What is brand-outreach?

A brand-outreach workflow for finding sponsorship targets and drafting collaboration emails from a creator's verified analytics.

It helps select suitable brands, research contacts, draft pitches and replies, negotiate rates, and track outreach in a pipeline.

It prevents invented or outdated numbers and keeps messages under human review instead of sending them automatically.

brand-outreach — Skill for Claude Code by aryaminus

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.

Any agent

npx skills add aryaminus/socials-assistant --skill brand-outreach

Clone the repo

git clone --depth 1 https://github.com/aryaminus/socials-assistant

Made for: Claude Code.

Or install socials-assistant, the plugin that ships this one along with the rest of its 6 skills, 1 MCP server.

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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/aryaminus/socials-assistant/brand-outreach/github.svg)](https://agentmods.dev/skills/aryaminus/socials-assistant/brand-outreach)

Your own site

<a href="https://agentmods.dev/skills/aryaminus/socials-assistant/brand-outreach"><img src="https://agentmods.dev/badge/skills/aryaminus/socials-assistant/brand-outreach/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.

Your own site · 80×15

<a href="https://agentmods.dev/skills/aryaminus/socials-assistant/brand-outreach"><img src="https://agentmods.dev/badge/skills/aryaminus/socials-assistant/brand-outreach.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 70 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 717 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.

Model	Per session	Once invoked
Fable 5.1	$0.00070	$0.00717
Opus 5	$0.00035	$0.00358
Sonnet 5	$0.00014	$0.00143
Haiku 4.5	$0.00007	$0.00072

Measured 11d ago against content hash a2658b6fff00, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

brand-outreach 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 11d 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.

skills/brand-outreach/SKILL.md · 44 lines

How it starts

The opening of the file, as written. The whole thing — 44 lines — stays where its author put it; the contents beside it link to each section on GitHub.

brand-outreach — pitch with real numbers

Hard rules

Draft-first. Always produce a draft for human review. Never send, schedule, or promise sending without the user's explicit go-ahead.
Real numbers only — from socials-mcp:media_kit_data, socials-mcp:top_content, socials-mcp:compare_periods. Cite the time window of every number ("last 30 days"). If the vault lacks data, run socials-mcp:snapshot first; don't guess.
Log every draft with socials-mcp:outreach_log_add; update status with socials-mcp:outreach_log_update.

Pipeline

0. Read the creator profile

Call socials-mcp:profile_get first: niche, audience summary, brand_categories, rate_floor, past_collaborations drive targeting and pricing. If empty, build it with the user (audience facts auto-fill from socials-mcp:audience_overview).

1. Target selection (help the user think)

Rank targets by audience–product fit: brands whose customers look like the creator's audience demographics (country/age from socials-mcp:audience_overview + profile brand_categories). Prefer profile.past_collaborations categories — repeat sponsors convert best. Research each brand's marketing contact name before drafting — never "Dear Sir/Madam".

2. Pull verified numbers

Call socials-mcp:media_kit_data. Extract: followers per platform, 30-day views, avg engagement rate, top 3 videos, audience highlights.

3. Draft

Use the template in assets/pitch-template.md — ≤150 words, plain text, one link, numbers with windows, one clear CTA. Rate guidance lives in references/rate-card.md; the user sets final rates.

4. Log it

socials-mcp:outreach_log_add with brand, contact email, subject, and a short pitch-angle note.

5. Follow-ups

Check socials-mcp:outreach_log_list for drafts 5–7 days old with no reply → draft a 2-line bump. Maximum one bump. Mark replied/rejected/closed honestly.

Negotiation quick answers

"What's your rate?" → range with deliverables, anchored mid-high.
Budget pushback → cut scope (fewer deliverables, shorter usage rights), not price below floor.
Always define: usage rights (organic vs paid amplification), exclusivity window, deliverable count, timeline, payment terms (50% upfront for new brands).

Read the full file on GitHub · 44 lines

Files

What ships with it

2 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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.

11d ago First seen · 44 lines · 70 tokens per session scan A a2658b6fff00

Subscribe to this mod's changes

brand-outreach is a skill published in the GitHub repository aryaminus/socials-assistant (0 stars, last pushed yesterday), licensed MIT. It adds 70 tokens to every session and 717 once invoked, about $0.0003 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.

Analytics and metrics Marketing and SEO ai-agent chatgpt claude content-creator creator

brand-outreach