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/aarifmms/keyblind/claude-mdgit clone --depth 1 https://github.com/aarifmms/keyblindWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/instructions/aarifmms/keyblind/claude-md)<a href="https://agentmods.dev/instructions/aarifmms/keyblind/claude-md"><img src="https://agentmods.dev/badge/instructions/aarifmms/keyblind/claude-md.svg" alt="Measured on agentmods" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5 | $0.00923 | $0.00923 |
| Opus 5 | $0.00462 | $0.00462 |
| Sonnet 5 | $0.00185 | $0.00185 |
| Haiku 4.5 | $0.00092 | $0.00092 |
Grade A, and why
keyblind 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 3d 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 — 83 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Keyblind — Blind AI to Your Keys
Encrypted secrets vault with MCP for AI agents. Secrets resolved at runtime, never leaked to LLM conversations.
Tech Stack
- Runtime: Node.js (TypeScript, ESM)
- Encryption: AES-256-GCM (Node crypto)
- Storage: SQLite (better-sqlite3)
- Protocol: MCP (Model Context Protocol) via stdio + Streamable HTTP transport
- Backends: Local vault, 1Password CLI, Bitwarden CLI, env vars, AWS, GCP, Azure
Project Structure
src/
├── vault.ts → AES-256-GCM encryption + SQLite store
├── server.ts → MCP server (16 tools) + REST API for dashboard
├── sandbox.ts → .env sandbox with deterministic fakes (HMAC-SHA256)
├── backends.ts → Multi-backend abstraction (local, 1Password, Bitwarden, env)
├── cli.ts → CLI entry point (40+ commands)
├── index.ts → Public API exports
├── totp.ts → TOTP/HOTP 2FA code generation (zero deps)
├── share.ts → Encrypted secret sharing via URL fragments
├── deadman.ts → Dead man's switch with email notification
├── https.ts → Let's Encrypt HTTPS for MCP server
├── sso.ts → SSO/OIDC authentication for team vaults
├── setup-mcp.ts → Auto-configure MCP for Claude Code (`keyblind setup-mcp`)
├── auth.ts → Biometric authentication gate
├── license.ts → Ed25519 license key verification
├── team.ts → Shared team vaults (git-safe)
├── sync.ts → Version history, rollback, sync bundles
├── doctor.ts → Vault health check
├── config.ts → Project configuration (.keyblind)
├── completions.ts → Shell completions (bash, zsh, fish)
├── hook.ts → Pre-commit hook for secret detection
├── watch.ts → Watch .env and auto-sandbox
└── alerts.ts → Slack/Discord webhook alerts
dashboard/ → Next.js web dashboard (app.keyblind.dev)
browser-extension/ → Chrome extension (MV3, paste interception)
Commands
npm run build # Compile TypeScript
npx tsc --watch # Dev mode
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.
- 3d ago First seen · 83 lines · 923 tokens per session scan A 495f9f2359ba
keyblind CLAUDE.md is an instructions file published in the GitHub repository aarifmms/keyblind (3 stars, last pushed 3mo ago), licensed MIT. It adds 923 tokens to every session, about $0.0046 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.