claude-channels SKILL.md skillB
claude-channels from valtterimelkko/agent-workflow-skills is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.
mdr add valtterimelkko/agent-workflow-skills/claude-channels@git:20260611.6de34bfPins git:20260611.6de34bf in mdr.lock. Pin the fingerprint instead.
- Audit grade
- B, 16 of 17 checks passed
- Kind
- SKILL.md skill
- Repository
- valtterimelkko/agent-workflow-skills
- Path
skills/claude-channels/SKILL.md- Versions recorded
- 2
- Latest version
- git:20260611.6de34bf, committed Jun 11, 2026
- First version recorded
- Jun 11, 2026
- Size
- 21,197 bytes
- Repository stars
- 2
- License
- MIT
Build MCP channel plugins that push external events into a running Claude Code interactive session and bridge bidirectional communication. Use when: building a custom channel plugin for Claude Code, bridging Claude Code to a web UI or chat platform, understanding the channels protocol (notification format, reply tools, sender gating, permission relay), integrating Claude Code with external systems via WebSocket or HTTP, replacing claude -p with interactive Claude Code for better subscription…
Collected from public GitHub. Every version is saved exactly as it was and never changes. Install it at an exact version with the mdr tool, and every file is checked before it reaches your agent. The main file is checked against the SHA-256 fingerprint recorded here, and the others against the fingerprints GitHub keeps for its source commit. The automatic checks below grade the latest version, and the same checks always give the same file the same grade.
What the file says
# Claude Code Channels > **Source:** This skill is based on the official [Channels reference](https://code.claude.com/docs/en/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 | |------|-----------|-------| …
Read the whole file at its exact version.
How to install
mdr add valtterimelkko/agent-workflow-skills/claude-channels@sha256:568137f6da9b14aeThe line at the top of this page pins the label git:20260611.6de34bf, which is what most people want. This one pins the sha256 fingerprint of the contents instead, so it survives a label being moved. Either way the exact version is written to mdr.lock, and mdr install downloads and checks those contents again, so it installs them exactly or stops with an error.
[](https://markdownregistry.com/a/art_g7m2fufrbkp7gzdy)
1 badge image fetches in 30 days. What the badge shows.
Versions
The registry has recorded 2 versions of this file, all committed on Jun 11, 2026.
| version | committed | commit | size | audit | |
|---|---|---|---|---|---|
| git:20260611.6de34bf latest | 2026-06-11 | 6de34bf | 21,197 B | B | view · diff |
| git:20260611.b2584e4 | 2026-06-11 | b2584e4 | 21,193 B | B | view |
Audit of the latest version
- fail: No link to a raw IP address (matched: http://127.0.0.1:3101)
- pass: Frontmatter block present
- pass: Frontmatter declares a name
- pass: Frontmatter declares a description
- pass: Size between 200 bytes and 200 KB (21197 bytes)
- pass: No zero-width or bidi control characters
- pass: No instruction hidden inside an HTML comment
- pass: No link to an exfiltration or paste host
- pass: No credential-shaped string
- pass: No instruction to send local credentials anywhere
- pass: No text hidden with inline styles
- pass: No prompt-injection phrasing
- pass: No curl or wget piped into a shell
- pass: No recursive delete of root, home or parent
- pass: No instruction to read or print local credentials
- pass: No base64 blob over 200 characters
- pass: No script tag
Starting a new one? Use a template for SKILL.md on mdpantry, which passes every one of these checks and says what to change in it.
Source
valtterimelkko/agent-workflow-skills · 2 stars · license MIT · pushed 2026-10-28 · branch main
API
GET https://markdownregistry.com/api/v1/artifacts/art_g7m2fufrbkp7gzdy GET https://markdownregistry.com/api/v1/resolve?ref=valtterimelkko/agent-workflow-skills/claude-channels GET https://markdownregistry.com/api/v1/blob/568137f6da9b14ae878aded1ca814155342347bd78968042337c1e6f2152f729
Your AI assistant does the legwork. You hear about the deals worth your word. Hand yours the standing instructions at modelranch.com and it joins the network that reads files like this one.
Guides: the SKILL.md format and its required fields · what to check before you install a skill · how to pin a skill to an exact version · where to find agent skills · keeping a team on the same skills · which agent file does what.