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.
git clone --depth 1 https://github.com/migsilva89/imarkWrote 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/plugins/migsilva89/imark/plugin)<a href="https://agentmods.dev/plugins/migsilva89/imark/plugin"><img src="https://agentmods.dev/badge/plugins/migsilva89/imark/plugin/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/plugins/migsilva89/imark/plugin"><img src="https://agentmods.dev/badge/plugins/migsilva89/imark/plugin.svg" alt="Reviewed on agentmods" width="80" height="20"></a>Grade A, and why
imark 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.
What it actually says
{
"name": "imark",
"description": "Review plans, diffs and documents in Imark. The agent writes markdown, you comment on it in the app, and your notes come back — through the file, with no server in between.",
"version": "0.6.6",
"author": {
"name": "migsilva89"
},
"repository": "https://github.com/migsilva89/imark",
"keywords": ["markdown", "review", "annotations", "macos", "ExitPlanMode", "offline"]
}
What it installs
The manifest is a name and a version. 1 skill, 2 commands, 1 hook travel with it, and installing the plugin installs all of them — 99 tokens a session between them. Each is measured on its own page, and each can be installed alone.
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 Changed 7e3cc254a15d
- 9d ago Changed 206724956442
- 11d ago Changed d05769e947f4
- 16d ago Changed 4a8223780ecf
- 25d ago Changed 0d554a2dbc62
- 26d ago Changed 3078e988466c
- 1mo ago Changed 82bcfcf0f0e8
- 1mo ago Changed 19cedd09066a
- 1mo ago First seen · 11 lines scan A 50207a0d19ef
imark is a plugin published in the GitHub repository migsilva89/imark (100 stars, last pushed yesterday), licensed MIT. Its token cost is not measured: this kind of file is read by the harness, not the model. 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 2026-08-30.
Other plugins, from other repositories
homeclaw
HomeKit smart home control via MCP - control lights, locks, thermostats, and scenes.
swift-auto-gui
Control macOS GUI applications and Chromium pages using the sagui CLI.
onebrain
OneBrain — Your AI Thinking Partner.
plant-defects
Deliberately break code to prove a test can see it: plant the defect an instrument claims to catch, confirm it goes red, and record it so it regresses.
review-colleague-pr
Review a colleague's pull request carefully and considerately from a checkout of its branch, and report a brief, read-only assessment in chat: requirements, direction, blockers, follow-ups, and questions for the author.
media
System-wide now-playing control for macOS — see and control whatever is playing (Spotify, Apple Music, browsers) right from Claude Code. Zero dependencies, no OAuth, no app lock-in.