indranilbanerjee
contentforge
Open-source enterprise content pipeline: 21 skills, 13 agents, 10 quality gates, 35-pattern humanizer, and C2PA-signed .docx output.
Repository last updated Jul 18, 2026
Overview
ContentForge is an open-source enterprise content production pipeline designed for marketing teams that need to ship large volumes of long-form content with brand consistency, citation integrity, and internal-link strategy. It orchestrates a 10-phase workflow using 13 specialist agents and enforces a quality gate after every phase to catch issues before they propagate.
The pipeline produces real .docx files with embedded appendices for SEO, quality, production details, and internal link maps. A 35-pattern AI-detection humanizer and a fact-checker subagent ensure output reads naturally and citations are verified. C2PA content provenance signing provides EU AI Act Article 50 compliance.
ContentForge installs on Claude Code, Anthropic Cowork, OpenAI Codex, Cursor 2.5+, GitHub Copilot CLI, Google Antigravity 2.0, Hermes Agent, OpenClaw, and 35+ additional Agent Skills platforms. It is created by Indranil Banerjee and released under the MIT license.
Highlights
- 10-phase pipeline with 13 specialist agents and 10 quality gates
- 35-pattern AI-detection humanizer with self-critique meta-pass
- Fact-checker subagent verifies URLs and cross-references claims
- Real .docx output with embedded SEO, quality, and link appendices
- C2PA provenance signing for EU AI Act Article 50 compliance
- Checkpoint/resume support for interrupted runs
Features
Multi-Phase Content Pipeline
10 phases from research to output, each with a dedicated quality gate that catches and re-runs bad output before it propagates.
AI-Detection Humanizer
35 patterns plus a self-critique meta-pass that rewrite AI-sounding text to read human, with measured burstiness gates via text-metrics.py.
Fact-Checker Subagent
Verifies URLs and cross-references factual claims against sources to eliminate hallucinated citations.
Internal Linking Strategy
Three-category linking (topical, commercial, authority) that turns content into a funnel rather than a stranded page.
Real .docx Output
Produces Word files with body, references, and four appendices: SEO scorecard, quality scorecard, production details, and internal link map.
C2PA Provenance Signing
Signs content with C2PA provenance metadata for EU AI Act Article 50 compliance, applicable from August 2, 2026.
Checkpoint and Resume
Saves each completed phase to disk; interrupted runs can be resumed from the last completed phase without re-running earlier work.
Cross-Platform Installation
Supports 8 native platforms (Claude Code, Cowork, Codex, Cursor, Copilot CLI, Antigravity, Hermes, OpenClaw) plus 35+ Agent Skills platforms.
Installation
Commands are reproduced exactly as published by the project maintainers. Always check the upstream repository for the current instructions.
> If ContentForge saves your team time, [give it a star ⭐](https://github.com/indranilbanerjee/contentforge/stargazers) — it's the single thing that helps other marketing teams find it.
---
## Why ContentForge
Most AI writing tools produce one draft, in one tone, with no quality gates. The output reads like AI, factual claims are unverified, internal links don't exist, brand voice drifts, and the file format is markdown when the editor wants Word. ContentForge fixes this end-to-end:
| Capability | Why it matters |
|---|---|
| **10-phase pipeline with a quality gate after every phase** | Bad output is caught and re-run before it propagates downstream |
| **35-pattern AI-detection humanizer** + self-critique meta-pass | Output reads human, not AI — measured burstiness gate (`text-metrics.py`) |
| **Fact-checker subagent** verifies URLs and cross-references claims | Citations work and aren't hallucinated |
| **Three-category internal linking** (topical / commercial / authority) | Content becomes a funnel, not a stranded page |
| **Real `.docx` output** with embedded SEO + Quality + Production + Internal-Link appendices | Editor / design team gets a working Word file, not markdown |
| **C2PA content provenance signing** for EU AI Act Article 50 compliance | Long-form AI-written content distributed in EU markets needs provenance from 2 Aug 2026 |
---
## Supported surfaces (v3.16.1)
| Platform | Install command | Manifest path | Status |
|---|---|---|---|
| **Claude Code** CLI + IDE extension | `/plugin install contentforge@neels-plugins` | `.claude-plugin/plugin.json` | Full support (canonical for solo devs) |
| **Anthropic Cowork** | Plugins panel in UI → Add marketplace → `indranilbanerjee/neels-plugins` → Install ContentForge | same `.claude-plugin/` files | **Recommended for teams** — `/contentforge:cf-cowork-setup` wires Google Drive for team-shareable output |
| **OpenAI Codex** CLI + IDE + App | `codex plugin marketplace add indranilbanerjee/neels-plugins` then `codex plugin install contentforge@neels-plugins` | `.codex-plugin/plugin.json` (published OpenAI schema) | Full skills + MCP support |
| **Cursor 2.5+** | In any Cursor Agent chat: `/add-plugin contentforge@https://github.com/indranilbanerjee/contentforge` | `.cursor-plugin/plugin.json` (verified Cursor 2.5+ JSON Schema) | Full skills + agents + commands support |
| **GitHub Copilot CLI** | `copilot plugin marketplace add indranilbanerjee/neels-plugins` then `copilot plugin install contentforge@neels-plugins` | `.github/plugin/plugin.json` (Copilot also recognizes `.claude-plugin/plugin.json` as fallback) | Full skills + MCP support |
| **Google Antigravity 2.0** CLI + IDE | `agy plugin install https://github.com/indranilbanerjee/contentforge` | `gemini-extension.json` (at repo root, per Google's reference pattern) | Full skills + hooks support |
| **Hermes Agent** (Nous Research) — Desktop + CLI on macOS / Windows / Linux | `hermes plugins install indranilbanerjee/contentforge` | `plugin.yaml` + `__init__.py` at repo root (Hermes native spec) | Native plugin — adapter walks `skills/` at register time and exposes all 21 skills via `ctx.register_skill()`. Targets Hermes Desktop v0.15.2+ (public preview June 2 2026). |
| **OpenClaw** (formerly Clawdbot / Moltbot) | `openclaw plugins install git:github.com/indranilbanerjee/contentforge` | `openclaw.plugin.json` at repo root (also auto-detects `.claude-plugin/plugin.json` as Claude-compatible bundle) | Native plugin via `openclaw.plugin.json`; `skills` field points at `./skills`. |
**Why this works:** Agent Skills became an open standard in December 2025 (41+ agent products by June 2026). All 21 SKILL.md files in ContentForge are platform-portable as written. The sibling manifests are thin platform-specific wrappers around the same `skills/` directory — no skill duplication.
**Works on 35+ additional Agent Skills platforms** without per-platform manifests — Goose (Block), OpenHands, OpenCode (sst), Junie (JetBrains), Gemini CLI, Roo Code, Cline/Windsurf, Kiro, Amp, Letta, Mux, Factory, Workshop, Tabnine, Mistral Vibe, and more. Point any Agent-Skills-compatible client at `https://github.com/indranilbanerjee/contentforge/tree/master/skills` and all 21 ContentForge skills are immediately discoverable.
---
## Quick start
### 1. Install the plugin
**In Claude Code (CLI or VS Code/JetBrains extension):****In Anthropic Cowork:**
1. Open the **Plugins** panel in the Cowork UI (sidebar / settings)
2. Click **Add marketplace**, paste `indranilbanerjee/neels-plugins`
3. After the marketplace syncs, find **ContentForge** in the listed plugins and click **Install**
4. Then run `/contentforge:cf-cowork-setup` once to wire Google Drive as your team's output destination
> ⚠ `/plugin` slash commands work **only in Claude Code (CLI + IDE extension)**. They do NOT work in Cowork, Claude.ai web, or Claude Desktop — use UI navigation in those environments. The `/contentforge:*` skills (like `/contentforge:create-content`) work in all environments where plugins are loaded; only the `/plugin` management family is Claude-Code-only.
### 2. Turn on auto-update (one-time, recommended)
**Third-party marketplaces — including this one — have auto-update OFF by default in Claude Code.** When v3.12.6 is the marketplace's latest and you're still running v3.12.0, nothing tells you. There's no banner, no badge, no notification. So the first thing to do after install is enable updates:
Open `/plugin`, go to the **Marketplaces** tab, find `neels-plugins`, and toggle **Enable auto-update**. Done — Claude Code will refresh and pull new ContentForge releases at startup from now on, prompting you to run `/reload-plugins` to pick up changes mid-session (no full restart, conversation context preserved).
If you'd rather update manually each time instead, see the [Updating](#updating) section below.
### 3. Set up your first brandThe agent walks you through brand voice, terminology, guardrails, citation rules, internal-linking site structure, and (if you want commercial impact) the **brand_pages** block — your product/service URLs, conversion CTAs, and authority pages. It saves a `brand-profile.json` to `~/.claude-marketing/<brand-slug>/`.
### 4. Generate contentThe skill prompts you for content type, brand, topic, target word count, and audience. It then runs 10 phases via specialized subagents (research → fact-check → draft → visuals → validate → proofread → SEO → humanize → review → output), enforces a quality gate after each phase, and writes a real `.docx` you can hand to your editor or design team.
### 5. Find your output
ContentForge now writes the finished `.docx` to **two** places (v3.12.3+):
**User-visible copy — this is the one to open:**Requirements
- Python 3.8+
- Claude Code, Anthropic Cowork, OpenAI Codex, Cursor 2.5+, GitHub Copilot CLI, Google Antigravity 2.0, Hermes Agent v0.15.2+, or OpenClaw
- Internet connection for marketplace plugin installation
How it's built
ContentForge is written in Python and organized as a plugin with platform-specific manifests in .claude-plugin/, .codex-plugin/, .cursor-plugin/, .github/plugin/, and plugin.yaml at the repo root. All 21 skills live in the skills/ directory as portable SKILL.md files; sibling manifests are thin wrappers around the same skill directory, avoiding duplication.
The pipeline uses a file-based phase handoff contract: each phase writes its output to a canonical run directory, and the next phase reads from disk rather than receiving pasted drafts. Checkpointing is handled by scripts/checkpoint-manager.py, which saves state after each phase. The humanizer uses config/humanization-patterns.json (35 patterns) and scripts/text-metrics.py to measure burstiness and FK readability scores.
ContentForge integrates with agent platforms via the Agent Skills open standard (December 2025). On Hermes Agent, the __init__.py adapter walks the skills/ directory at registration time and exposes all skills via ctx.register_skill(). The plugin also supports MCP (Model Context Protocol) via .mcp.json.example and connectors documented in CONNECTORS.md.
Source
This summary was written for Neura Market from the project's own repository. Install commands, identifiers and licence details are reproduced unchanged. The indranilbanerjee/contentforge repository is the authoritative source and the place to file issues or contribute.
Category: Content Creation · Licensed under MIT