authy AGENTS.md

Project instructions for Authy, a Rust command-line tool that stores encrypted secrets locally and supplies them to AI agents under access rules. It includes the project's build, test, structure, and coding guidance.

In plain words
What is it for?
Building, testing, linting, and modifying Authy's command-line features, secret handling, agent dispatch, and project files.
Why use it?
It helps contributors understand how the project works and how to make changes that fit its existing organization and safety model.

Instructions file for CodexOpenCode

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 instructions/eric8810/authy/agents-md
Clone the repo
git clone --depth 1 https://github.com/eric8810/authy

Made for: Codex, OpenCode.

Per session 1,764 This file is loaded in full into every session.
When invoked 1,764 The same file — it is already loaded in full.
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 $0.01764 $0.01764
Opus 5 $0.00882 $0.00882
Sonnet 5 $0.00353 $0.00353
Haiku 4.5 $0.00176 $0.00176

Measured 2d ago against content hash 8cd9282c61c3, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

authy AGENTS.md 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 2d 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.

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.

AGENTS.md · 184 lines

How it starts

The opening of the file, as written. The whole thing — 184 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AGENTS.md — AI Agent Project Guide

Project Overview

Authy is a CLI secrets store & dispatch tool for AI agents. Built in Rust. Single binary, no server, no accounts. It stores encrypted secrets locally and dispatches them to agents with policy-based scoping, short-lived session tokens, and audit logging.

Tech Stack: Rust 2021 edition, clap (CLI), age (encryption), MessagePack (serialization), HMAC-SHA256 (session tokens).

Build & Test Commands

cargo build                    # dev build
cargo build --release          # release build (binary at target/release/authy)
cargo test                     # run all tests (unit + integration)
cargo test --test integration  # run integration tests only
cargo test <test_name>         # run a single test
cargo clippy -- -D warnings    # lint (must pass clean)

Project Structure

src/
  main.rs               Entry point — parse CLI args, dispatch to handlers
  error.rs              AuthyError enum (thiserror), Result type alias
  types.rs              Common re-exports (serde, chrono, BTreeMap, PathBuf)

  cli/                  clap command definitions (one file per command)
    mod.rs              CLI struct with Subcommand enum
    init.rs             authy init — create vault, generate keyfile or passphrase
    store.rs            authy store — decrypt vault, insert secret, re-encrypt
    get.rs              authy get — decrypt vault, policy check, output to stdout
    list.rs             authy list — list secret names with optional scope filter
    remove.rs           authy remove — delete secret from vault
    rotate.rs           authy rotate — update secret value, bump version
    policy.rs           authy policy * — CRUD for scope policies
    session.rs          authy session * — create/list/revoke tokens
    run.rs              authy run — subprocess injection with scoped secrets
    audit.rs            authy audit * — show/verify/export audit log
    config.rs           authy config — show configuration

  vault/                Encrypted vault storage
    mod.rs              Vault struct, VaultKey enum, load_vault(), save_vault()
    crypto.rs           age encrypt/decrypt (passphrase + keyfile), HKDF derivation
    secret.rs           SecretEntry, SecretMetadata (with Zeroize)

  auth/                 Authentication dispatcher
    mod.rs              resolve_auth() — resolve credentials to VaultKey + AuthContext
    context.rs          AuthContext — carries resolved identity and permission level

  policy/               Access control
    mod.rs              Policy struct, can_read() with globset matching

  session/              Session token management
    mod.rs              SessionRecord, generate_token(), validate_token()

  audit/                Audit logging
    mod.rs              AuditEntry, append_entry(), verify_chain()

  subprocess/           Child process spawning
    mod.rs              Spawn child process with env var injection

  config/               Configuration parsing
    mod.rs              authy.toml parsing

tests/integration/      Integration tests using assert_cmd + tempfile

Read the full file on GitHub · 184 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. 2d ago First seen · 184 lines · 1,764 tokens per session scan A 8cd9282c61c3

Subscribe to this mod's changes

authy AGENTS.md is an instructions file published in the GitHub repository eric8810/authy (24 stars, last pushed 6mo ago), licensed MIT. It adds 1,764 tokens to every session, about $0.0088 per session on Opus 5. 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.