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 WYRE-AI/msp-claude-plugins --skill chat-delivery-adaptersgit clone --depth 1 https://github.com/WYRE-AI/msp-claude-pluginsWrote 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/wyre-ai/msp-claude-plugins/chat-delivery-adapters)<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.
<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>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 | $0.00042 | $0.00915 |
| Opus 5.5 | $0.00017 | $0.00366 |
| Sonnet 5.5 | $0.00008 | $0.00183 |
| Haiku 4.5 | $0.00004 | $0.00092 |
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.
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 (
itgluevendor 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 callitglue__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 — theitglueplugin'sGOVERNANCE.mddocuments bare names likecreate_documentfor its internal permission-tier lookup, but the servable/callable name always carries theitglue__prefix, same as every other vendor.
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.
- 3d ago First seen · 82 lines · 42 tokens per session scan A 0e6e5b2aa31e
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.
Other skills, from other repositories
houseclean
Cross-drive storage audit and cleanup. Surveys all drives, finds orphaned git worktrees, large AI tool caches (.ollama, .gemini, .cursor, npm, pip), and buildable artifacts (nodemodules, .venv). Produces a prioritized action plan with specific migration commands. Use when disk space is low or worktrees need cleanup…
schedule
Manages recurring and one-off scheduled tasks. Session-scoped scheduling via CronCreate/CronDelete/CronList. Documents the cloud path for tasks that need to survive machine sleep or network drops.
career-portfolio
A portfolio-building skill for Korean job seekers that organizes projects and explains their work for development, design, marketing, and planning roles.
hr-operations
A skill for designing remote-work and team-operation policies. It covers flexible work, asynchronous communication, collaboration tools, productivity tracking, and employee experience.
collab-conflict
A guide for handling difficult workplace colleagues and recurring communication conflicts.
collab-feedback-loop
A guide for giving and receiving workplace feedback about specific actions and their effects.