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 commands/konradmichalik/md-annotator/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/commands/konradmichalik/md-annotator/md)<a href="https://agentmods.dev/commands/konradmichalik/md-annotator/md"><img src="https://agentmods.dev/badge/commands/konradmichalik/md-annotator/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 | $0.00012 | $0.00430 |
| Opus 5 | $0.00006 | $0.00215 |
| Sonnet 5 | $0.00002 | $0.00086 |
| Haiku 4.5 | $0.00001 | $0.00043 |
Grade A, and why
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 4d 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.
What it actually says
Markdown Annotations
!md-annotator --origin claude-code $ARGUMENTS
Your task
Address the annotation feedback above. The user has reviewed the markdown file in the browser UI and provided specific annotations:
- "Remove this" entries: Delete the quoted text from the file
- "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
If the output shows APPROVED:, the user approved the file with no changes needed — confirm and stop.
If the output shows APPROVED WITH NOTES:, the user approved the file as-is but left annotations. Do not edit the file. Read the notes, acknowledge them, and stop — they are context for your understanding, not change requests.
Re-review loop
After applying all changes:
-
Build feedback notes JSON describing what you changed. Each note has a
textfield and an optionallinefield (line number in the updated file). Omitlinefor general notes. -
Re-open the annotator with inline notes:
md-annotator --origin claude-code --feedback-notes '<JSON_ARRAY>' <file1.md> [file2.md ...]Example:
md-annotator --origin claude-code --feedback-notes '[{"text":"Rewrote intro for clarity","line":5},{"text":"Removed redundant section"}]' README.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 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.
- 4d ago First seen · 42 lines · 12 tokens per session scan A 266309ebc399
md is a command published in the GitHub repository konradmichalik/md-annotator (5 stars, last pushed 17d ago), licensed MIT. It adds 12 tokens to every session and 430 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 commands, from other repositories
annotate-last
The /plannotator-last slash command for annotating the agent's most recent message.
live-canvas
Conduct design interviews, generate UI variations, and collect live click-to-annotate feedback that streams into the session so edits land without leaving the browser. Use when the user wants rapid iterative UI refinement, not just batched feedback.
fd-task
Define a task end to end — auto-init the workspace, research the codebase, confirm requirements, and save task.md + architecture.md + affect.md + plan.md.
fd-done
Close the task — summarize built vs required, then commit and push on confirmation.
fd-execute
Implement plan.md with the TDD pipeline — parallel worktree guard from affect.md, wave-based execution, checkpoint after each wave.
fd-review
Two-lens review of the task artifacts before execution — CEO review challenges scope and premise, eng review checks architecture, edge cases, and blast radius.