What is cli-gateway AGENTS.md?

Repository instructions for cli-gateway, a service that connects chat channels such as Discord and Telegram to coding agents. It also describes the project structure, database, scheduling, permissions, and user-interface modes.

Use it when developing cli-gateway, including its chat adapters, agent sessions, SQLite data, scheduler, permission controls, or restart scripts.

It gives coding agents the project context and file locations they need before editing this multi-part system. This lowers the risk of changing the wrong component or violating its permission rules.

How clawbot7/cli-gateway configures Codex and OpenCode

Reuse

Borrowing it

Nothing to install: this file belongs to clawbot7/cli-gateway. 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/clawbot7/cli-gateway/main/AGENTS.md

Clone the repo

git clone --depth 1 https://github.com/clawbot7/cli-gateway

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/clawbot7/cli-gateway/agents-md/github.svg)](https://agentmods.dev/instructions/clawbot7/cli-gateway/agents-md)

Your own site

<a href="https://agentmods.dev/instructions/clawbot7/cli-gateway/agents-md"><img src="https://agentmods.dev/badge/instructions/clawbot7/cli-gateway/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/clawbot7/cli-gateway/agents-md"><img src="https://agentmods.dev/badge/instructions/clawbot7/cli-gateway/agents-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 728 This file is loaded in full into every session.

When invoked 728 The same file — it is already loaded in full.

Security scan A 0 findings. 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	$0.00728	$0.00728
Opus 5.5	$0.00291	$0.00291
Sonnet 5.5	$0.00146	$0.00146
Haiku 4.5	$0.00073	$0.00073

Measured 2mo ago against content hash e7fd7a3ac758, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

cli-gateway 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 2mo 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.

AGENTS.md · 81 lines

How it starts

The opening of the file, as written. The whole thing — 81 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AGENTS.md (cli-gateway)

This file is for coding agents (Codex/Claude/etc) working in this repository.

Project summary

cli-gateway is a chat-channel ↔ ACP (Agent Client Protocol) gateway with:

Discord + Telegram + Feishu adapters
Per-binding ACP stdio runtime isolation (one agent process per binding)
SQLite persistence (sessions/bindings/runs/events/jobs)
Deny-by-default tool execution via ACP session/request_permission (interactive buttons on DC/TG + Discord reaction shortcuts)

Key paths

Entry: src/main.ts
Router/runtime: src/gateway/router.ts, src/gateway/bindingRuntime.ts
ACP stdio client: src/acp/client.ts
DB schema/migrations: src/db/migrations.ts
Scheduler: src/scheduler/scheduler.ts
Channel sinks: src/channels/discord.ts, src/channels/telegram.ts, src/channels/feishu.ts
Process guard/restart bridge: scripts/run-guard.sh, scripts/restart-watcher.sh

UI

UI modes: verbose (default) and summary.
Per-conversation override: /ui verbose|summary (stored in DB ui_prefs).
Per-conversation runtime prefs include /workspace and /cli (persist across /new).
Permission allowlist can be managed per conversation via /whitelist (tool_kind + optional prefix scoped, persisted via tool_policies and tool_allow_prefixes).

Local dev

Install: npm i
Run: npm run dev
Build: npm run build
Lint: npm run lint

Config is file-based; see ~/.cli-gateway/config.json (example in skills.md).

Conventions / constraints

TypeScript + ESM ("type": "module"). Keep imports with .js suffix in TS source.
Prefer small, composable modules; avoid over-abstracting.
Keep tool execution deny-by-default. Any expansion of tool surface must be explicitly gated.
File/terminal tool calls must remain restricted to WORKSPACE_ROOT.
Avoid adding new dependencies unless necessary.

Persistence & migrations

All DB schema changes go through src/db/migrations.ts.
Bump LATEST_VERSION when adding a migration.
Migrations must be additive and safe on existing DBs.

Read the full file on GitHub · 81 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.

2mo ago First seen · 81 lines · 728 tokens per session scan A e7fd7a3ac758

Subscribe to this mod's changes

cli-gateway AGENTS.md is an instructions file published in the GitHub repository clawbot7/cli-gateway (51 stars, last pushed 8mo ago), licensed MIT. It adds 728 tokens to every session, about $0.0029 per session on Opus 5.5. 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.

cli-gateway AGENTS.md next to 6 instructions from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
cli-gateway AGENTS.mdclawbot7/cli-gateway	Instructions file	51	8mo ago	MIT	A	728	Codex, OpenCode
vscode buildNext.instructions.mdmicrosoft/vscode	Instructions file	195k	today	MIT	A	9,719	GitHub Copilot
vscode oss-third-party-notices.instructions.mdmicrosoft/vscode	Instructions file	195k	today	MIT	A	5,516	GitHub Copilot
next.js AGENTS.mdvercel/next.js	Instructions file	143k	today	MIT	A	7,461	Codex, OpenCode
langchain AGENTS.mdlangchain-ai/langchain	Instructions file	149k	today	MIT	A	4,680	Codex, OpenCode
vscode copilot-instructions.mdmicrosoft/vscode	Instructions file	195k	today	MIT	A	3,093	GitHub Copilot
vscode model-prompts.instructions.mdmicrosoft/vscode	Instructions file	195k	today	MIT	A	2,022	GitHub Copilot

cli-gateway: Instructions file for Codex