Chat Delivery Adapters

Chat Delivery Adapters is a skill for Claude Code from WYRE-AI/msp-claude-plugins. It costs 42 tokens per session (915 once invoked), scanned A, original, Apache-2.0.

A set of delivery adapters that sends a workflow's finished report to a place people can read it. It supports Slack messages or canvases and IT Glue documents, while Microsoft Teams is marked as unavailable.

In plain words
What is it for?
Use it to post short summaries to Slack, create a full Slack canvas with a summary link, or create an IT Glue document.
Why use it?
It avoids leaving workflow results inside the automation where people may not see them. It also defines how to handle missing or multiple connected destinations.

Skill for Claude Code

Written for Claude Code: when-to-use in frontmatter.

Part of the advanced-workflows plugin — 3 skills shipped together

Good fit Use it to post short summaries to Slack, create a full Slack canvas with a summary link, or create an IT Glue document.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/wyre-ai/msp-claude-plugins/chat-delivery-adapters
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.

Any agent
npx skills add WYRE-AI/msp-claude-plugins --skill chat-delivery-adapters
Clone the repo
git clone --depth 1 https://github.com/WYRE-AI/msp-claude-plugins

Made for: Claude Code.

Or install advanced-workflows, the plugin that ships this one along with the rest of its 3 skills.

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 Chat Delivery Adapters

README.md
[![agentmods](https://agentmods.dev/badge/skills/wyre-ai/msp-claude-plugins/chat-delivery-adapters/github.svg)](https://agentmods.dev/skills/wyre-ai/msp-claude-plugins/chat-delivery-adapters)
Your own site
<a href="https://agentmods.dev/skills/wyre-ai/msp-claude-plugins/chat-delivery-adapters"><img src="https://agentmods.dev/badge/skills/wyre-ai/msp-claude-plugins/chat-delivery-adapters/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.

agentmods 80×15 button for Chat Delivery Adapters

Your own site · 80×15
<a href="https://agentmods.dev/skills/wyre-ai/msp-claude-plugins/chat-delivery-adapters"><img src="https://agentmods.dev/badge/skills/wyre-ai/msp-claude-plugins/chat-delivery-adapters.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 42 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 915 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 5.1 $0.00042 $0.00915
Opus 5.5 $0.00017 $0.00366
Sonnet 5.5 $0.00008 $0.00183
Haiku 4.5 $0.00004 $0.00092

Measured 3d ago against content hash 0e6e5b2aa31e, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

Chat Delivery Adapters 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 3d 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.

msp-claude-plugins/advanced-workflows/advanced-workflows/skills/chat-delivery-adapters/SKILL.md · 82 lines

How it starts

The opening of the file, as written. The whole thing — 82 lines — stays where its author put it; the contents beside it link to each section on GitHub.

The contract

Every workflow's body produces a report payload; a delivery adapter takes that payload and writes it somewhere a human will see it. Detect which delivery target is connected the same way you detect a data-role vendor: if more than one is connected, ask the human which to use; if none is connected, tell the human what's needed — don't guess, don't fail silently.

Shipped adapters

Slack summary

  • Connector: Slack (first-party claude.ai connector, not Conduit-routed).
  • permitted_tools: slack_send_message.
  • Write snippet: post a one-paragraph summary to the destination channel.
  • Limits: plain text, no rich layout — best for a short result.

Slack canvas

  • Connector: Slack.
  • permitted_tools: slack_create_canvas, slack_send_message.
  • Write snippet: create a canvas titled <report name> — <date> with the full report; post a summary message linking it.
  • Limits: one canvas per run — each run leaves its own dated artefact rather than updating a single document in place.

IT Glue document

  • Connector: Conduit (itglue vendor connection).
  • permitted_tools: itglue__search_documents, itglue__create_document, itglue__update_document_section, itglue__publish_document.
  • Write snippet: search for an existing document named <report name> in the target IT Glue org; if found, update its section, else create it; then call itglue__publish_document — section edits are invisible to a human until the document is published.
  • Limits: needs a target org ID baked in. Updates in place, so reruns converge on a single document rather than accumulating artefacts. Conduit prefixes every served tool name with {vendor}__ at the gateway (itglue__ here) regardless of what the vendor's own internal classification table calls it — the itglue plugin's GOVERNANCE.md documents bare names like create_document for its internal permission-tier lookup, but the servable/callable name always carries the itglue__ prefix, same as every other vendor.

Read the full file on GitHub · 82 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. 3d ago First seen · 82 lines · 42 tokens per session scan A 0e6e5b2aa31e

Subscribe to this mod's changes

Chat Delivery Adapters is a skill published in the GitHub repository WYRE-AI/msp-claude-plugins (49 stars, last pushed yesterday), licensed Apache-2.0. It adds 42 tokens to every session and 915 once invoked, about $0.0002 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 2026-10-13.