A shared-file communication method that lets separate coding agents exchange messages through named channels.

Use it to open, join, watch, poll, send messages on, or leave a channel shared by Codex, Claude Code, or OpenCode agents.

It provides a way for agents running in different sessions or tools to coordinate without placing all work in one session.

channel — Skill for Claude Code and Codex by fl4p: A shared-file communication method that lets separate coding agents…

Install

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.

agentmods

npx agentmods add skills/fl4p/agent-channel/channel

Any agent

npx skills add fl4p/agent-channel --skill channel

Clone the repo

git clone --depth 1 https://github.com/fl4p/agent-channel

Made for: Claude Code, Codex.

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/skills/fl4p/agent-channel/channel.svg)](https://agentmods.dev/skills/fl4p/agent-channel/channel)

Your own site

<a href="https://agentmods.dev/skills/fl4p/agent-channel/channel"><img src="https://agentmods.dev/badge/skills/fl4p/agent-channel/channel.svg" alt="Measured on agentmods" height="20"></a>

Per session 60 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 2,616 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. Scan, not verified.

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	$0.00060	$0.02616
Opus 5	$0.00030	$0.01308
Sonnet 5	$0.00012	$0.00523
Haiku 4.5	$0.00006	$0.00262

Measured 5d ago against content hash a9d61008d7d2, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

channel 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 5d ago.

The scan reads SKILL.md. This mod also ships 1 executable file (scripts/channel.py), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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.

codex/channel/SKILL.md · 205 lines

How it starts

The opening of the file, as written. The whole thing — 205 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Channel

Use a shared append-only NDJSON file to talk with another agent in a separate session. This is compatible with Codex, Claude Code, and OpenCode channel skills: all agents share /tmp/claude-channels/<channel>.ndjson, and each participant has its own cursor.

User Interface

The user should invoke this as a skill, for example $channel vrp gpt, or ask in natural language to join, watch, send on, poll, or leave a channel. Do not ask the user to run the Python helper. The helper commands below are internal implementation details for the agent to execute.

Important Model

Agents are turn-based. A channel watcher only enters context while the agent is idle if the host can wake the agent from background command output.

Codex with exec_command.wake_on_output: use stream. This is the local fork path for https://github.com/openai/codex/issues/22003. The tool may be shown as exec_command or namespaced like functions.exec_command; the wake_on_output parameter is decisive. Launch python3 <HELPER> stream <channel> <agent> with wake_on_output: true, tty: true, and a short yield_time_ms. stream prints one flushed line per peer message and keeps running, so Codex is re-entered by synthetic background-output user messages. No re-arm is needed. Do not also run foreground poll/listen/wait while stream is live because they share the same cursor. Keep the returned session_id. If the user stops watching without leaving, stop it with write_stdin Ctrl-C ("\u0003"). On leave, the helper writes a cooperative stop marker before announcing departure, so bundled streams exit without replaying the transcript; use Ctrl-C only if the host still reports the stream as live afterward.

Stock Codex: use foreground listen, not background wait. If the wake_on_output parameter is absent, Codex cannot receive asynchronous channel updates while idle. Drive the channel with foreground listen --timeout 30 and re-run it while waiting. wait still works if you actively block on it in the turn, but launching it in the background will not wake Codex.

Read the full file on GitHub · 205 lines

Files

What ships with it

1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

scripts/channel.py 37 KB runs code

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.

5d ago First seen · 205 lines · 60 tokens per session scan A a9d61008d7d2

Subscribe to this mod's changes

channel is a skill published in the GitHub repository fl4p/agent-channel (24 stars, last pushed 17d ago), licensed MIT. It adds 60 tokens to every session and 2,616 once invoked, about $0.0003 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 2026-08-30.

Building agents

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

local-ai-agents

Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…

microsoft/ai-agents-for-beginners · 200 tokens

next-cache-components-adoption

Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…

vercel/next.js · 95 tokens

chat-pet-sprite-creation

Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.

microsoft/vscode · 53 tokens

cpu-profile-analysis

Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…

microsoft/vscode · 71 tokens

insight-error-page

Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…

vercel/next.js · 83 tokens