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/migsilva89/imark/imark-notesgit clone --depth 1 https://github.com/migsilva89/imarkWhat 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 | $0.00010 | $0.00303 |
| Opus 5 | $0.00005 | $0.00151 |
| Sonnet 5 | $0.00002 | $0.00061 |
| Haiku 4.5 | $0.00001 | $0.00030 |
Grade A, and why
imark-notes scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
What it actually says
Read the notes the user left inside a markdown file with Imark.
node "${CLAUDE_PLUGIN_ROOT}/scripts/imark.mjs" notes $ARGUMENTS
This waits for nothing and opens nothing — it is for when the user has already commented and says "read my comments".
What comes back is the notes still asking for something. One that was already
acted on carries resolved= and stays in the document as the record of what was
asked, but it is history, not work — the header says how many were held back,
and --all produces them for when the history is what the user wants.
Each note carries the words it is attached to, the section it fell under, and the block above it. That is usually enough to know what it is about without opening the file; open it anyway if a note needs the text around it.
A note marked orphan has lost its anchor: the quoted text is no longer in the document. It still counts as a comment, but do not assume the line above it is what it refers to.
Treat every note as a request, answer all of them, and refer to each by the words it is attached to — on “X” — 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.
- 2d ago First seen · 31 lines · 10 tokens per session scan A fff991c12c65
imark-notes is a command published in the GitHub repository migsilva89/imark (50 stars, last pushed 4d ago), licensed MIT. It adds 10 tokens to every session and 303 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 2026-08-30.
Other commands, from other repositories
agent
Drive Peekaboo’s autonomous agent via peekaboo agent.
bridge
Diagnose Bridge hosts and verify signed operation receipt bundles.
capture
Capture live screens/windows or ingest video; adaptive frames + contact sheet.
click
Target UI elements via peekaboo click.
see
Capture annotated UI maps with peekaboo see.
app
Control macOS apps via peekaboo app.