agentmods.dev

backchannel: Instructions file for Codex

AGENTS.md

backchannel AGENTS.md is an instructions file for Codex, OpenCode from unison-labs-ai/backchannel. It costs 612 tokens per session, scanned A, original, MIT.

Project instructions for backchannel, an asynchronous messaging tool for AI agents. It stores messages in a spool, a temporary message queue, until an agent reads and acknowledges them.

In plain words
What is it for?
Changing the command-line tool, message queue implementations, relay server, or MCP server while keeping messages deleted after acknowledgement.
Why use it?
They preserve the tool's temporary-message behavior while allowing local files, an HTTP relay, or the Unison brain service to provide the queue.

Instructions file for CodexOpenCode

Written for Codex and OpenCode: the file is AGENTS.md. Also seen: mentions AGENTS.md.

This is unison-labs-ai/backchannel's own configuration. It tells Codex and OpenCode how to work on backchannel 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 backchannel configures →

not rated 2repo 2mo ago A scan 612 tokens original MIT
View source ↗ unison-labs-ai/backchannel unisonlabs.ai
Reuse

Borrowing it

Nothing to install: this file belongs to unison-labs-ai/backchannel. 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/unison-labs-ai/backchannel/main/AGENTS.md
Clone the repo
git clone --depth 1 https://github.com/unison-labs-ai/backchannel

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.

agentmods badge for backchannel AGENTS.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/unison-labs-ai/backchannel/agents-md.svg)](https://agentmods.dev/instructions/unison-labs-ai/backchannel/agents-md)
Your own site
<a href="https://agentmods.dev/instructions/unison-labs-ai/backchannel/agents-md"><img src="https://agentmods.dev/badge/instructions/unison-labs-ai/backchannel/agents-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 612 This file is loaded in full into every session.
When invoked 612 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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00612 $0.00612
Opus 5 $0.00306 $0.00306
Sonnet 5 $0.00122 $0.00122
Haiku 4.5 $0.00061 $0.00061

Measured 7d ago against content hash 1eb99db68ec8, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

backchannel 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 7d 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 · 41 lines

How it starts

The opening of the file, as written. The whole thing — 41 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AGENTS.md — working on this repo

You are an agent contributing to backchannel. (If you want to use backchannel to talk to other agents, read SKILL.md instead.)

What this is

A spool-based async messaging tool for AI agents. One core abstraction: the Spool interface (src/types.ts) with three implementations — FsSpool (local Maildir-style files), HttpSpool (same semantics over a self-hosted relay), and BrainSpool (same semantics over the Unison brain API). Everything else (CLI, MCP server, relay) is a thin layer over Spool.

Commands

bun install        # deps (only @modelcontextprotocol/sdk + zod)
bun test           # full suite, must stay green
bun src/cli.ts     # run the CLI from source

There is no build step. The CLI runs TypeScript directly under Bun.

Architecture rules (load-bearing — don't break these)

  1. Delete-on-ack is the product. backchannel stores messages until read, not forever. Any feature that turns the spool into a history database changes what this tool is — reject it or gate it behind an explicit flag like ack --keep.
  2. The relay is a dumb spool host. relay.ts wraps FsSpool over HTTP. It must not grow logic that FsSpool doesn't have; if local and remote mode behave differently, that's a bug.
  3. Spool is the only contract. New features go into the interface first, then both implementations, then the CLI/MCP layers. Never reach around the interface.
  4. Zero infrastructure by default. Local mode must keep working with no daemon, no server, no config beyond bch init.
  5. Crash safety via Maildir discipline. Writes go to tmp/ then atomic-rename into new/. Don't replace this with anything that can expose partial writes.

Conventions

  • Bun APIs (Bun.file, Bun.write, Bun.serve, bun:test) over Node equivalents where both exist.
  • No comments unless a constraint is invisible in the code.
  • No new dependencies without a strong reason — the dependency surface (2 packages) is a feature.
  • Errors are thrown with actionable messages (tell the user the command that fixes it).

Read the full file on GitHub · 41 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. 7d ago First seen · 41 lines · 612 tokens per session scan A 1eb99db68ec8

Subscribe to this mod's changes

backchannel AGENTS.md is an instructions file published in the GitHub repository unison-labs-ai/backchannel (2 stars, last pushed 2mo ago), licensed MIT. It adds 612 tokens to every session, about $0.0031 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.

Building agentsClaude Codeagent-communicationai-agentscodexgemini-climcp
Related

Other instructions, from other repositories

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

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

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

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

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