pitch

A command for writing targeted pitches to journalists, podcast hosts, newsletter writers, or online creators.

In plain words
What is it for?
Use it to pitch company news, product launches, guest appearances, articles, or creator collaborations, with subject lines, supporting materials, and follow-up steps.
Why use it?
It helps turn a story or opportunity into a concise message that explains why the recipient should care, without sending the same generic note to everyone.

Command

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 commands/brainbytes-dev/everything-claude-marketing/pitch
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.

Per session 19 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,696 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 $0.00019 $0.01696
Opus 5 $0.00010 $0.00848
Sonnet 5 $0.00004 $0.00339
Haiku 4.5 $0.00002 $0.00170

Measured 2d ago against content hash e8ef0af34d5e, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

pitch 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 2d 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.

commands/pitch.md · 170 lines

How it starts

The opening of the file, as written. The whole thing — 170 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/pitch

Craft a compelling media or influencer pitch with a sharp angle, personalized outreach, and a follow-up plan that gets responses.

What This Command Does

This command creates a targeted pitch designed to earn media coverage or influencer collaboration. It starts by identifying the right angle — the reason a journalist or creator would care about your story — then builds a concise, personalized outreach message that respects the recipient's time and interests. The output includes the pitch email itself, subject line options, supporting materials to include or have ready, a follow-up sequence, and guidance on timing and targeting. The command adapts its approach based on whether you are pitching traditional media, trade publications, newsletters, podcasts, or social media creators.

When to Use

  • Pitching a journalist about a product launch, funding round, or company news
  • Reaching out to a podcast host for a guest appearance
  • Contacting a newsletter writer about featuring your product or perspective
  • Proposing a contributed article or opinion piece to a publication
  • Pitching an influencer or creator for a sponsored collaboration
  • Responding to a journalist's request for sources (HARO, Qwoted, etc.)
  • Building a media list and outreach plan for a PR campaign

How It Works

  1. Identifies the target — Determines whether this is a media pitch, influencer pitch, or podcast pitch and adjusts format accordingly
  2. Finds the angle — Isolates what makes your story newsworthy, timely, or relevant to the specific outlet's audience
  3. Researches the recipient — Considers the journalist's beat, recent coverage, or the creator's content style and audience
  4. Writes the pitch — Crafts a concise, skimmable email that leads with the hook and makes the ask clear
  5. Prepares supporting assets — Lists what to attach or have ready (data, images, demo access, press kit)
  6. Plans the follow-up — Builds a follow-up sequence with timing and messaging for each touch
  7. Suggests alternatives — If the primary target is a long shot, recommends backup outlets or angles

Read the full file on GitHub · 170 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. 2d ago First seen · 170 lines · 19 tokens per session scan A e8ef0af34d5e

Subscribe to this mod's changes

pitch is a command published in the GitHub repository brainbytes-dev/everything-claude-marketing (5 stars, last pushed 5mo ago), licensed MIT. It adds 19 tokens to every session and 1,696 once invoked, about $0.0001 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.