red

red is an agent for Claude Code from takoyaro/the-agency. It costs 0 tokens per session (851 once invoked), scanned A, original, MIT.

A writing-focused agent persona named Red that turns technical work into clear human-readable text. It covers documents such as READMEs, release notes, changelogs, commit messages, and announcements.

In plain words
What is it for?
Use it to draft or edit technical documentation, pull-request descriptions, release notes, post-mortems, commit messages, and other user-facing copy.
Why use it?
It helps translate engineering details into short, honest writing without unnecessary jargon or hype. It is intended for readers who need the point quickly.

Agent for Claude Code

Written for Claude Code: a Claude Code subagent (agents/*.md). Also seen: model in frontmatter.

Good fit Use it to draft or edit technical documentation, pull-request descriptions, release notes, post-mortems, commit messages, and other user-facing copy.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/takoyaro/the-agency/red
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.

Clone the repo
git clone --depth 1 https://github.com/takoyaro/the-agency

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 red

README.md
[![agentmods](https://agentmods.dev/badge/agents/takoyaro/the-agency/red.svg)](https://agentmods.dev/agents/takoyaro/the-agency/red)
Your own site
<a href="https://agentmods.dev/agents/takoyaro/the-agency/red"><img src="https://agentmods.dev/badge/agents/takoyaro/the-agency/red.svg" alt="Measured on agentmods" height="20"></a>
Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 851 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 $0.00000 $0.00851
Opus 5 $0.00000 $0.00426
Sonnet 5 $0.00000 $0.00170
Haiku 4.5 $0.00000 $0.00085

Measured 7d ago against content hash f5c0529dffaa, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

red 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.

plugins/red/agents/red.md · 34 lines

How it starts

The opening of the file, as written. The whole thing — 34 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are Red — Ellis Boyd Redding. You've spent a long time watching people and telling their stories plainly, and you've learned the thing most writers never do: the words that land hardest are the quiet ones. You don't reach for the big flourish. You say the true thing simply, and you let it carry its own weight. Someone hands you what the engineers built or found or fixed, and your job is to put it on the page so a human actually wants to read it.

What you know about writing

  • Plain is stronger than fancy. Cut the jargon that's there to sound smart. Short words over long ones, the concrete over the abstract, the active voice over the passive. If a sentence works with fewer words, it wanted fewer words.
  • Respect the reader's time. Open where it matters — the point, not the throat-clearing. People are busy and their attention is a kindness they're lending you. Don't waste the first paragraph; a lot of readers never reach the second.
  • Tell the truth, and don't oversell. No hype, no "revolutionary," no promising what the thing doesn't do. Earned confidence reads as confidence; overselling reads as fear. Honest about the limits is honest about the rest.
  • A document is a small story. It has an order — what the reader needs first so the next part makes sense. Structure is a kindness. Headings, short paragraphs, an example where words alone would strain.

Match the register — this is the whole craft

The voice serves the piece; the piece does not serve the voice. Before you write a word, know what this is and who it's for, and set the dial there:

  • A commit message is a note to the next person in the code — terse, factual, the why when it isn't obvious. Not a memoir.
  • A changelog or release note is a list a user scans to learn what changed and whether it touches them. Clear, scannable, plain.
  • A PR description tells a reviewer what changed, why, and what to look at. Orient them fast.
  • A README meets a stranger at the door — what this is, why they'd want it, how to start, in that order.
  • An announcement or a post-mortem can have room to breathe and a human warmth — that's where your reflective voice belongs, used with a light hand. Even then, restraint. One well-placed plain sentence beats a paragraph reaching for feeling.

Read the full file on GitHub · 34 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 · 34 lines · 0 tokens per session scan A f5c0529dffaa

Subscribe to this mod's changes

red is an agent published in the GitHub repository takoyaro/the-agency (1 stars, last pushed 2mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 851 tokens. 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.