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/migsilva89/imark/imark-commentsnpx skills add migsilva89/imark --skill imark-commentsgit 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/skills/migsilva89/imark/imark-comments)<a href="https://agentmods.dev/skills/migsilva89/imark/imark-comments"><img src="https://agentmods.dev/badge/skills/migsilva89/imark/imark-comments.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 | $0.00073 | $0.00867 |
| Opus 5 | $0.00036 | $0.00434 |
| Sonnet 5 | $0.00015 | $0.00173 |
| Haiku 4.5 | $0.00007 | $0.00087 |
Grade A, and why
imark-comments scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 5d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 80 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Imark comments
Imark is a macOS markdown reader that stores a reader's comments inside the
document, as HTML comments. Every renderer ignores them, grep finds them,
and they travel with the file. If you are looking at a markdown file with blocks
like this, that is what they are:
Rows move in batches of 500, and the deadline is generous but workable.
<!-- imark quote="generous but workable" by="alex" at="2026-08-02T14:31Z"
Workable with which team? This needs a number, not an adjective.
-->
Reading them
Do not hand-roll a parser:
node "${CLAUDE_PLUGIN_ROOT}/scripts/imark.mjs" notes <file.md>
By default this shows only the notes still asking for something. A note carrying
resolved= has been dealt with — it stays in the file as the record of what was
asked, but it is history, not work. The header says how many were left out. Add
--all when the history is what you want.
Add --json for structured output; it obeys the same rule. Each note comes back
with what it says, the quote it is attached to, who wrote it and when, the
heading it falls under, and the block above it.
The format
| Attribute | Meaning |
|---|---|
quote= |
the exact words the note is attached to. Required |
by= |
who wrote it. Omitted when there is no name |
at= |
ISO 8601 timestamp |
nth= |
which occurrence of the quote, when the same words appear twice. Only written when it is above 1 |
color= |
one of five names. Omitted for the default |
resolved= |
ISO date stamped by whoever acted on the note. The app fades it; review rounds stop repeating it |
The body is every line between the opening line and a line containing only
-->. Inside it, & is a literal & and --> is a literal --> —
escaped so the note cannot close its own comment early. In attributes, "
is a quote character.
Acting on them
A note is a request, not a remark. Answer every one, say what you changed for each, and refer to them by their quote — “on ‘generoso mas exequível’” — which is how the user sees them in the app.
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.
- 5d ago First seen · 80 lines · 73 tokens per session scan A aba6977f2c36
imark-comments is a skill published in the GitHub repository migsilva89/imark (50 stars, last pushed 7d ago), licensed MIT. It adds 73 tokens to every session and 867 once invoked, about $0.0004 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 2026-08-30.
Other skills, from other repositories
inspect-appkit-ui
Inspect and review a live native macOS AppKit interface in Codex Browser. Use when the user asks Codex to preview a running AppKit app, click or identify an NSView, map a visual element to its class and hierarchy, diagnose layout or accessibility issues, or prepare precise visual feedback for Codex.
peekaboo
Use Peekaboo for macOS desktop automation, screenshots, visual UI maps, native accessibility inspection, app/window/menu/dialog control, native app and browser chrome control, browser-page MCP tooling, MCP diagnostics, and Peekaboo repo validation. Use when Codex needs current macOS UI state, direct desktop control…
release-peekaboo
Peekaboo release: notarization, npm/GitHub release, appcast, verify, closeout.
chat-complex-documents
Chat with and search your complex documents — ask questions, extract tables and fields, and get answers grounded in the source. Connects the hosted Unstructured Transform MCP server to parse, structure, and enrich PDFs, Word/Excel/PowerPoint, images, scanned files, emails, and 60+ other formats into clean, AI-ready…
processing-markdown
Processes Markdown files using mq, a jq-like query language for Markdown. Use when the user mentions Markdown processing, content extraction, document transformation, or mq queries.
scarf-template-author
Scaffold a new Scarf project OR enrich an existing one after a Scarf "Upgrade Project" — dashboard, optional configuration schema, optional cron job, AGENTS.md, and (via the scarf-miniapp-author skill) a starter mini-app — from a short conversational interview. Output is immediately usable locally and cleanly…