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/nighthawk42/bnet_auth_tool/agents-mdgit clone --depth 1 https://github.com/Nighthawk42/bnet_auth_toolWhat 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 | $0.00843 | $0.00843 |
| Opus 5 | $0.00421 | $0.00421 |
| Sonnet 5 | $0.00169 | $0.00169 |
| Haiku 4.5 | $0.00084 | $0.00084 |
Grade A, and why
bnet_auth_tool 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 — 64 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md
Guidance for AI agents and human contributors working on bnet_auth_tool.
What this is
A Python CLI for managing Battle.net software authenticators. Two halves:
- Offline (the important, fully-tested half): an encrypted vault of authenticator secrets, TOTP/QR reconstruction, and migration of legacy backups.
- Online (unverified): attach/retrieve flows against Blizzard's identity API. These
may be blocked by Blizzard at any time. Do not claim they are "fixed" — keep the
tempered "unverified" framing in the README and
--help/menu text.
Architecture
Source lives under src/bnet_auth_tool/ (a proper package; there is no top-level script).
| Module | Responsibility |
|---|---|
config.py |
Load bundled settings.yaml + user override; resolve config/data dirs (platformdirs). Typed Settings/ApiConfig/CryptoConfig/TotpConfig. |
crypto.py |
EncryptionManager: scrypt+AES‑256‑GCM encrypt; decrypt dispatches on a versioned header (scrypt / PBKDF2 600k / legacy PBKDF2 100k). |
storage.py |
Vault: single encrypted file keyed by serial; add/list/get/remove. |
fileio.py |
Atomic, 0600-hardened writes (atomic_write_bytes, _harden). |
api.py |
BattleNetAuthenticator online client; leak-safe error handling. |
totp.py |
hex→base32, otpauth:// URL builder, QR PNG. |
migrate.py |
Discover + import legacy battlenet_authenticator_*.json files into the vault. |
cli.py |
Interactive menu and argparse subcommands; main() is the entry point. |
gui.py |
Optional Flet desktop GUI (bnet-auth-gui); imperative, same vault/crypto as the CLI. Behind the gui extra. |
errors.py |
Exception hierarchy rooted at BnetAuthError. |
settings.yaml is shipped inside the package and copied to the user's config dir on first
run. Endpoints/KDF/TOTP params are config, not code — change them there.
Hard constraints (do not break)
- Legacy decryption must keep working. Files encrypted by v1.x — including pre‑v1.3
files with no
kdf_iterationsfield — must still decrypt. Covered bytests/test_crypto.py. - Secrets are sensitive. Never log raw device secrets, restore codes, session tokens,
or full server error bodies. Vault/QR files are written
0600and atomically. - Online flows stay labelled unverified. No optimistic "it works now" claims.
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 · 64 lines · 843 tokens per session scan A b6393df0c120
bnet_auth_tool AGENTS.md is an instructions file published in the GitHub repository Nighthawk42/bnet_auth_tool (45 stars, last pushed 2mo ago), licensed MIT. It adds 843 tokens to every session, about $0.0042 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
spec-kit AGENTS.md
AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.
codex AGENTS.md
AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.
vscode buildNext.instructions.md
Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).
langchain AGENTS.md
AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).
next.js AGENTS.md
Instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.