agent-channel-module

agent-channel-module is a skill for Claude Code, Codex from yogasw/wick. It costs 164 tokens per session (4,536 once invoked), scanned A, original, MIT.

A set of rules for building and maintaining agent channels, which connect chat services such as Slack or Telegram to a group of agents. It covers incoming messages, replies, approvals, and live reloading.

In plain words
What is it for?
Use it when creating, changing, or debugging a Slack, Telegram, Discord, or similar transport in the agent channel system.
Why use it?
It gives channel code a shared structure for access control, message delivery, threaded replies, and approval requests. This reduces differences and mistakes across chat integrations.

Skill for Claude CodeCodex

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/yogasw/wick/agent-channel-module
Any agent
npx skills add yogasw/wick --skill agent-channel-module
Clone the repo
git clone --depth 1 https://github.com/yogasw/wick

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.

agentmods badge for agent-channel-module

README.md
[![agentmods](https://agentmods.dev/badge/skills/yogasw/wick/agent-channel-module.svg)](https://agentmods.dev/skills/yogasw/wick/agent-channel-module)
Your own site
<a href="https://agentmods.dev/skills/yogasw/wick/agent-channel-module"><img src="https://agentmods.dev/badge/skills/yogasw/wick/agent-channel-module.svg" alt="Measured on agentmods" height="20"></a>
Per session 164 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 4,536 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.

ModelPer sessionOnce invoked
Fable 5 $0.00164 $0.04536
Opus 5 $0.00082 $0.02268
Sonnet 5 $0.00033 $0.00907
Haiku 4.5 $0.00016 $0.00454

Measured 4d ago against content hash 293ce2699d4e, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

agent-channel-module 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 4d 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.

.claude/skills/agent-channel-module/SKILL.md · 411 lines

How it starts

The opening of the file, as written. The whole thing — 411 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Agent Channel Module — wick core

Scope: this skill is for transports under internal/agents/channels/ — Slack, Telegram, and any future channel (Discord, Line, MS Teams, …). Channels are wick-internal: downstream projects never write their own. If you are building a tool, job, or connector, use a different skill.

Activate this skill whenever the user touches a channel transport — creating a new one, refactoring an existing one, fixing event fan-out / approval flow / hot-reload bugs, or editing the registry, setup composer, or shared interfaces. When editing an existing channel, audit it against the rules below and bring it up to spec as part of the change.

Mental model

A channel bridges one external chat surface (Slack thread, Telegram chat, …) to the wick agent pool. It owns:

  • Inbound: listening for user messages, access control, meta-command intercept, dispatch to the pool via SendFunc.
  • Outbound: posting agent replies (chunked, threaded, with reactions/lifecycle markers as appropriate).
  • Approval: surfacing gate approval requests as native UI (Slack buttons, Telegram inline keyboard) and resolving the user's decision back through ApproveFn.
  • Hot-reload: applying new credentials without restarting the server, via a ConfigSource.

The registry (channels.Registry) is the single seam between the server and individual channels. Server constructs each channel with its config alone, hands it to the registry, and the registry auto-wires shared dependencies through optional setter interfaces and fans events out to whichever channels implement the matching receiver.

Applies to (non-exhaustive triggers)

  • "Add a new channel for Discord / Line / MS Teams / …"
  • "Add a meta-command to Slack / Telegram"
  • "Fix event fan-out / approval flow / hot-reload bug in channels"
  • Any edit under internal/agents/channels/<name>/
  • Changes to internal/agents/channels/{channel.go, registry.go, store.go} or internal/agents/channels/setup/

Read the full file on GitHub · 411 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. 4d ago First seen · 411 lines · 164 tokens per session scan A 293ce2699d4e

Subscribe to this mod's changes

agent-channel-module is a skill published in the GitHub repository yogasw/wick (5 stars, last pushed today), licensed MIT. It adds 164 tokens to every session and 4,536 once invoked, about $0.0008 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.

Related

Other skills, from other repositories