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 agentmods add skills/gaelic-ghost/socket/mailkit-workflownpx skills add gaelic-ghost/socket --skill mailkit-workflowgit clone --depth 1 https://github.com/gaelic-ghost/socketWrote 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/gaelic-ghost/socket/mailkit-workflow)<a href="https://agentmods.dev/skills/gaelic-ghost/socket/mailkit-workflow"><img src="https://agentmods.dev/badge/skills/gaelic-ghost/socket/mailkit-workflow.svg" alt="Measured on agentmods" 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 | $0.00048 | $0.01617 |
| Opus 5 | $0.00024 | $0.00809 |
| Sonnet 5 | $0.00010 | $0.00323 |
| Haiku 4.5 | $0.00005 | $0.00162 |
Grade A, and why
mailkit-workflow 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 yesterday.
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 — 118 lines — stays where its author put it; the contents beside it link to each section on GitHub.
MailKit Workflow
Purpose
Design macOS MailKit app extensions around Apple Mail’s documented handler model. MailKit supplies an MEExtension entry point and four distinct capabilities: content blocking, message actions, compose-session handling, and message security. This skill owns that Mail-specific behavior and its privacy boundary.
It does not own a mail server, IMAP/SMTP transport, account provisioning, general authentication, generic extension mechanics, or Messages/iMessage collaboration.
When To Use
- Use this skill when a macOS app needs a MailKit extension that blocks remote content, acts on downloaded messages, participates in composition, or secures messages.
- Use this skill when selecting
MEContentBlocker,MEMessageActionHandler,MEComposeSessionHandler, orMEMessageSecurityHandlerand theirMEExtensionCapabilitiesdeclaration. - Use
app-extension-architecture-workflowwhen the extension point or app/extension target architecture is not yet settled. - Use
file-provider-and-finder-sync-workflowfor remote files and Finder behavior, not message attachments or mail synchronization. - Use Messaging Collaboration Skills for Messages/iMessage, communication notifications, VoIP, or Push to Talk behavior.
- Recommend
xcode-build-run-workflow,xcode-testing-workflow, andmacos-distribution-workflowfor their respective execution boundaries.
Single-Path Workflow
- Classify the MailKit capability:
- use a content blocker for declarative remote-content rules shown in Mail
- use message actions for a decision as Mail downloads a message
- use compose sessions for recipient validation, compose-window UI, delivery suitability, or custom headers
- use message security for encryption and digital signatures
- split capabilities only when each one has a concrete Mail behavior and privacy case
- State the documented MailKit behavior relied on:
MEExtensionsupplies handlers for the capabilities declared inMEExtensionCapabilities- enabled content-blocking extensions continue to apply their rules even when a person asks Mail to load remote content
- message action decisions run as Mail downloads messages, not as a retroactive bulk-mail automation contract
- compose-session approval is a delivery gate, not an excuse to silently alter recipient intent
- Set up the target boundary:
- keep the containing macOS app responsible for onboarding, settings, account-independent configuration, and user explanation
- keep the Mail extension responsible for its selected MailKit handlers and short, deterministic decisions
- declare only the chosen capabilities in the extension’s
Info.plist; do not advertise handlers that are not implemented
- Design each handler conservatively:
- content blocker: generate narrow JSON rules, explain their effect, and provide a test corpus for allowed and blocked content
- message action: use explicit, explainable rules and avoid irreversible actions unless the user has made the policy clear
- compose session: validate only what the feature needs, provide focused UI when justified, fail delivery with a concrete user-readable reason, and make custom headers intentional
- message security: identify key material, trust policy, signing/encryption state, user consent, failure recovery, and interoperable message expectations before implementation
- Protect mail data:
- minimize access to message bodies, recipients, headers, attachments, and remote-content identifiers
- do not log raw message content, addresses, tokens, cryptographic material, or full headers
- keep any shared configuration separate from message-derived data; use an App Group only when the app and extension have a documented shared-data need
- Validate in layers:
- verify the macOS target, extension point,
MEExtensionCapabilities, signing, embedding, install, and Mail enablement state - test representative messages and account states in a non-production mailbox
- test content-blocker rules, action decisions, compose allow/deny outcomes and UI, or security encryption/signature success and failure paths as applicable
- prove that disabled, interrupted, malformed, missing-key, and offline conditions produce clear behavior without leaking mail data
- verify the macOS target, extension point,
- Return the chosen handler set, documented behavior, Mail/app data boundary, privacy policy, validation matrix, and next handoff.
What ships with it
4 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.
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.
- yesterday First seen · 118 lines · 48 tokens per session scan A e5c7ca2fd090
mailkit-workflow is a skill published in the GitHub repository gaelic-ghost/socket (7 stars, last pushed 9d ago), licensed Apache-2.0. It adds 48 tokens to every session and 1,617 once invoked, about $0.0002 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 2026-09-03.
Other skills, from other repositories
pipeline
Use when the user wants a feature idea taken end-to-end in one autonomous run — phrases like "run the whole pipeline", "take this feature from idea to finished branch", "brainstorm then build it autonomously", "do everything from idea to merged", "implement all phases without stopping". Triggers when they want…
craft
Use when a product idea is still vague and needs to become a clear definition of what to build — "let's craft an app like X", "help me define what I actually want", "clarify this idea before we plan it". Also use before planning or implementation when requirements, UX, domain behaviour, or technical preferences have…
scenario-planning
Plans under genuine uncertainty — building scenarios, identifying which assumptions are load-bearing, setting early-warning indicators, and stress-testing a plan against futures rather than forecasting one. Use this when a decision depends on something unknowable, when a plan assumes conditions that may not hold…
ai-ml-governance
Governs models and AI systems in production — intended use, evaluation, monitoring, human oversight, documentation, and the decision to deploy or retire. Use this before deploying a model or AI feature, when defining evaluation criteria, when a model's behavior has drifted, when assessing AI risk or regulatory…
ai-research-analyst
Produces executive-level research — market sizing, competitor mapping, trend analysis, and strategic intelligence — grounded in cited sources with the confidence in each claim made explicit. Use this to analyze a market or industry, map competitors, evaluate a market-entry or build-versus-buy decision, produce a…
implement-factory
Factory loop orchestrator for multi-feature or multi-component implementation manifests. Use for high-complexity work with parallel-eligible workstreams and holdout-scenario evaluation.