Borrowing it
Nothing to install: this file belongs to indranilbanerjee/socialforge. 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/indranilbanerjee/socialforge/main/AGENTS.mdgit clone --depth 1 https://github.com/indranilbanerjee/socialforgeWrote 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/indranilbanerjee/socialforge/agents-md)<a href="https://agentmods.dev/instructions/indranilbanerjee/socialforge/agents-md"><img src="https://agentmods.dev/badge/instructions/indranilbanerjee/socialforge/agents-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/indranilbanerjee/socialforge/agents-md"><img src="https://agentmods.dev/badge/instructions/indranilbanerjee/socialforge/agents-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 | $0.01215 | $0.01215 |
| Opus 5.5 | $0.00486 | $0.00486 |
| Sonnet 5.5 | $0.00243 | $0.00243 |
| Haiku 4.5 | $0.00121 | $0.00121 |
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 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.
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 — 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), AI video generation (WaveSpeed image-to-video), multi-platform copy adaptation, human-in-the-loop review galleries, and C2PA content provenance signing for EU AI Act Article 50 compliance. 21 skills · 18 commands · 5 agents · 30 scripts · 12 opt-in HTTP MCP connectors (none auto-connected) · 0 global hooks.
Supported surfaces (v1.29.7): 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. 21 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 images; WaveSpeed for image-to-video (models resolve at run time from the registry aliases). Run the
setupskill once to store credentials in plugin persistent data; API keys come from environment variables, never from the chat. Nothing installs itself: a missing package prints its exact pinned install command. - C2PA signing happens automatically before delivery when
--c2pa-signflag is on (recommended for EU campaigns). - Human-in-the-loop review is mandatory before delivery —
build-review-gallery+manage-reviewsskills surface posts for client approval.
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 Changed 2cbd7057f056
- 11d ago Changed · +39 tokens per session 08f6d0c6a539
- 12d ago Changed 1155d5334f0e
- 16d ago Changed 1dd7eb0ae2d4
- 17d ago Changed · -5 tokens per session 809934f82e1f
- 1mo ago First seen · 74 lines · 1,181 tokens per session scan A 12994ee63741
socialforge AGENTS.md is an instructions file published in the GitHub repository indranilbanerjee/socialforge (42 stars, last pushed 9d ago), licensed MIT. It adds 1,215 tokens to every session, about $0.0049 per session on Opus 5.5. 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.
Other instructions, from other repositories
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).
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.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, cache eligibility and rollout and applying the notice (cutover).
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.
vscode copilot-instructions.md
Copilot instructions for microsoft/vscode, covering vs code copilot instructions, project overview, root folders, core architecture (src/ folder) and built-in extensions (extensions/ folder).
deno copilot-instructions.md
Copilot instructions for denoland/deno, covering deno development guide for github copilot, network access, high level overview, key directories and key files to understand first.