init

A project setup command for TandemKit, a tool that coordinates development roles and tools in a project. It creates the coordination folder, configures roles, installs tools, and checks Codex access.

In plain words
What is it for?
Use it once when adding TandemKit to a project, with approval before installing tools or changing existing configuration.
Why use it?
It gives a project the files and configuration needed to use TandemKit consistently.

Command

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/flinedev/tandemkit/init
Clone the repo
git clone --depth 1 https://github.com/FlineDev/TandemKit
Per session 27 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 7,336 The whole file, excluding the scripts and references it only reads on demand.
Security scan D 3 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 $0.00027 $0.07336
Opus 5 $0.00014 $0.03668
Sonnet 5 $0.00005 $0.01467
Haiku 4.5 $0.00003 $0.00734

Measured yesterday against content hash c6623ff7e919, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade D, and why

init scanned grade D with 3 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 yesterday.

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.

Downloads and executes remote codehighSupply chain

curl | sh runs whatever the server returns today, which is not necessarily what it returned when this was reviewed.

curl -fsSL https://browser-use.com/cli/install.sh | bash

Reads agent configuration directoriesmediumAgent snooping

.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.

- Read `~/.claude/settings.json` for global permissions and MCP tool allowances

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

curl -fsSL https://browser-use.com/cli/install.sh | bash
commands/init.md · 500 lines

How it starts

The opening of the file, as written. The whole thing — 500 lines — stays where its author put it; the contents beside it link to each section on GitHub.

TandemKit — Project Initialization

Note: This command is for plugin-based distribution only. For local development, use direct symlinks to the TandemKit repo instead — see README.md for setup instructions.

This command sets up TandemKit in the current project. Run it once per project.

Important UX Rules

Follow these rules throughout the entire init flow:

  1. Do NOT explain what TandemKit is. The user already knows — they just ran the init command.
  2. Ask questions ONE AT A TIME. Before each question, write 2-3 sentences of context in chat explaining WHY this matters and what you recommend. Then ask using AskUserQuestion. Never batch multiple questions.
  3. Do NOT install or configure anything without explicit user approval. Ask first, show what you want to do, get a "yes", then do it.
  4. Before modifying any existing file (.gitignore, settings.json, config.toml), explain what you want to change and get user approval.
  5. When recommending external tools, always provide: verified GitHub URL, star count, brief description of what it does, and at least one alternative. Never present a single option as the only choice.
  6. For npm packages, use npx -y (run without global install), never npm install -g. Check the user's permission deny list in settings.json — never recommend commands that appear there.
  7. MCP server configurations go in .mcp.json at the project root, NOT in .claude/settings.json. MCP tool permissions (allow rules) go in settings.json.
  8. Start brief. Jump straight to investigation. No preamble, no tutorial.
  9. Before writing any files, show a recap of all the settings you're about to encode and get user confirmation. This catches misunderstandings before they're baked into config files.

Pre-Flight Check

  1. Verify TandemKit/ does not already exist in the project root. If it does, tell the user: "TandemKit is already initialized in this project. Config is at TandemKit/Config.json."
  2. Check that this is a git repository. If not, warn: "This project is not a git repository. TandemKit works best with git for feature branches and milestone commits. Continue anyway?"

Read the full file on GitHub · 500 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. yesterday First seen · 500 lines · 27 tokens per session scan D c6623ff7e919

Subscribe to this mod's changes

init is a command published in the GitHub repository FlineDev/TandemKit (39 stars, last pushed 4mo ago), licensed MIT. It adds 27 tokens to every session and 7,336 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it D with 3 findings (downloads and executes remote code, reads agent configuration directories, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.