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/ex-nihilo-labs/agent-auth/agents-mdgit clone --depth 1 https://github.com/ex-nihilo-labs/agent-authWhat 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 | $0.00784 | $0.00784 |
| Opus 5 | $0.00392 | $0.00392 |
| Sonnet 5 | $0.00157 | $0.00157 |
| Haiku 4.5 | $0.00078 | $0.00078 |
Grade A, and why
agent-auth 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 — 65 lines — stays where its author put it; the contents beside it link to each section on GitHub.
agent-auth
Zero-knowledge credential service for AI agents. MCP server that injects credentials into browsers and HTTP requests without the agent ever seeing them.
Architecture
agent-auth/
├── src/
│ ├── index.ts # Entry point — CLI dispatcher + MCP serve
│ ├── mcp/ # MCP stdio server, 3 tools
│ ├── browser/ # CDP injection via Playwright (fill/type/click/wait/select)
│ ├── placeholder/ # {{email}}, {{username}}, {{password}}, {{totp}} resolution
│ ├── vault/ # AES-256-GCM encrypted SQLite vault + Argon2id KDF
│ ├── totp/ # TOTP code generation via otpauth
│ ├── proxy/ # HTTP credential injection (6 methods)
│ ├── approval/ # Human approval gate + Pushover notifications
│ ├── security/ # Rate limiter, input validator, domain allowlist
│ ├── audit/ # Append-only JSONL audit log
│ └── cli/ # Human-only credential management
├── tests/ # 65 tests across 6 suites
└── ~/.agent-auth/ # Vault data (gitignored, local only)
├── vault.db # Encrypted SQLite
├── keyring.json # Master key (file fallback when keychain unavailable)
└── audit.log # JSONL audit trail
Stack
Bun, TypeScript (strict), @modelcontextprotocol/sdk, playwright-core, bun:sqlite, otpauth, @noble/hashes (Argon2id)
How to Test
AGENT_AUTH_NO_KEYCHAIN=1 bun test # 65 tests, all suites
bun run typecheck # TypeScript strict mode
AGENT_AUTH_NO_KEYCHAIN=1 avoids macOS Keychain permission dialogs in tests and CI.
Security Rules
These are non-negotiable. PRs that violate them will be rejected.
- Credentials are NEVER converted to JS strings. They flow as
Buffer/Uint8Arrayand are zeroed withbuf.fill(0)after injection. JS strings are immutable and GC'd — cannot be zeroed. - TOTP codes are NEVER returned to the agent. They are only injected via browser CDP or HTTP proxy.
- Domain allowlist is deny-by-default. Credentials can only be injected into explicitly listed domains.
- Domain is verified AFTER each navigation step to catch redirects to unauthorized domains.
- Rate limiting persists across restarts (SQLite-backed, not in-memory).
- First use of any credential+domain pair requires human approval (Pushover notification with 4-digit code, 50s window).
- No cloud features. The vault is local-only. No sync, no upload, no phoning home.
- No new runtime dependencies without justification. We have 5. That's enough.
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 · 65 lines · 784 tokens per session scan A f4e546c86a77
agent-auth AGENTS.md is an instructions file published in the GitHub repository ex-nihilo-labs/agent-auth (1 stars, last pushed 4mo ago), licensed MIT. It adds 784 tokens to every session, about $0.0039 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 2026-08-31.
Other instructions, from other repositories
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).
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.
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.