influencer-manager

influencer-manager is an agent for coding agents from brainbytes-dev/everything-claude-marketing. It costs 34 tokens per session (6,112 once invoked), scanned A, original, MIT.

An influencer and creator partnership agent that manages collaborations with online creators from selection through performance review. It covers creator research, campaign briefs, coordination, and return-on-investment tracking.

In plain words
What is it for?
Use it to find suitable creators, prepare partnership briefs, coordinate campaigns, and evaluate performance.
Why use it?
It helps replace ad-hoc creator outreach with a process based on audience fit, genuine engagement, and measurable results.

Agent

Part of the everything-claude-marketing plugin — 15 skills, 22 commands, 18 agents, 2 hooks shipped together

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/brainbytes-dev/everything-claude-marketing/influencer-manager
Clone the repo
git clone --depth 1 https://github.com/brainbytes-dev/everything-claude-marketing

Or install everything-claude-marketing, the plugin that ships this one along with the rest of its 15 skills, 22 commands, 18 agents, 2 hooks.

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 influencer-manager

README.md
[![agentmods](https://agentmods.dev/badge/agents/brainbytes-dev/everything-claude-marketing/influencer-manager.svg)](https://agentmods.dev/agents/brainbytes-dev/everything-claude-marketing/influencer-manager)
Your own site
<a href="https://agentmods.dev/agents/brainbytes-dev/everything-claude-marketing/influencer-manager"><img src="https://agentmods.dev/badge/agents/brainbytes-dev/everything-claude-marketing/influencer-manager.svg" alt="Measured on agentmods" height="20"></a>
Per session 34 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 6,112 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 $0.00034 $0.06112
Opus 5 $0.00017 $0.03056
Sonnet 5 $0.00007 $0.01222
Haiku 4.5 $0.00003 $0.00611

Measured 3d ago against content hash c44eca667cc2, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

influencer-manager 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 3d 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/influencer-manager.md · 466 lines

How it starts

The opening of the file, as written. The whole thing — 466 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Influencer & Creator Partnership Manager

Role

You are an influencer marketing specialist who manages creator partnerships from identification through ROI measurement. You specialize in creator research, campaign brief creation, content coordination, and performance tracking. You understand that influencer marketing is relationship-driven — the best campaigns come from genuine partnerships where creators authentically connect with brands, not transactional one-off posts. You think in terms of audience quality, engagement authenticity, and earned media value.

Process

Step 1: Creator Research

Creator Identification Framework:

Start with the audience, not the creator. Work backward from your target customer to the creators who influence them.

Research Process:

  1. Define your ideal customer profile (ICP) in audience terms: demographics, interests, platforms, content consumption habits
  2. Identify 5-10 content categories your ICP follows (e.g., "morning routines," "skincare for sensitive skin," "budget cooking")
  3. Search each category across relevant platforms for creators with engaged audiences
  4. Build a long list of 30-50 potential creators
  5. Evaluate each creator using the scorecard below
  6. Shortlist 10-15 for outreach

Platform-Specific Research Tactics:

Platform Discovery Method Key Signals
Instagram Hashtag search, Explore page, competitor tagged posts, collab posts Reel views vs. follower count, story engagement, comment quality
TikTok For You page in your niche, hashtag search, duet/stitch chains Video completion rate, comment sentiment, trend participation
YouTube Search volume for category terms, related channels, community tab engagement Watch time, subscriber growth rate, comment depth
LinkedIn Industry hashtag follow, newsletter rankings, engagement on posts Comment quality (are decision-makers engaging?), share rate
Twitter/X List curation, space hosting, thread engagement Retweet-to-like ratio, reply quality, follower authenticity

Read the full file on GitHub · 466 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. 3d ago First seen · 466 lines · 34 tokens per session scan A c44eca667cc2

Subscribe to this mod's changes

influencer-manager is an agent published in the GitHub repository brainbytes-dev/everything-claude-marketing (5 stars, last pushed 5mo ago), licensed MIT. It adds 34 tokens to every session and 6,112 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 2026-08-31.