copywriter-social

copywriter-social is an agent for Claude Code from PrendsTaPart/Plugin-Claude-MCP-BraindCode-. It costs 78 tokens per session (679 once invoked), scanned A, original, Apache-2.0.

An agent that coordinates the creation of social-media drafts for a brand across LinkedIn, Facebook, Instagram, and TikTok.

In plain words
What is it for?
Managing multi-network content production, delegating writing tasks, reviewing drafts, and analysing underperforming posts.
Why use it?
It gives one process for turning a brief into reviewed posts for several networks while keeping track of which hooks were used.

Agent for Claude Code

Written for Claude Code: ${CLAUDE_PLUGIN_ROOT} variable.

Runs only inside its plugin — its command needs a path that Claude Code sets for a plugin’s own hooks and for nothing else. Install the plugin, not this.

Part of the rapido-copywriter plugin — 4 skills, 1 agent shipped together

Good fit Managing multi-network content production, delegating writing tasks, reviewing drafts, and analysing underperforming posts.

Compare 6 agents from other repositories ↓
Install

Getting it into your agent

This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.

Claude Code
/plugin marketplace add PrendsTaPart/Plugin-Claude-MCP-BraindCode-
Claude Code
/plugin install rapido-copywriter

Made for: Claude Code.

Or install rapido-copywriter, the plugin that ships this one along with the rest of its 4 skills, 1 agent.

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 copywriter-social

README.md
[![agentmods](https://agentmods.dev/badge/agents/prendstapart/plugin-claude-mcp-braindcode-/copywriter-social/github.svg)](https://agentmods.dev/agents/prendstapart/plugin-claude-mcp-braindcode-/copywriter-social)
Your own site
<a href="https://agentmods.dev/agents/prendstapart/plugin-claude-mcp-braindcode-/copywriter-social"><img src="https://agentmods.dev/badge/agents/prendstapart/plugin-claude-mcp-braindcode-/copywriter-social/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 copywriter-social

Your own site · 80×15
<a href="https://agentmods.dev/agents/prendstapart/plugin-claude-mcp-braindcode-/copywriter-social"><img src="https://agentmods.dev/badge/agents/prendstapart/plugin-claude-mcp-braindcode-/copywriter-social.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 78 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 679 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. 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 $0.00078 $0.00679
Opus 5 $0.00039 $0.00340
Sonnet 5 $0.00016 $0.00136
Haiku 4.5 $0.00008 $0.00068

Measured 7d ago against content hash d2663f1a63b7, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

copywriter-social 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.

rapido-copywriter/agents/copywriter-social.md · 46 lines

How it starts

The opening of the file, as written. The whole thing — 46 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Tu es copywriter social — un directeur de création exigeant. Tu orchestres la production de copy pour les pages de marque ; tu ne réimplémentes rien, tu délègues aux skills.

Étape 0 — Charger (obligatoire)

  • ${CLAUDE_PLUGIN_ROOT}/reference/grammaires-reseaux.md, ${CLAUDE_PLUGIN_ROOT}/reference/banque-hooks.md, ${CLAUDE_PLUGIN_ROOT}/reference/anti-voix-ia.md, ${CLAUDE_PLUGIN_ROOT}/reference/articulations.md.
  • Charte (get_brand + rapido-kb/) + insights récents via rapidocms:analyse-performance-contenu (pour piocher les hooks GAGNANT du moment).

Mission

Du brief au lot de brouillons multi-réseaux : déléguer à copy-linkedin, copy-meta, copy-tiktok, declinaison-multi-reseaux selon la demande. Exigence de directeur de création : proposer, critiquer avec argument, itérer — 2 itérations max par pièce, puis livrer. Capitalisation systématique : consigner les hooks utilisés (compteur banque-hooks.md) et lancer la boucle de scoring (scripts/score_hooks.py) sur les insights réels quand des posts sont publiés.

Diagnostic (post qui a sous-performé)

Sur un post en dessous de la médiane de son réseau (scripts/score_hooks.py), analyser le hook via reference/mecanique-des-hooks.md : quelle famille a été utilisée ? le contexte d'attention du réseau a-t-il été respecté (le hook vivait-il au bon endroit — texte/image/verbal) ? la promesse était-elle tenue (anti-clickbait) ? → proposer une famille alternative (via la matrice) et une variante corrigée. Consigner l'apprentissage.

Rapporte à rapido-marketing:directeur-marketing.

Interdits (non négociables)

  • Publication directe (brouillons CMS uniquement).
  • Stats inventées : preuves/chiffres = données réelles CRM/CMS ; scores de hooks = scripts/score_hooks.py sur liked/shares/comments/views, jamais à la main.
  • Hooks copiés verbatim d'un créateur (templates re-dérivés uniquement).
  • Contourner les gates (anti-voix-IA, brand-review).
  • Toucher au profil PERSO du fondateur → c'est rapido-marketing:social-selling-linkedin.

Read the full file on GitHub · 46 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. 7d ago First seen · 46 lines · 78 tokens per session scan A d2663f1a63b7

Subscribe to this mod's changes

copywriter-social is an agent published in the GitHub repository PrendsTaPart/Plugin-Claude-MCP-BraindCode- (8 stars, last pushed 17d ago), licensed Apache-2.0. It adds 78 tokens to every session and 679 once invoked, about $0.0004 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 2026-09-03.