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 agentfront/frontmcp --skill frontmcp-channelsgit clone --depth 1 https://github.com/agentfront/frontmcpWrote 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/agentfront/frontmcp/frontmcp-channels)<a href="https://agentmods.dev/skills/agentfront/frontmcp/frontmcp-channels"><img src="https://agentmods.dev/badge/skills/agentfront/frontmcp/frontmcp-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/agentfront/frontmcp/frontmcp-channels"><img src="https://agentmods.dev/badge/skills/agentfront/frontmcp/frontmcp-channels.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 5 findings, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium Prompt Injection · line 130 Large whitespace padding was detected (a block of blank lines or a long run of spaces). This can push injected instructions below or to the right of the visible area so a human reviewer never sees them while the agent still reads them. Manual review of the hidden content is recommended.Fix: Remove the large whitespace padding (blank-line blocks or long space runs) and review any content hidden below or to the right of it. Keep skill files compact and reviewable so no instructions can be
- medium Memory Poisoning · line 151 Skill attempts to fill the context window with filler content, displacing legitimate instructions and safety constraints. This can degrade agent performance or bypass safety boundaries.Fix: Implement context-window management that detects and rejects padding or stuffing attempts. Prioritize system instructions over user-injected content.
- medium Prompt Injection · line 151 Large whitespace padding was detected (a block of blank lines or a long run of spaces). This can push injected instructions below or to the right of the visible area so a human reviewer never sees them while the agent still reads them. Manual review of the hidden content is recommended.Fix: Remove the large whitespace padding (blank-line blocks or long space runs) and review any content hidden below or to the right of it. Keep skill files compact and reviewable so no instructions can be
- medium Prompt Injection · line 153 Large whitespace padding was detected (a block of blank lines or a long run of spaces). This can push injected instructions below or to the right of the visible area so a human reviewer never sees them while the agent still reads them. Manual review of the hidden content is recommended.Fix: Remove the large whitespace padding (blank-line blocks or long space runs) and review any content hidden below or to the right of it. Keep skill files compact and reviewable so no instructions can be
- medium Prompt Injection · line 154 Large whitespace padding was detected (a block of blank lines or a long run of spaces). This can push injected instructions below or to the right of the visible area so a human reviewer never sees them while the agent still reads them. Manual review of the hidden content is recommended.Fix: Remove the large whitespace padding (blank-line blocks or long space runs) and review any content hidden below or to the right of it. Keep skill files compact and reviewable so no instructions can be
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 | $0.00140 | $0.02513 |
| Opus 5.5 | $0.00056 | $0.01005 |
| Sonnet 5.5 | $0.00028 | $0.00503 |
| Haiku 4.5 | $0.00014 | $0.00251 |
Grade A, and why
frontmcp-channels 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 13d 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.
How it starts
The opening of the file, as written. The whole thing — 180 lines — stays where its author put it; the contents beside it link to each section on GitHub.
FrontMCP Channels
Build push-based notification channels that stream real-time events into Claude Code. Channels let your MCP server forward webhooks, application errors, agent completions, job results, and chat messages directly into Claude's context, with optional two-way reply support.
When to Use This Skill
Must Use
- You need Claude Code to react to external events (CI failures, monitoring alerts, deploy status)
- You are building a chat bridge (WhatsApp, Telegram, Slack, Discord) for Claude Code
- You want agents or background jobs to notify Claude Code upon completion
Recommended
- You want to forward application errors to Claude for debugging assistance
- You need a messaging interface where remote users can interact with Claude via chat platforms
Skip When
- You only need standard MCP resource subscriptions (use
@Resourcewithresources/subscribe) - Your client is not Claude Code and does not support
experimental['claude/channel'] - You need request-response patterns (use
@Toolinstead)
Decision: Use channels when you need server-initiated push notifications into Claude Code. Use resources when the client pulls data on demand.
Prerequisites
@frontmcp/sdk>= 1.0.0- Basic understanding of
@FrontMcp,@App, and@Tooldecorators - For webhook sources: HTTP transport (not stdio-only)
- For chat bridges: external API credentials (WhatsApp Business API, Telegram Bot Token, etc.)
Steps
- Choose your channel source type from the Scenario Routing Table
- Create a channel class or function
- Register it in your app
- Enable channels in
@FrontMcpconfig - Test with Claude Code using
--dangerously-load-development-channels
Scenario Routing Table
| Scenario | Reference | Description |
|---|---|---|
| Webhook alerts (CI, monitoring) | references/channel-sources.md |
Forward HTTP webhooks into Claude |
| Application error forwarding | references/channel-sources.md |
Push app errors via event bus |
| Agent completion notifications | references/channel-sources.md |
Notify when agents finish |
| Job/workflow completion | references/channel-sources.md |
Notify when jobs complete |
| Service connector (WhatsApp, etc.) | references/channel-sources.md |
Persistent connection with bidirectional tools |
| File/log watcher | references/channel-sources.md |
File system change monitoring |
| Event replay for offline sessions | references/channel-sources.md |
Buffer events for later delivery |
| WhatsApp/Telegram chat bridge | references/channel-two-way.md |
Two-way messaging with Claude |
| Slack/Discord integration | references/channel-two-way.md |
Chat platform bridges |
| Permission relay | references/channel-two-way.md |
Remote tool approval via chat |
What ships with it
10 files 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.
- examples/channel-sources/agent-notify.md 1.9 KB
- examples/channel-sources/app-errors.md 1.8 KB
- examples/channel-sources/file-watcher.md 3.2 KB
- examples/channel-sources/job-completion.md 2.3 KB
- examples/channel-sources/replay-buffer.md 7.0 KB
- examples/channel-sources/service-connector.md 4.6 KB
- examples/channel-sources/webhook-github.md 2.7 KB
- examples/channel-two-way/whatsapp-bridge.md 5.9 KB
- references/channel-sources.md 9.4 KB
- references/channel-two-way.md 6.3 KB
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.
- 13d ago Changed 3aac6b835410
- 14d ago Changed · +1 lines 738e060ce2d7
- 15d ago Changed · +13 lines 8d2a8a821717
- 17d ago Changed · +1 lines 1c305cf9cb73
- 1mo ago First seen · 165 lines · 140 tokens per session scan A 33647ee7d204
frontmcp-channels is a skill published in the GitHub repository agentfront/frontmcp (147 stars, last pushed today), licensed Apache-2.0. It adds 140 tokens to every session and 2,513 once invoked, about $0.0006 per session on Opus 5.5. 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.
Other skills, from other repositories
remindme
⏰ simple Telegram reminders for OpenClaw. cron, zero dependencies.
telegram-bot
Telegram bot development - chatbots, notifications, AI assistants, and group automation.
communication-systems
Email, notifications, and messaging system patterns.
novu-framework-integration
Build code-first notification workflows with @novu/framework. Use when defining workflows in TypeScript (Zod / JSON Schema / Class Validator), composing channel steps (email, SMS, push, chat, in-app) with action steps (delay, digest, custom), exposing Step Controls for non-technical teammates, rendering…
slackdump
Collect the Slack conversation data from Slackdump Archive format.
slackdump-sqlite3
Guidance for querying a Slackdump SQLite3 database directly via the sqlite3 CLI.