authy CLAUDE.md

Project instructions for Authy, a Rust command-line tool that stores encrypted secrets locally and supplies them to AI agents. They describe the project, its commands, file layout, and important modules.

In plain words
What is it for?
Working on Authy's command-line commands, secret import and export, environment handling, programmatic API, and MCP server.
Why use it?
They give an agent the context needed to navigate Authy and follow its expected build and development practices.

Instructions file

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/claude-md
Clone the repo
git clone --depth 1 https://github.com/eric8810/authy
Per session 752 This file is loaded in full into every session.
When invoked 752 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 $0.00752 $0.00752
Opus 5 $0.00376 $0.00376
Sonnet 5 $0.00150 $0.00150
Haiku 4.5 $0.00075 $0.00075

Measured 2d ago against content hash b8ebc064ce89, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

authy CLAUDE.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.

CLAUDE.md · 59 lines

How it starts

The opening of the file, as written. The whole thing — 59 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CLAUDE.md — Project Instructions

What is this

Authy is a CLI secrets store & dispatch tool for AI agents. Built in Rust. Single binary, no server, no accounts.

Build & Test

cargo build                    # dev build
cargo build --release          # release build
cargo test                     # all tests (unit + integration)
cargo clippy -- -D warnings    # lint (must pass clean)

Project Structure

  • src/cli/ — clap command definitions and handlers (one file per command)
  • src/cli/common.rs — shared secret resolution logic (used by run, env, export)
  • src/cli/json_output.rs — JSON response structs for --json output
  • src/cli/env.rsauthy env command (output secrets as env vars)
  • src/cli/import.rsauthy import command (import from .env files)
  • src/cli/export.rsauthy export command (export as .env or JSON)
  • src/cli/serve.rsauthy serve --mcp command (MCP server entry point)
  • src/lib.rs — library crate root, re-exports core modules
  • src/api.rsAuthyClient high-level programmatic API facade
  • src/mcp/mod.rs — MCP server: JSON-RPC 2.0 handler, McpServer struct
  • src/mcp/tools.rs — MCP tool definitions and dispatch (5 tools)
  • src/vault/ — encrypted vault storage (age encryption, MessagePack serialization)
  • src/auth/ — authentication dispatcher (passphrase / keyfile / session token)
  • src/policy/ — glob-based access control policies
  • src/session/ — HMAC session token generation and validation
  • src/audit/ — append-only JSONL audit log with HMAC chain
  • src/subprocess/ — child process spawning with env var injection
  • tests/api_test.rs — lib-level tests for AuthyClient API (serial, isolated HOME)
  • tests/mcp_test.rs — in-memory MCP server tests (JSON-RPC, serial, isolated HOME)
  • tests/integration/ — CLI integration tests using assert_cmd + tempfile
  • skills/authy/ — Agent Skills standard skill (works with Claude Code, Cursor, OpenClaw, etc.)

Key Conventions

  • All secret-holding types must derive Zeroize and be zeroized on drop
  • Secret values flow through stdin/stdout, never CLI arguments
  • Diagnostics and errors go to stderr, secret values to stdout
  • Session tokens are read-only — no mutation commands accept token auth
  • Policy evaluation: deny overrides allow, default deny
  • Vault writes use atomic rename (write to .tmp, then rename)
  • --json flag produces structured JSON output on stdout, JSON errors on stderr
  • Non-interactive mode: fails fast when no TTY and no credentials provided
  • Typed exit codes: each error category maps to a specific exit code (1-7)

Read the full file on GitHub · 59 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 · 59 lines · 752 tokens per session scan A b8ebc064ce89

Subscribe to this mod's changes

authy CLAUDE.md is an instructions file published in the GitHub repository eric8810/authy (24 stars, last pushed 6mo ago), licensed MIT. It adds 752 tokens to every session, about $0.0038 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.