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 lroolle/ihme-cli --skill skillgit clone --depth 1 https://github.com/lroolle/ihme-cliWrote 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/lroolle/ihme-cli/skill)<a href="https://agentmods.dev/skills/lroolle/ihme-cli/skill"><img src="https://agentmods.dev/badge/skills/lroolle/ihme-cli/skill/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/lroolle/ihme-cli/skill"><img src="https://agentmods.dev/badge/skills/lroolle/ihme-cli/skill.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 | $0.00020 | $0.04142 |
| Opus 5.5 | $0.00008 | $0.01657 |
| Sonnet 5.5 | $0.00004 | $0.00828 |
| Haiku 4.5 | $0.00002 | $0.00414 |
Grade B, and why
ihme scanned grade B with 2 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 1mo 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.
Asks for rootmediumPrivilege escalation
A mod that escalates privileges can change anything on the machine, not only the project.
curl -sL https://github.com/lroolle/ihme-cli/releases/latest/download/ihme_macOS_arm64.tar.gz | tar xz && sudo mv ihme /usr/local/bin/ Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
curl -sL https://github.com/lroolle/ihme-cli/releases/latest/download/ihme_macOS_arm64.tar.gz | tar xz && sudo mv ihme /usr/local/bin/ How it starts
The opening of the file, as written. The whole thing — 377 lines — stays where its author put it; the contents beside it link to each section on GitHub.
ihme — iCloud Hide My Email CLI
Setup
Prefer the local checkout when available, so agents use the newest CLI changes:
# From the root of an ihme-cli checkout
make install
make install builds ihme and copies it to $GOPATH/bin/ihme, or to
~/go/bin/ihme when $GOPATH is unset. Make sure that directory is on PATH.
If the checkout is unavailable, install a release:
# macOS (Apple Silicon)
curl -sL https://github.com/lroolle/ihme-cli/releases/latest/download/ihme_macOS_arm64.tar.gz | tar xz && sudo mv ihme /usr/local/bin/
# macOS (Intel)
curl -sL https://github.com/lroolle/ihme-cli/releases/latest/download/ihme_macOS_x86_64.tar.gz | tar xz && sudo mv ihme /usr/local/bin/
# Linux
curl -sL https://github.com/lroolle/ihme-cli/releases/latest/download/ihme_linux_x86_64.tar.gz | tar xz && sudo mv ihme /usr/local/bin/
# Or via Go
go install github.com/lroolle/ihme-cli/cmd/ihme@latest
First run requires ihme auth login (interactive — Apple ID + 2FA).
Session lookup uses IHME_SESSION_PATH when set; otherwise it reads
$XDG_CONFIG_HOME/ihme/session.json, falling back to ~/.config/ihme/session.json.
ihme auth status --json first reads the local session file, then checks whether
that session can currently access iCloud. It includes Apple's /validate payload
as rawResponse. Use ihme auth status --local --json only when you want the
local file/timestamp check without a network request.
--verbose only logs method, URL, status, and size.
Current /validate success responses are account-info payloads with dsInfo
and webservices; they may omit a success boolean.
JSON response shapes
list --json → {"addresses":[{anonymousId,label,hme,isActive,createTimestamp,note,...}],"count":N,"hints":{...}}
view --json → {"result":{anonymousId,label,hme,forwardToEmail,isActive,...},"hints":{...}}
new --json → {"candidates":["[email protected]",...],"label":"...","preferences":["..."],"hint":"ihme new <label> --address <addr>"}
(preferences: the user's standing preferences, present only when any are recorded)
new -y --json → {anonymousId,label,hme,isActive,...}
forward --json → {"forwardTo":"...","available":[...],"hint":"ihme forward set <email>"}
auth status → {"loggedIn":true,"appleId":"...","expired":false,"canAccessICloud":true,"rawResponse":{...},...}
deactivate → {"status":"deactivated","hme":"...","id":"...","hints":{...}}
reactivate → {"status":"reactivated","hme":"...","id":"...","hint":"..."}
What ships with it
2 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.
- 1mo ago Changed · +23 lines febe7d09d144
- 1mo ago First seen · 354 lines · 20 tokens per session scan B bcf0d05928ad
ihme is a skill published in the GitHub repository lroolle/ihme-cli (3 stars, last pushed 16d ago), licensed MIT. It adds 20 tokens to every session and 4,142 once invoked, about $0.0001 per session on Opus 5.5. A static security scan graded it B with 2 findings (asks for root, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
deck-obsidian-claude
A visual design template for presentation slides with a dark GitHub-like background, colored lighting, gradient headings, and code-style formatting.
web-proto-soft
A web prototype style inspired by Apple's soft product interfaces, using cream or silver surfaces, rounded cards, layered edges, and subtle motion.
apple-hig
Apple Human Interface Guidelines reference, updated for iPhone Duo and OS 27. Provides authoritative platform-specific design rules, component specifications, exact measurements, and interaction patterns for iOS, iPadOS, macOS, tvOS, visionOS, and watchOS. Use when designing, reviewing, auditing, or fixing any Apple…
site-craft
A design method for building static websites, meaning sites whose pages are generated from code rather than managed by a server database. It covers how to choose a visual style, plan page structure, and apply typography, colors, and images.
stage-setup
A preparation guide for starting and managing a role-playing session (RP), including characters, setting, rules, state, and writing style. It also gives steps for changing these during an ongoing session.
docx-craft
A set of rules for creating editable Microsoft Word documents (.docx), including their layout, styles, numbering, tables, and language-specific typography.