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 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/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/konradmichalik/md-annotator/annotate-md"><img src="https://agentmods.dev/badge/skills/konradmichalik/md-annotator/annotate-md.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 | $0.00028 | $0.00576 |
| Opus 5.5 | $0.00011 | $0.00230 |
| Sonnet 5.5 | $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 2mo 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.
- 2mo 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 (6 stars, last pushed 2mo ago), licensed MIT. It adds 28 tokens to every session and 576 once invoked, about $0.0001 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 2026-08-31.
annotate-md compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| annotate-mdkonradmichalik/md-annotator | Skill | 6 | 2mo ago | MIT | A | 28 | Claude Code |
| firecrawl-cliHiAi-gg/hiai-opencode | Skill | 18 | 20d ago | none | A | 198 | Claude Code, Codex |
| full-page-screenshotHiAi-gg/hiai-opencode | Skill | 18 | 20d ago | none | A | 32 | Claude Code, Codex |
| agent-browserHiAi-gg/hiai-opencode | Skill | 18 | 20d ago | none | C | 81 | Claude Code, Codex |
| browser-testing-with-devtoolsHiAi-gg/hiai-opencode | Skill | 18 | 20d ago | none | D | 57 | Claude Code, Codex |
| plannotator-inboxbacknotprop/plannotator | Skill | 9.9k | yesterday | Apache-2.0 | A | 39 | Claude Code |
| southwestborski/travel-hacking-toolkit | Skill | 895 | yesterday | MIT | A | 40 | Claude Code |