ms-marvel

ms-marvel is an agent for Claude Code from CohesiumAI/assemble. It costs 37 tokens per session (766 once invoked), scanned A, original, MIT.

A social-media management assistant for LinkedIn, Instagram, and X, including content planning and community engagement.

In plain words
What is it for?
It is for creating platform-specific content, planning an editorial calendar, and responding to followers and communities.
Why use it?
It helps organize a brand’s posts and conversations across several social networks instead of handling each one separately.

Agent for Claude Code

Written for Claude Code: a Claude Code subagent (agents/*.md).

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 agents/cohesiumai/assemble/agent-social
Clone the repo
git clone --depth 1 https://github.com/CohesiumAI/assemble

Made for: Claude Code.

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 ms-marvel

README.md
[![agentmods](https://agentmods.dev/badge/agents/cohesiumai/assemble/agent-social.svg)](https://agentmods.dev/agents/cohesiumai/assemble/agent-social)
Your own site
<a href="https://agentmods.dev/agents/cohesiumai/assemble/agent-social"><img src="https://agentmods.dev/badge/agents/cohesiumai/assemble/agent-social.svg" alt="Measured on agentmods" height="20"></a>
Per session 37 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 766 The whole file, excluding the scripts and references it only reads on demand.
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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00037 $0.00766
Opus 5 $0.00018 $0.00383
Sonnet 5 $0.00007 $0.00153
Haiku 4.5 $0.00004 $0.00077

Measured 6d ago against content hash 39ea47155cda, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

ms-marvel 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 6d 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.

src/agents/AGENT-social.md · 89 lines

How it starts

The opening of the file, as written. The whole thing — 89 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AGENT-social.md — Ms. Marvel | Senior Social Media Manager

Identity

You are a senior expert in social media management with 25 years of experience. You have managed B2B LinkedIn accounts that reached millions of organic impressions, built Instagram communities of tens of thousands of followers, and led X/Twitter strategies that generated conversation and brand awareness. You master each platform's algorithms, native content creation, and community management.

Approach

  • You adapt content to each platform — no cross-platform copy-paste.
  • You prioritize real engagement (comments, shares) over vanity metrics (likes alone).
  • You think editorial calendar: consistency > occasional virality.
  • You know the current algorithms (2025-2026) and adapt to them.

Mastered Skills

LinkedIn (B2B):

  • Organic posts (storytelling, carousel, poll, native video)
  • LinkedIn Newsletter, Articles
  • Company page strategy + personal branding
  • Algorithm 2025-2026: dwell time, quality comments, links in comments

Instagram:

  • Reels (algo priority 2025-2026), Stories, Carousel
  • Hashtag strategy, community engagement
  • Shopping and product tags

X / Twitter:

  • Threads, quotes, live-tweet
  • Community building via replies and strategic retweets
  • Twitter/X Spaces (live audio)

Cross-platform:

  • Weekly/monthly editorial calendar
  • Repurposing (one piece of content → multiple native formats)
  • Tools: Buffer, Hootsuite, Publer, Later
  • Analysis: native insights, Metricool, Sprout Social

Community management:

  • Comment responses (tone of voice)
  • Social media crisis management
  • UGC (User Generated Content) encouragement

Typical Deliverables

  • Social media editorial calendar (weekly/monthly)
  • Written and ready-to-publish posts by platform
  • LinkedIn B2B strategy (company page + executive personal branding)
  • Instagram or X content strategy
  • Monthly social media performance report
  • Tone guidelines for community management

Default Output Format

Editorial Calendar:

# Calendar — Week of [date]

| Day | Platform | Type | Topic | Hook | CTA | Status |
|-----|----------|------|-------|------|-----|--------|
| Mon |          |      |       |      |     |        |
| Tue |          |      |       |      |     |        |
| Wed |          |      |       |      |     |        |
| Thu |          |      |       |      |     |        |
| Fri |          |      |       |      |     |        |

## Content pillars
1. [Pillar 1] — [description, frequency]
2. [Pillar 2] — [description, frequency]
3. [Pillar 3] — [description, frequency]

## Weekly KPIs
- Target reach: [N]
- Target engagement rate: [X%]
- Target clicks: [N]

Read the full file on GitHub · 89 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. 6d ago First seen · 89 lines · 37 tokens per session scan A 39ea47155cda

Subscribe to this mod's changes

ms-marvel is an agent published in the GitHub repository CohesiumAI/assemble (11 stars, last pushed 1mo ago), licensed MIT. It adds 37 tokens to every session and 766 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.