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 datatorag/mcp-gateway --skill outbound-copygit clone --depth 1 https://github.com/datatorag/mcp-gatewayWrote 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/datatorag/mcp-gateway/outbound-copy)<a href="https://agentmods.dev/skills/datatorag/mcp-gateway/outbound-copy"><img src="https://agentmods.dev/badge/skills/datatorag/mcp-gateway/outbound-copy.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 5.1 | $0.00058 | $0.02187 |
| Opus 5 | $0.00029 | $0.01094 |
| Sonnet 5 | $0.00012 | $0.00437 |
| Haiku 4.5 | $0.00006 | $0.00219 |
Grade A, and why
outbound-copy 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 7d 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 — 198 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Outbound Copy
Words that leave the building. Not blog posts and not docs, which have their
own skills (blog-writing, site-content) — this is the copy nobody thinks
of as copy: the confirmation email, the welcome email, the button label, the
error message a stranger reads at the worst moment of their day.
It gets less review than a blog post and reaches people who have not decided to trust us yet.
Load manuel-voice before drafting
Not after, not "if it sounds off". This copy carries a person's name and the company's, and the default drafting register is the wrong one every time.
The failure it prevents is specific: a draft can be fluent, well-structured and still read as generic template copy at a glance. The usual tell is em-dashes, which is why the next rule is a hard one.
Two rules that are not negotiable
Zero em-dashes. — and —. This is the single strongest AI marker
in English prose and Manuel does not use them; he comma-chains. Where copy
lives in code, assert it in a test rather than remembering it. In markdown,
grep before shipping.
Never claim a capability we do not ship. The axis is create-new versus change-existing, never "they read, we write" and never a breadth claim. If copy mentions CASA it uses the canonical string exactly:
Google-verified app · CASA Tier 2 security approved (June 2026)
CASA is a Google-specific assessment. Copy must never let it read as SOC 2, ISO 27001, or a general audit. Approved 2026-06-29, recert ~June 2027 — the date is in the string because it expires.
Register: customer email is not Slack
manuel-voice has two registers and the wrong one is a real trap. Customer
email keeps his casual sentence structure (comma-chains, hedges, short,
no ceremony) but uses standard capitalization — sentence starts, "I",
people's names, "DataToRAG". The Slack lowercase drift does NOT carry over.
Subject lines are the exception and stay lowercase.
Shape that works, from his own rewrite:
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.
- 7d ago First seen · 198 lines · 58 tokens per session scan A f6cc1e24a041
outbound-copy is a skill published in the GitHub repository datatorag/mcp-gateway (4 stars, last pushed 3d ago), licensed MIT. It adds 58 tokens to every session and 2,187 once invoked, about $0.0003 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…
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…
chronicle
Analyze Copilot session history for standup reports, usage tips, session search, and session reindexing. Use when the user asks for a standup, daily summary, usage tips, workflow recommendations, wants to search or find past sessions by keyword/file/PR, wants to reindex their session store, or asks about deleting…
babysit-pr
Babysit a GitHub pull request after creation by continuously polling review comments, CI checks/workflow runs, and mergeability state until the PR is merged/closed or user help is required. Diagnose failures, retry likely flaky failures up to 3 times, auto-fix/push branch-related issues when appropriate, and keep…