6,785 tokens

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).

microsoft/vscode · 5,001 tokens

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.

langchain-ai/langchain · 4,469 tokens

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.

deepseek-ai/deepseek-harness · 3,735 tokens