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 mailgun/mailgun-plugins --skill deliverability-triagegit clone --depth 1 https://github.com/mailgun/mailgun-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/mailgun/mailgun-plugins/deliverability-triage)<a href="https://agentmods.dev/skills/mailgun/mailgun-plugins/deliverability-triage"><img src="https://agentmods.dev/badge/skills/mailgun/mailgun-plugins/deliverability-triage/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/mailgun/mailgun-plugins/deliverability-triage"><img src="https://agentmods.dev/badge/skills/mailgun/mailgun-plugins/deliverability-triage.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 | $0.00029 | $0.00492 |
| Opus 5 | $0.00015 | $0.00246 |
| Sonnet 5 | $0.00006 | $0.00098 |
| Haiku 4.5 | $0.00003 | $0.00049 |
Grade A, and why
deliverability-triage 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 8d 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 — 46 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Deliverability Triage
Use this skill when the user asks why email is failing, landing in spam, bouncing, throttling, or showing poor engagement.
Intake
Collect any missing context before using tools:
- Domain or domains.
- Region, if not already configured.
- Date range, defaulting to the last 7 days when the user agrees.
- Symptoms: bounces, deferrals, provider blocks, spam placement, low opens, low clicks, or complaint spikes.
- Whether the user wants diagnosis only or also remediation suggestions.
Workflow
- Confirm the active region and domain.
- Start with data gathering: domain details, DNS verification state, recent logs, metrics, bounce classification, and suppression counts.
- Group failures into permanent bounces, temporary failures, provider throttling, responses similar to blocklist rejections, authentication/DNS issues, and content or template quality issues.
- Compare current rates to a prior similar window when the user provides enough context.
- Summarize the most likely root causes with evidence from the Mailgun tools.
- Recommend next actions, separating diagnostic steps from actions that require confirmation.
Signals to Check
- Complaint rate near or above 0.1 percent is a serious reputation signal.
- Bounce rate above 2 percent should trigger list quality review, and hard bounce spikes should be treated as urgent.
- Cold domains, cold IPs, and sudden volume jumps often show up as throttling or temporary failures before hard blocking.
- Suppressed recipients can explain missing mail because later sends may be dropped without a request failure.
- Provider specific failures should be grouped separately for Gmail, Microsoft, Yahoo, iCloud, and other major mailbox providers.
- If current analytics are available, use logs and metrics rather than deprecated stats or events endpoints.
Safety
Do not modify suppressions, tracking, templates, webhooks, IP pools, domain settings, or account settings without explicit confirmation. Do not send test messages unless the user confirms sender, recipient, subject, and whether test mode should be used.
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.
- 8d ago First seen · 46 lines · 29 tokens per session scan A 8ee60ce85ba9
deliverability-triage is a skill published in the GitHub repository mailgun/mailgun-plugins (1 stars, last pushed 19d ago), licensed Apache-2.0. It adds 29 tokens to every session and 492 once invoked, about $0.0001 per session on Opus 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 2026-08-31.
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…