What is tech-team-agents CLAUDE.md?

Repository instructions for Tech Team Agents, a collection of coding-agent personas based on fictional technology characters.

Creating a new agent, choosing its company folder, naming its Markdown file, and understanding the source, customisation, and generated folders.

They explain where agent files and tool-specific customisations belong, reducing mistakes when adding or changing an agent.

How cliffano/tech-team-agents configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to cliffano/tech-team-agents. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file

curl -O https://raw.githubusercontent.com/cliffano/tech-team-agents/main/CLAUDE.md

Clone the repo

git clone --depth 1 https://github.com/cliffano/tech-team-agents

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.

README.md

[![agentmods](https://agentmods.dev/badge/instructions/cliffano/tech-team-agents/claude-md/github.svg)](https://agentmods.dev/instructions/cliffano/tech-team-agents/claude-md)

Your own site

<a href="https://agentmods.dev/instructions/cliffano/tech-team-agents/claude-md"><img src="https://agentmods.dev/badge/instructions/cliffano/tech-team-agents/claude-md/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/instructions/cliffano/tech-team-agents/claude-md"><img src="https://agentmods.dev/badge/instructions/cliffano/tech-team-agents/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 8,226 This file is loaded in full into every session.

When invoked 8,226 The same file — it is already loaded in full.

Security scan C 1 finding. 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	$0.08226	$0.08226
Opus 5.5	$0.03290	$0.03290
Sonnet 5.5	$0.01645	$0.01645
Haiku 4.5	$0.00823	$0.00823

Measured 2mo ago against content hash bea020a5253a, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade C, and why

tech-team-agents CLAUDE.md scanned grade C with 1 finding 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 2mo 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.

Recursive force deletehighDestructive command

rm -rf with a variable or a broad path is one typo away from removing the wrong tree.

make clean # rm -rf dist

CLAUDE.md · 685 lines

How it starts

The opening of the file, as written. The whole thing — 685 lines — stays where its author put it; the contents beside it link to each section on GitHub.

tech-team-agents

A collection of Claude Code agent personalities modelled on tech characters from film and TV. Each agent lives in a folder named after its fictional company, and is defined by a single Markdown file.

Repository structure

Every company is a three-layer stack — see ## Three-layer layout below for the full picture:

characters/<company-folder>/<first-last>.md          # generic, portable — Character Card V3
customisations/<tool>/<company-folder>/               # tool-specific overlay
dist/<tool>/<company-folder>/<first-last>.md           # built, gitignored — what you install

Examples: characters/pied-piper/richard-hendricks.md, characters/fsociety/elliot-alderson.md.

The filename stem becomes the agent's @handle in Claude Code (e.g. @richard-hendricks).

Adding a new agent

This section specifies the character content — voice, mission, rules, relationships. Where that content physically lives has changed since this section was written: the body goes in characters/<company>/<name>.md (CCv3-rendered markdown, see ## Three-layer layout), color/emoji go in customisations/claude/<company>/personas.yaml, and orchestrator/vibe are expressed as a CCv3 tag and first_mes respectively. Everything below is still the correct spec for what to write; only the file it goes in has changed.

1. Choose or create the company folder

Use the fictional company name, kebab-cased (cardiff-electric, pied-piper, fsociety, reynholm-industries). Create the folder if it doesn't exist.

2. Create the agent file

Filename: <first-name>-<last-name>.md (or a recognised single-name handle like mr-robot.md).

3. Follow the required structure exactly

Every agent file must contain all of the sections below, in this order.

Required file structure

Frontmatter (YAML, mandatory fields)

---
name: First Last
description: One sentence — role + defining trait + what they bring to a team. Written as a capability statement, not a bio.
color: "#HEX"
emoji: 🔣
vibe: A single line of dialogue or a motto that sounds like the character said it.
---

Read the full file on GitHub · 685 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.

2mo ago First seen · 685 lines · 8,226 tokens per session scan C bea020a5253a

Subscribe to this mod's changes

tech-team-agents CLAUDE.md is an instructions file published in the GitHub repository cliffano/tech-team-agents (5 stars, last pushed 3mo ago), licensed MIT. It adds 8,226 tokens to every session, about $0.0329 per session on Opus 5.5. A static security scan graded it C with 1 finding (recursive force delete). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

ai-agents

tech-team-agents CLAUDE.md next to 6 instructions from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
tech-team-agents CLAUDE.mdcliffano/tech-team-agents	Instructions file	5	3mo ago	MIT	C	8,226	Claude Code
vscode buildNext.instructions.mdmicrosoft/vscode	Instructions file	195k	today	MIT	A	9,719	GitHub Copilot
next.js AGENTS.mdvercel/next.js	Instructions file	143k	today	MIT	A	7,461	Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscode	Instructions file	195k	today	MIT	A	5,685	GitHub Copilot
langchain AGENTS.mdlangchain-ai/langchain	Instructions file	149k	today	MIT	A	4,680	Codex, OpenCode
vscode copilot-instructions.mdmicrosoft/vscode	Instructions file	195k	today	MIT	A	3,086	GitHub Copilot
deepseek-harness AGENTS.mddeepseek-ai/deepseek-harness	Instructions file	280k	2d ago	MIT	A	4,325	Codex, OpenCode

tech-team-agents: Instructions file for Claude Code