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 mindbox-cloud/agent-skills --skill email-opsgit clone --depth 1 https://github.com/mindbox-cloud/agent-skillsWrote 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/mindbox-cloud/agent-skills/email-ops)<a href="https://agentmods.dev/skills/mindbox-cloud/agent-skills/email-ops"><img src="https://agentmods.dev/badge/skills/mindbox-cloud/agent-skills/email-ops/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/mindbox-cloud/agent-skills/email-ops"><img src="https://agentmods.dev/badge/skills/mindbox-cloud/agent-skills/email-ops.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 | $0.00078 | $0.12044 |
| Opus 5.5 | $0.00031 | $0.04818 |
| Sonnet 5.5 | $0.00016 | $0.02409 |
| Haiku 4.5 | $0.00008 | $0.01204 |
Grade A, and why
email-ops 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 11d 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 — 766 lines — stays where its author put it; the contents beside it link to each section on GitHub.
email-ops — Mindbox operations for emails
The project-aware executor of all integration actions. The JSX generator is
email; this skill does not invent email content and does not change JSX
silently. Return a preview error to the generator verbatim — it is the editor's text,
with line numbers; do not rephrase or classify it.
Communicating with the user
JSX, internal IDs and rowVersion are internal execution details. In normal conversation with the
user say "email", "email layout", "content", "preview" and "saving",
not JSX, mailingInternalId, variantInternalId, formatInternalId, rowVersion
or visualTemplateRowVersion. Do not replace the terms Active/Draft: if they are needed to
pick a version precisely, use exactly Active/Draft. Do not show raw JSX or GUIDs
unless the user explicitly asked for code, export, markup or technical details.
Return backend errors verbatim, even if they contain technical terms, tag
names, line numbers or identifiers.
Skill feedback via MCP feedback
The MCP feedback of the current Mindbox/email MCP server is an optional channel for passing
confirmed feedback about the skill's work to the developers. Use one of two entry points:
- Agent's initiative. If you have confirmed that you see a critical problem that cannot be solved with the current skill — a mismatch between the instructions or references and the actual backend behavior, repeated errors of the same type, a blocked safe workflow — offer the user to send feedback to the developers. Do not send it without explicit consent.
- User's initiative. If the user asks how to pass a message/feedback to the developers, answer: "This is available. What message would you like to send?" Then format their words using the format below.
The sending protocol is mandatory in both cases:
- First compose the exact text of the message. The first line is the marker
[skill-feedback:v1], followed by the fieldsskill=<email|email-ops>(the skill whose instructions the problem is about),skillVersion=<metadata.version of that skill's SKILL.md>,source=user-report|agent-observation,problemandcontext.problemis the essence: what gets in the way, what went wrong. Foruser-report, write the user's exact words intoproblem, and addcontextyourself. Foragent-observation, you write both fields.context— briefly: input data and requests, how the current situation came about, verbatim backend error texts, reproduction facts (run date, a throwaway campaign). Addarea=<layout|save|preview|gallery|personalization|other>only if the area is obvious. - Always first show the user the entire text to be sent and ask for explicit permission, for example: "Send this feedback to the developers?"
- Call
feedbackspecifically in the current Mindbox/email MCP server through which this skill's operations are performed, and only after unambiguous confirmation. If the user asks to change the text, show the corrected version again and get confirmation again. - Do not send feedback covertly, do not assume consent and do not silently attach it to another operation. Do not include email content, personal data, secrets, signed URLs or tokens.
What ships with it
3 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.
- 11d ago First seen · 766 lines · 78 tokens per session scan A 82febb04cdd9
email-ops is a skill published in the GitHub repository mindbox-cloud/agent-skills (6 stars, last pushed 9d ago), licensed MIT. It adds 78 tokens to every session and 12,044 once invoked, about $0.0003 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 2026-10-03.
Other skills, from other repositories
prove-the-gates
Audit the repository's own checks — for each test, gate and CI script, establish what it guards, whether anything still runs it, and whether it actually fails when you break what it protects. Use when the user says "prove the gates", "are our tests real", "audit the test suite", "which checks are fake", "תוכיח את…
implementation-notes
Maintain an IMPLEMENTATIONNOTES.md decision log during any multi-step implementation session. Use this in EVERY session that involves writing or modifying code across more than one file, or any session expected to run longer than a few tool calls. Records decisions, deviations from plan, and open questions so nothing…
full-audit
Audit a whole repository in one pass — dispatch every applicable audit lane in parallel, prove the repo's own gates fail when they should, and return one evidence-backed report ranked by severity. Use when the user says "full audit", "audit this repo", "check the whole codebase", "תעשה אודיט מלא", "אודיט לריפו"…
fable-method
The routing logic of the Fable Method - decides which unknowns-discovery technique (blindspot-pass, interview-me, prototype-first, implementation-notes, merge-quiz) applies to the current task, and which to skip. Consult this at the START of any non-trivial task, or when the user says "fable", "the method", "how…
blindspot-pass
Run a blindspot scan to surface the user's unknown unknowns BEFORE implementing a task. Use this whenever the user starts a non-trivial task in a domain they say (or appear) to be unfamiliar with, whenever they say "blindspot", "unknowns", "what am I missing", "before we start", or when a request is vague enough that…
convergence-guard
Stop-loss discipline for implementation sessions - detect fix-loops and runaway token burn, and stop to replan instead of patching. Consult during any debugging or implementation session, especially when tests keep failing, the same file keeps being edited, or the user mentions stoploss, token budget, fix loops, or…