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.
npx agentmods add instructions/cliffano/tech-team-agents/claude-mdgit clone --depth 1 https://github.com/cliffano/tech-team-agentsWrote 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.
[](https://agentmods.dev/instructions/cliffano/tech-team-agents/claude-md)<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="Measured on agentmods" height="20"></a>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 | $0.08226 | $0.08226 |
| Opus 5 | $0.04113 | $0.04113 |
| Sonnet 5 | $0.01645 | $0.01645 |
| Haiku 4.5 | $0.00823 | $0.00823 |
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 5d 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 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.
---
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.
- 5d ago First seen · 685 lines · 8,226 tokens per session scan C bea020a5253a
tech-team-agents CLAUDE.md is an instructions file published in the GitHub repository cliffano/tech-team-agents (5 stars, last pushed 1mo ago), licensed MIT. It adds 8,226 tokens to every session, about $0.0411 per session on Opus 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.
Other instructions, from other repositories
next.js AGENTS.md
AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.
codex AGENTS.md
AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.
vscode buildNext.instructions.md
Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).
spec-kit AGENTS.md
AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.
langchain AGENTS.md
AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).