init

A setup command for connecting AgentSecrets to the current computer and project. It can create or access an account, configure encryption, choose keychain or `.env` storage, and write local project settings.

In plain words
What is it for?
Setting up AgentSecrets in a project directory, choosing how secrets are stored, creating an account, or linking an existing account and project.
Why use it?
It provides the initial link between a project and AgentSecrets, including the keys and configuration needed to use stored secrets. It also creates guidance for the coding agent.

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/the-17/agentsecrets/init
Clone the repo
git clone --depth 1 https://github.com/The-17/agentsecrets
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 1,001 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 $0.00000 $0.01001
Opus 5 $0.00000 $0.00500
Sonnet 5 $0.00000 $0.00200
Haiku 4.5 $0.00000 $0.00100

Measured yesterday against content hash 4a4f9c9a7953, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

init 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 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.

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.

docs/commands/init.md · 123 lines

How it starts

The opening of the file, as written. The whole thing — 123 lines — stays where its author put it; the contents beside it link to each section on GitHub.

agentsecrets init

Initialize AgentSecrets in the current project directory.

Usage

agentsecrets init [--storage-mode 0|1]

Description

init is the entry point. Run it once per machine (to create your account) and once per project directory (to link it to a remote project).

It does four things:

  1. Authenticates you — create a new account or log in
  2. Sets up encryption — generates your local keypair, downloads your workspace key
  3. Chooses a storage mode — keychain or .env file
  4. Writes local config.agentsecrets/project.json and .agent/workflows/agentsecrets.md

What Happens Step by Step

If you don't have an account (signup)

  1. Prompts for email + password
  2. Generates an X25519 keypair client-side
  3. Derives a key from your password with Argon2id
  4. Encrypts your private key with the password-derived key
  5. Sends public key + encrypted private key to the API
  6. API creates your account, generates a workspace key, encrypts it with your public key, returns the encrypted copy
  7. CLI decrypts the workspace key with your private key, caches it in ~/.agentsecrets/config.json

Your private key never leaves your machine in plaintext.

If you already have an account (login)

  1. Prompts for email + password
  2. Downloads your encrypted private key from the server
  3. Derives the key from your password with Argon2id, decrypts the private key
  4. Downloads your encrypted workspace keys, decrypts them with your private key
  5. Caches workspace keys in ~/.agentsecrets/config.json

Storage Mode

agentsecrets init --storage-mode 1   # Keychain (recommended)
agentsecrets init --storage-mode 0   # Standard .env
Mode Secrets Go To .env File Behavior
1 — Keychain (default) OS keychain (macOS Keychain / Windows Credential Manager / Secret Service) .env.example created with key names only
2 — Standard Plaintext .env file .env created and updated with values

Read the full file on GitHub · 123 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 · 123 lines · 0 tokens per session scan A 4a4f9c9a7953

Subscribe to this mod's changes

init is a command published in the GitHub repository The-17/agentsecrets (172 stars, last pushed 3d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,001 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 2026-08-30.