What is cli AGENTS.md?

Repository instructions for the inboxapi CLI, a command-line tool whose project includes JavaScript/Node.js code, an MCP connection, packaging, and agent installation logic.

Use them when changing the CLI, its Node.js subprocess handling, Rust build and test workflow, npm packaging, or agent-installation code.

They call out safety and reliability issues such as shell injection, lost buffered input, hanging I/O, and incorrectly parsed streamed data.

How inboxapi/cli configures Codex and OpenCode

Reuse

Borrowing it

Nothing to install: this file belongs to inboxapi/cli. 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/inboxapi/cli/main/AGENTS.md

Clone the repo

git clone --depth 1 https://github.com/inboxapi/cli

Made for: Codex, OpenCode.

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.

README.md

[![agentmods](https://agentmods.dev/badge/instructions/inboxapi/cli/agents-md/github.svg)](https://agentmods.dev/instructions/inboxapi/cli/agents-md)

Your own site

<a href="https://agentmods.dev/instructions/inboxapi/cli/agents-md"><img src="https://agentmods.dev/badge/instructions/inboxapi/cli/agents-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.

Your own site · 80×15

<a href="https://agentmods.dev/instructions/inboxapi/cli/agents-md"><img src="https://agentmods.dev/badge/instructions/inboxapi/cli/agents-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 1,436 This file is loaded in full into every session.

When invoked 1,436 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.

Model	Per session	Once invoked
Fable 5.1	$0.01436	$0.01436
Opus 5.5	$0.00574	$0.00574
Sonnet 5.5	$0.00287	$0.00287
Haiku 4.5	$0.00144	$0.00144

Measured 1mo ago against content hash 1923fefdff9f, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

cli AGENTS.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 1mo 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.

Runs shell commandslowCapability

Expected in a hook, worth knowing in a rule or an instructions file.

- Never use `execSync` / `execFileSync` with string interpolation — pass arguments as arrays to avoid shell injection

AGENTS.md · 120 lines

How it starts

The opening of the file, as written. The whole thing — 120 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CLI Agent Stub

Rust STDIO proxy that bridges JSON-RPC (MCP protocol) over STDIO to the remote InboxAPI MCP service over Streamable HTTP/SSE. Distributed as @inboxapi/cli on npm with platform-specific binary packages.

Overview

Technology: Rust (Tokio async runtime, reqwest HTTP client, manual SSE parsing over bytes_stream())
Protocol: JSON-RPC over STDIO (MCP standard)
Transport: HTTP POST + SSE to remote endpoint
Distribution: npm with platform-specific optional dependencies
CI: GitHub Actions (5-platform cross-build, GitHub Releases, npm publish)

Canonical workflow lives in ../AGENTS.md.

Key Files

src/main.rs — Proxy loop, token injection, login flow, hashcash proof-of-work
index.js — npm binary resolver (platform package → local build → cargo run)
package.json — Root npm package with optionalDependencies for 5 platforms
npm/cli-*/package.json — Platform-specific package manifests (os/cpu fields)
.github/workflows/release.yml — Cross-build, GitHub Release, npm publish pipeline
Cargo.toml — Rust project configuration and dependencies
tests/mcp_integration_test.rs — Integration tests

CLI Commands

cargo run -- proxy   # Start STDIO proxy (default)
cargo run -- login   # Authenticate and store credentials
cargo run -- whoami  # Show current account

# Email operations
cargo run -- send-email --to [email protected] --subject "Hi" --body "Hello"
cargo run -- send-email --to [email protected] --subject "Newsletter" --body-file ./body.txt --html-body-file ./newsletter.html
cargo run -- get-emails --limit 5
cargo run -- get-email "<message-id>"
cargo run -- search-emails --subject "keyword"
cargo run -- get-attachment <id> --output ./file.pdf
cargo run -- send-reply --message-id "<id>" --body "Reply"
cargo run -- send-reply --message-id "<id>" --body-file ./reply.txt --html-body-file ./reply.html
cargo run -- forward-email --message-id "<id>" --to [email protected]
cargo run -- help

Read the full file on GitHub · 120 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.

1mo ago Changed · +80 lines · +891 tokens per session 1923fefdff9f
2mo ago First seen · 40 lines · 545 tokens per session scan A f368cc4f5e4a

Subscribe to this mod's changes

cli AGENTS.md is an instructions file published in the GitHub repository inboxapi/cli (13 stars, last pushed 1mo ago), licensed MIT. It adds 1,436 tokens to every session, about $0.0057 per session on Opus 5.5. A static security scan graded it A with 1 finding (runs shell commands). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

ai ai-agent email email-sender mcp mcp-client

cli AGENTS.md next to 6 instructions from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
cli AGENTS.mdinboxapi/cli	Instructions file	13	1mo ago	MIT	A	1,436	Codex, OpenCode
vscode buildNext.instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	9,719	GitHub Copilot
next.js AGENTS.mdvercel/next.js	Instructions file	143k	yesterday	MIT	A	7,461	Codex, OpenCode
langchain AGENTS.mdlangchain-ai/langchain	Instructions file	149k	yesterday	MIT	A	4,680	Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	5,516	GitHub Copilot
vscode copilot-instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	3,093	GitHub Copilot
deepseek-harness AGENTS.mddeepseek-ai/deepseek-harness	Instructions file	274k	2d ago	MIT	A	4,313	Codex, OpenCode

cli: Instructions file for Codex