ai-cli-bridge: Instructions file for Claude Code

CLAUDE.md

ai-cli-bridge CLAUDE.md is an instructions file for Claude Code from Shreyas-Dayal/ai-cli-bridge. It costs 1,282 tokens per session, scanned A, original, MIT.

A small web server that puts the Claude Code and Codex command-line tools behind an HTTP API. It uses subscription accounts, stores keys and usage in JSON files, and supports streaming responses.

In plain words
What is it for?
Use it to expose Claude Code and Codex through an Express API, authenticate users, track usage, stream output, and run the service on a VPS behind a reverse proxy or tunnel.
Why use it?
It gives applications a single network interface for calling these command-line assistants and includes user authentication, usage limits, and request logging.

Instructions file for Claude Code

Written for Claude Code: the file is CLAUDE.md. Also seen: mentions CLAUDE.md; mentions Claude Code; mentions Codex.

This is Shreyas-Dayal/ai-cli-bridge's own configuration. It tells Claude Code how to work on ai-cli-bridge itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything ai-cli-bridge configures →

Reuse

Borrowing it

Nothing to install: this file belongs to Shreyas-Dayal/ai-cli-bridge. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/Shreyas-Dayal/ai-cli-bridge/master/CLAUDE.md
Clone the repo
git clone --depth 1 https://github.com/Shreyas-Dayal/ai-cli-bridge

Made for: Claude Code.

Wrote 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.

agentmods badge for ai-cli-bridge CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/shreyas-dayal/ai-cli-bridge/claude-md/github.svg)](https://agentmods.dev/instructions/shreyas-dayal/ai-cli-bridge/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/shreyas-dayal/ai-cli-bridge/claude-md"><img src="https://agentmods.dev/badge/instructions/shreyas-dayal/ai-cli-bridge/claude-md/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for ai-cli-bridge CLAUDE.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/shreyas-dayal/ai-cli-bridge/claude-md"><img src="https://agentmods.dev/badge/instructions/shreyas-dayal/ai-cli-bridge/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 1,282 This file is loaded in full into every session.
When invoked 1,282 The same file — it is already loaded in full.
Security scan A 1 finding. A grade says what 26 rules found in the file — not that it is safe.
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 5.1 $0.01282 $0.01282
Opus 5 $0.00641 $0.00641
Sonnet 5 $0.00256 $0.00256
Haiku 4.5 $0.00128 $0.00128

Measured 9d ago against content hash 634c0f71ea8c, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

ai-cli-bridge CLAUDE.md scanned grade A with 1 finding 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 9d 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.

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

curl -s https://<YOUR_DOMAIN>/health
CLAUDE.md · 124 lines

How it starts

The opening of the file, as written. The whole thing — 124 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CLAUDE.md — ai-cli-bridge

What This Is

HTTP bridge server wrapping Claude Code CLI and Codex CLI behind an Express API. Uses Max/Pro subscriptions instead of per-token API keys. Designed to deploy on any VPS behind a reverse proxy or Cloudflare Tunnel.

Stack

  • Runtime: Bun, TypeScript, ES modules
  • Framework: Express 4
  • Package manager: bun
  • Process manager: systemd
  • Tunnel: Cloudflare Tunnel (cloudflared)
  • No database — JSON file persistence (data/keys.json, data/usage.json, data/logs.json)

Project Layout

src/
  server.ts           — Express app, routes, middleware, security headers
  config.ts           — Env var parsing + defaults
  keys.ts             — KeyManager: hashed key CRUD, usage tracking, limits, request logs
  middleware/auth.ts   — Per-user key auth + admin auth (timing-safe)
  utils/sse.ts        — SSE helpers (initSSE, sendSSEEvent, sendSSEError, sendSSEDone)
  providers/
    claude.ts         — Claude Code CLI wrapper (execFile + spawn for streaming)
    codex.ts          — Codex CLI wrapper (execFile + spawn for streaming)
public/
  admin.html          — Dashboard markup
  admin.css           — Dashboard styles
  admin.js            — Dashboard logic
dist/                 — Compiled JS (gitignored)
data/                 — Runtime data (gitignored, 0o600 permissions)

Commands

bun dev               # Dev server with watch
bun run build         # TypeScript compile (tsc)
bun start             # Run via bun
bun start:prod        # Run compiled JS (bun dist/server.js)

Build & Deploy

bun run build
rsync -avz --exclude node_modules --exclude .env --exclude data --exclude .git \
  ./ <YOUR_SERVER>:/path/to/ai-cli-bridge/
ssh <YOUR_SERVER> "systemctl restart ai-cli-bridge"

Static-only changes (public/) don't need a server restart.

See DEPLOY.md for full reference.

Architecture

  • CLI wrapping: execFile() spawns CLI for non-streaming, spawn() for streaming. Both use array args (no shell injection).
  • Endpoint-based routing: /generate → Claude CLI, /generate-codex → Codex CLI. Both support stream: true for SSE responses.
  • Auth: SHA-256 hashed keys with crypto.timingSafeEqual. Raw keys never stored — shown once at creation. req.keyHash on request object, never req.rawKey.
  • Limits: Per-key: requests/day, requests/month, tokens/month, cost/day, cost/month. All default 0 (unlimited).
  • Usage tracking: In-memory with 30s dirty-flag flush to disk. Daily entries pruned >90 days, monthly >12 months.
  • Request logs: Append-only in logs.json, capped at 1000 entries FIFO, prompts truncated to 200 chars.
  • Admin dashboard: Static HTML/CSS/JS served via express.static before admin auth middleware. Uses sessionStorage for admin key.

Read the full file on GitHub · 124 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. 9d ago First seen · 124 lines · 1,282 tokens per session scan A 634c0f71ea8c

Subscribe to this mod's changes

ai-cli-bridge CLAUDE.md is an instructions file published in the GitHub repository Shreyas-Dayal/ai-cli-bridge (13 stars, last pushed 4mo ago), licensed MIT. It adds 1,282 tokens to every session, about $0.0064 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Related

Other instructions, from other repositories

next.js AGENTS.md

AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.

vercel/next.js · 7,296 tokens

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.

openai/codex · 5,153 tokens

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).

microsoft/vscode · 6,785 tokens

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).

microsoft/vscode · 5,001 tokens

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.

langchain-ai/langchain · 4,469 tokens

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.

github/spec-kit · 7,104 tokens