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/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/commands/konradmichalik/md-annotator/annotate-md)<a href="https://agentmods.dev/commands/konradmichalik/md-annotator/annotate-md"><img src="https://agentmods.dev/badge/commands/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 | $0.00008 | $0.00262 |
| Opus 5 | $0.00004 | $0.00131 |
| Sonnet 5 | $0.00002 | $0.00052 |
| Haiku 4.5 | $0.00001 | $0.00026 |
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 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
Use the annotate_markdown tool to open the specified file for interactive review.
Arguments: $ARGUMENTS
If arguments contain file path(s), use those files. Otherwise, ask the user which markdown file they want to annotate.
The user can:
- Select text and mark it for deletion
- Select text and add comments
- Insert text at specific locations
- Approve the file with no changes
After the user submits their decision:
- If approved: No action needed
- If feedback provided: Apply the requested changes to the file
Re-review loop
Unless the user specified --no-review, after applying changes:
-
Create feedback notes describing what you changed:
- Use
feedbackNotesparameter with[{text, line?}]entries - Include
linefor location-specific notes (use line numbers from the updated file) - Omit
linefor general notes
- Use
-
Re-open the annotator with notes:
annotate_markdown({ filePath: "...", feedbackNotes: [{text: "Changed X", line: 5}] }) -
If approved → done. If more feedback → apply and repeat.
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 · 37 lines · 8 tokens per session scan A f1074ee8707e
annotate:md is a command published in the GitHub repository konradmichalik/md-annotator (5 stars, last pushed 17d ago), licensed MIT. It adds 8 tokens to every session and 262 once invoked, about $0.0000 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-execute
Implement plan.md with the TDD pipeline — parallel worktree guard from affect.md, wave-based execution, checkpoint after each wave.
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-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.