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.
npx skills add valtterimelkko/agent-workflow-skills --skill claude-channelsgit clone --depth 1 https://github.com/valtterimelkko/agent-workflow-skillsWrote 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.
[](https://agentmods.dev/skills/valtterimelkko/agent-workflow-skills/claude-channels)<a href="https://agentmods.dev/skills/valtterimelkko/agent-workflow-skills/claude-channels"><img src="https://agentmods.dev/badge/skills/valtterimelkko/agent-workflow-skills/claude-channels/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.
<a href="https://agentmods.dev/skills/valtterimelkko/agent-workflow-skills/claude-channels"><img src="https://agentmods.dev/badge/skills/valtterimelkko/agent-workflow-skills/claude-channels.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.00159 | $0.04905 |
| Opus 5 | $0.00079 | $0.02452 |
| Sonnet 5 | $0.00032 | $0.00981 |
| Haiku 4.5 | $0.00016 | $0.00490 |
Grade B, and why
claude-channels scanned grade B with 2 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 11d 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.
Sends data to an external URLmediumData exfiltration
A POST to an outside endpoint may be telemetry or may be exfiltration; either way the mod talks to somewhere, and you should know where.
curl -X POST localhost:8788 -d "build failed on main: https://ci.example.com/run/1234" Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
async fetch(req) { How it starts
The opening of the file, as written. The whole thing — 459 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Claude Code Channels
Source: This skill is based on the official Channels reference from Anthropic's Claude Code documentation. Always consult it for the latest protocol details.
Build channel plugins that push webhooks, alerts, chat messages, and external events into a running Claude Code session. Channels are MCP server plugins that bridge external systems into Claude Code's interactive agent loop — the same session you'd normally use from the terminal.
Why Channels Matter
Channels solve a specific problem: you want Claude Code to react to things happening outside the terminal while preserving its context, tools, and agent loop. Unlike claude -p (which starts a fresh one-shot subprocess per prompt), channels push events into a long-lived interactive Claude Code session that maintains working memory, MCP tools, and accumulated knowledge across messages.
The other major motivation is quota economics. Starting June 15, 2026, Anthropic separated quotas:
| Path | Quota pool | Limit |
|---|---|---|
| Interactive Claude Code (terminal, channels, Remote Control, Claude Cowork) | Main subscription quota | Generous |
Agent SDK + claude -p |
$20/month SDK credit | Limited |
Channels use the main subscription quota because they run inside an interactive session.
Architecture
A channel is an MCP server that Claude Code spawns as a subprocess over stdio. It also runs a network listener (WebSocket or HTTP) for external applications:
┌──────────────┐ ┌──────────────────┐
│ External │ ◄── WebSocket ──► │ Channel Plugin │
│ Application │ or HTTP │ (MCP server) │
└──────────────┘ └────────┬─────────┘
│ stdio (MCP)
┌──────▼──────────┐
│ Claude Code │
│ (interactive │
│ session) │
└──────────────────┘
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.
- 11d ago First seen · 459 lines · 159 tokens per session scan B 568137f6da9b
claude-channels is a skill published in the GitHub repository valtterimelkko/agent-workflow-skills (2 stars, last pushed 2mo ago), licensed MIT. It adds 159 tokens to every session and 4,905 once invoked, about $0.0008 per session on Opus 5. A static security scan graded it B with 2 findings (sends data to an external url, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
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…
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…
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…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…
next-partial-prefetching-adoption
Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…