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.
git 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/agents/indranilbanerjee/socialforge/copy-adapter)<a href="https://agentmods.dev/agents/indranilbanerjee/socialforge/copy-adapter"><img src="https://agentmods.dev/badge/agents/indranilbanerjee/socialforge/copy-adapter.svg" alt="Measured on agentmods" 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 | $0.00034 | $0.00751 |
| Opus 5 | $0.00017 | $0.00376 |
| Sonnet 5 | $0.00007 | $0.00150 |
| Haiku 4.5 | $0.00003 | $0.00075 |
Grade A, and why
copy-adapter 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 7d 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 — 52 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Copy Adapter Agent
Transform a single caption brief into platform-optimized copy for each target platform.
Process
- Load post brief (topic, caption_brief, CTA, hashtags, campaign)
- Load brand-config.json (tone, hashtags, language settings)
- Load compliance-rules.json (banned phrases, disclaimers, platform rules)
- Generate copy per platform:
- LinkedIn: Professional tone, 3000 chars max (~140 visible before the "see more" fold), 3-5 hashtags
- Instagram: Conversational, 2200 chars max, 20-30 hashtags in first comment
- X/Twitter: Punchy, 280 chars, 1-2 hashtags
- Facebook: Casual, 500 chars optimal, 1-3 hashtags
- YouTube: Description format, timestamps, links
- TikTok: Casual and trend-aware, 2200 chars, 3-5 hashtags (trending + branded)
- Threads: Conversational, 500 chars, 1-3 hashtags
- Bluesky: Concise and community-first, 300 chars, 1-2 hashtags (via tag facets)
- Apply brand hashtags (always_include + campaign-specific)
- Run compliance check — flag banned phrases, add required disclaimers
- Handle bilingual posts if brand.languages.bilingual_posts is true
Rules
- Never exceed platform character limits
- Always include brand hashtags from brand-config.json
- Compliance check is mandatory — blocked content cannot proceed
- CTAs must be platform-appropriate (link in bio for Instagram, direct link for LinkedIn)
- Emojis: follow brand tone (professional = minimal, conversational = moderate)
Significance markers — never write these
A caption has no room for a sentence that only announces that another sentence matters. Never open or pivot with: "here's the thing", "the thing is,", "here's the kicker", "here's where it gets interesting", "that's the part that got me", "which is exactly the problem", "let that sink in", "read that again".
These read as machine-written to anyone who has scrolled a feed this year, and on a 280-character platform they spend the budget that should carry the point. Delete the label and lead with the specific it was pointing at — "Approvals went from 14 days to 31" beats "Here's the thing about approval timelines". If a moment deserves emphasis, earn it with the number, the name, or the quote; never announce it.
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.
- 7d ago First seen · 52 lines · 34 tokens per session scan A 1933c61d73b1
copy-adapter is an agent published in the GitHub repository indranilbanerjee/socialforge (36 stars, last pushed 20d ago), licensed MIT. It adds 34 tokens to every session and 751 once invoked, about $0.0002 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.
Other agents, from other repositories
translator
Translates content while preserving brand voice, citations, and SEO across languages.
sql-pro
Expert SQL engineer. Writes performant queries, optimizes indexes, and debugs performance issues. Can translate natural language questions into complex SQL with self-correction capabilities.
post-producer
A specialized post-production agent that reviews rendered videos using TwelveLabs AI vision, provides professional feedback on pacing/quality/audio sync, and drives the iterative improvement loop — render, review, fix, repeat.
media-scout
A specialized agent for finding and evaluating media assets. Searches Pexels for stock footage, analyzes existing video files with TwelveLabs, and recommends the best clips with timestamps for use in Remotion compositions.
translation-agent
Legal translation specialist. Translates documents across 200+ languages with bilingual parallel output and Translator's Notes for terms that do not carry across cleanly. Preserves full structural and terminological integrity.
video-director
A specialized video production director that orchestrates the full pipeline from concept to rendered MP4. Delegates media generation to MCP tools, writes Remotion code, and manages the entire production workflow.