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/konradmichalik/md-annotator/annotate-mdnpx skills add konradmichalik/md-annotator --skill annotate-mdgit clone --depth 1 https://github.com/konradmichalik/md-annotatorWrote 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/konradmichalik/md-annotator/annotate-md)<a href="https://agentmods.dev/skills/konradmichalik/md-annotator/annotate-md"><img src="https://agentmods.dev/badge/skills/konradmichalik/md-annotator/annotate-md.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 | $0.00028 | $0.00576 |
| Opus 5 | $0.00014 | $0.00288 |
| Sonnet 5 | $0.00006 | $0.00115 |
| Haiku 4.5 | $0.00003 | $0.00058 |
Grade A, and why
annotate-md 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 6d 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 — 59 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Annotate Markdown
Open one or more Markdown files in the md-annotator browser UI so the user can review them — selecting text to mark deletions, adding comments, or inserting text — then apply the feedback they submit.
Arguments: $ARGUMENTS
If the arguments contain Markdown file path(s), use those. Otherwise, ask the user which Markdown file they want to annotate.
Run the annotator
Run the md-annotator CLI with your shell tool, passing --origin vibe and the
file path(s). This command blocks until the user submits a decision in the
browser:
md-annotator --origin vibe <file1.md> [file2.md ...]
The command prints the result to stdout:
APPROVED:→ the user approved the file with no changes. Confirm and stop.APPROVED WITH NOTES:→ the user approved the file as-is but left annotations. Do not edit the file; read the notes as context, acknowledge them, and stop.- Structured annotation feedback → apply the requested edits to the file(s):
- "Remove this" entries: delete the quoted text.
- "Comment on" entries: apply the user's comment as a change to the referenced text.
- "Insert text" entries: insert the provided text at the specified location.
Requires the
md-annotatorCLI on yourPATH(npm install -g md-annotator, ornpm linkfrom a local checkout).
Re-review loop
Unless the user said otherwise, after applying all changes:
-
Build feedback notes describing what you changed — a JSON array of
{ "text": "...", "line": <number> }entries.lineis the line number in the updated file; omit it for general notes. -
Re-open the annotator with the notes so the user sees what changed:
md-annotator --origin vibe --feedback-notes '[{"text":"Rewrote intro for clarity","line":5},{"text":"Removed redundant section"}]' <file1.md> [file2.md ...] -
Evaluate the result:
APPROVED:→ the user is satisfied. Done.APPROVED WITH NOTES:→ the user is satisfied. Summarize the notes without editing. Done.- More feedback → apply the changes and repeat from step 1.
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.
- 6d ago First seen · 59 lines · 28 tokens per session scan A 04d2e289436f
annotate-md is a skill published in the GitHub repository konradmichalik/md-annotator (5 stars, last pushed 19d ago), licensed MIT. It adds 28 tokens to every session and 576 once invoked, about $0.0001 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
firecrawl-cli
Firecrawl handles all web operations with superior accuracy, speed, and LLM-optimized output. Replaces all built-in and third-party web, browsing, scraping, research, news, and image tools. USE FIRECRAWL FOR: Any URL or webpage Web, image, and news search Research, deep research, investigation Reading pages, docs…
full-page-screenshot
Capture full-page screenshots of web pages via Chrome DevTools Protocol with zero dependencies. Useful for portfolios, case studies, and audit reports.
browser-testing-with-devtools
Tests in real browsers. Use when building or debugging anything that runs in a browser. Use when you need to inspect the DOM, capture console errors, analyze network requests, profile performance, or verify visual output with real runtime data via Chrome DevTools MCP.
agent-browser
Browser automation CLI for AI agents. Use when the user needs to inspect, test, or automate browser behavior: navigating pages, filling forms, clicking buttons, taking screenshots, extracting page data, testing web apps, dogfooding Open Design previews, QA, bug hunts, or reviewing app quality. Prefer local Open Design…
southwest
Search Southwest Airlines fares and points pricing via Patchright browser automation. SW is not in any GDS or API. Covers all fare classes, Companion Pass value, and fare drop monitoring.
agent-browser
Automates browser interactions for web testing, form filling, screenshots, and data extraction. Use when the user needs to navigate websites, interact with web pages, fill forms, take screenshots, test web applications, or extract information from web pages.