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 instructions/eric8810/authy/agents-mdgit clone --depth 1 https://github.com/eric8810/authyWhat 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 | $0.01764 | $0.01764 |
| Opus 5 | $0.00882 | $0.00882 |
| Sonnet 5 | $0.00353 | $0.00353 |
| Haiku 4.5 | $0.00176 | $0.00176 |
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.
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
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.
- 2d ago First seen · 184 lines · 1,764 tokens per session scan A 8cd9282c61c3
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.
Other instructions, from other repositories
deer-flow copilot-instructions.md
Copilot instructions for bytedance/deer-flow, covering copilot onboarding instructions for deerflow, 1) repository summary, 2) runtime and toolchain requirements, 3) build/test/lint/run - verified command sequences and a. bootstrap and install.
zeroclaw CLAUDE.md
Claude Code instructions for zeroclaw-labs/zeroclaw, covering claude.md — zeroclaw (claude code), claude code settings, hooks and slash commands.
cursor-talk-to-figma-mcp AGENTS.md
AGENTS.md instructions for grab/cursor-talk-to-figma-mcp, covering agents.md, project overview, build & development commands, architecture and mcp server (src/talktofigmamcp/server.ts).
nuwax AGENTS.md
Instructions for nuwax-ai/nuwax, covering ai agent system documentation, 系统概述, ai agent 架构, 核心组件 and ai 功能特性.
AgentEval maf-upgrade-preparation.instructions.md
Instructions for analyzing a new MAF version and producing an upgrade plan BEFORE updating the NuGet package.
AgentEval copilot-instructions.md
Instructions for AgentEvalHQ/AgentEval, covering agenteval - ai coding agent instructions, architecture overview, environment setup, optional: secondary models for comparison and build & test commands.