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 commands/the-17/agentsecrets/initgit clone --depth 1 https://github.com/The-17/agentsecretsWhat 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 | $0.00000 | $0.01001 |
| Opus 5 | $0.00000 | $0.00500 |
| Sonnet 5 | $0.00000 | $0.00200 |
| Haiku 4.5 | $0.00000 | $0.00100 |
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.
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:
- Authenticates you — create a new account or log in
- Sets up encryption — generates your local keypair, downloads your workspace key
- Chooses a storage mode — keychain or
.envfile - Writes local config —
.agentsecrets/project.jsonand.agent/workflows/agentsecrets.md
What Happens Step by Step
If you don't have an account (signup)
- Prompts for email + password
- Generates an X25519 keypair client-side
- Derives a key from your password with Argon2id
- Encrypts your private key with the password-derived key
- Sends public key + encrypted private key to the API
- API creates your account, generates a workspace key, encrypts it with your public key, returns the encrypted copy
- 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)
- Prompts for email + password
- Downloads your encrypted private key from the server
- Derives the key from your password with Argon2id, decrypts the private key
- Downloads your encrypted workspace keys, decrypts them with your private key
- 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 |
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.
- yesterday First seen · 123 lines · 0 tokens per session scan A 4a4f9c9a7953
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.
Other commands, from other repositories
nyxid-connect
Connect a catalog service through NyxID without placing its credential in the agent context.
checklist
Generate a custom checklist for the current feature based on user requirements.
clarify
Identify underspecified areas in the current feature spec by asking up to 5 highly targeted clarification questions and encoding answers back into the spec.
specify
Create or update the feature specification from a natural language feature description.
analyze
Perform a non-destructive cross-artifact consistency and quality analysis across spec.md, plan.md, and tasks.md after task generation.
converge
Assess the current codebase against the feature's spec, plan, and tasks, then append any remaining unbuilt work as new tasks to tasks.md so implement can complete it.