What is socialforge AGENTS.md?

Project instructions for SocialForge, a production system for creating and adapting social-media content. It covers calendars, brand assets, generated images and videos, review, platform-specific copy, and content provenance.

Use them when planning, generating, adapting, reviewing, or signing social-media campaigns and their visual assets.

They help agents follow the system's rules when producing content, especially the requirement to preserve brand assets and include human review where needed.

socialforge AGENTS.md — Instructions file for Codex and OpenCode by indranilbanerjee: Project instructions for SocialForge, a production sys

Install

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.

agentmods

npx agentmods add instructions/indranilbanerjee/socialforge/agents-md

Clone the repo

git clone --depth 1 https://github.com/indranilbanerjee/socialforge

Made for: Codex, OpenCode.

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.

README.md

[![agentmods](https://agentmods.dev/badge/instructions/indranilbanerjee/socialforge/agents-md.svg)](https://agentmods.dev/instructions/indranilbanerjee/socialforge/agents-md)

Your own site

<a href="https://agentmods.dev/instructions/indranilbanerjee/socialforge/agents-md"><img src="https://agentmods.dev/badge/instructions/indranilbanerjee/socialforge/agents-md.svg" alt="Measured on agentmods" height="20"></a>

Per session 1,181 This file is loaded in full into every session.

When invoked 1,181 The same file — it is already loaded in full.

Security scan A 0 findings. Scan, not verified.

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.

Model	Per session	Once invoked
Fable 5	$0.01181	$0.01181
Opus 5	$0.00590	$0.00590
Sonnet 5	$0.00236	$0.00236
Haiku 4.5	$0.00118	$0.00118

Measured 5d ago against content hash 12994ee63741, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

socialforge AGENTS.md 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 5d 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.

AGENTS.md · 74 lines

How it starts

The opening of the file, as written. The whole thing — 74 lines — stays where its author put it; the contents beside it link to each section on GitHub.

SocialForge — agent context

This file is auto-loaded by OpenAI Codex, Google Antigravity, GitHub Copilot CLI, Cursor (when in the agent context chain), and other Agent Skills runtimes. Equivalent of CLAUDE.md for non-Claude surfaces.

What this plugin is

SocialForge is an open-source agency-grade social media production engine — calendar parsing, asset-first compositing (brand assets are sacred, AI is the creative layer around them), AI image generation (Vertex AI Nano Banana Pro), AI video generation (WaveSpeed Kling v3.0 Pro), multi-platform copy adaptation, human-in-the-loop review galleries, and C2PA content provenance signing for EU AI Act Article 50 compliance. 20 skills · 25 commands · 5 agents · 28 scripts · 10 opt-in HTTP MCP connectors (none auto-connected) · 0 global hooks.

Supported surfaces (v1.25.1): Claude Code (CLI + IDE extensions), Anthropic Cowork, OpenAI Codex (CLI + IDE + App), Cursor 2.5+, GitHub Copilot CLI, Google Antigravity 2.0 (CLI + IDE), Hermes Agent, OpenClaw, Grok (xAI Build CLI, native .grok-plugin/ pair).

Core principle

Brand assets are sacred. AI is the creative layer around them. Product photos, headshots, screenshots — these are the brand's real visual identity. AI generates backgrounds, mood, and context around them. The brand asset stays pixel-faithful in every composition.

Four creative modes

Mode	When	What happens
ANCHOR_COMPOSE	Brand photo is the centerpiece	AI generates scene around the untouched asset
ENHANCE_EXTEND	Brand photo is the base	AI extends/enhances periphery, core stays faithful
STYLE_REFERENCED	No specific asset needed	AI generates using brand's style reference photos as visual DNA
PURE_CREATIVE	Generic/abstract content	AI generates from text prompt + brand colors/mood

How to use it as an agent

Discover skills by description. 20 skills auto-discover via SKILL.md frontmatter.
Skill bodies reference Python scripts at scripts/<name>.py — invoke via Bash. Key: generate_image.py, edit_image.py, index_assets.py, match_assets.py, c2pa_sign.py.
Image/video APIs require credentials. Vertex AI for Nano Banana Pro (image); WaveSpeed for Kling v3.0 Pro (video). Run setup skill once to store credentials in plugin persistent data.
C2PA signing happens automatically before delivery when --c2pa-sign flag is on (recommended for EU campaigns).
Human-in-the-loop review is mandatory before delivery — build-review-gallery + manage-reviews skills surface posts for client approval.

Read the full file on GitHub · 74 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.

5d ago First seen · 74 lines · 1,181 tokens per session scan A 12994ee63741

Subscribe to this mod's changes

socialforge AGENTS.md is an instructions file published in the GitHub repository indranilbanerjee/socialforge (36 stars, last pushed 18d ago), licensed MIT. It adds 1,181 tokens to every session, about $0.0059 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.

Creative and media Marketing and SEO agency-operations ai-image ai-video c2pa claude-code claude-plugin

socialforge AGENTS.md

Getting it into your agent

Wrote this? Show the measurements

What it costs to keep this loaded

Grade A, and why

Nothing flagged

How it starts

SocialForge — agent context

What this plugin is

Core principle

Four creative modes

How to use it as an agent

What this file has done since we first saw it

Other instructions, from other repositories

higgsfield-skills CLAUDE.md

magi-workflow CLAUDE.md

ai-software-architect AGENTS.md

knowledge-base CLAUDE.md

seedance-viral-forge CLAUDE.md

VeoMCP CLAUDE.md