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/masterleopold/book-capture/booksgit clone --depth 1 https://github.com/masterleopold/book-captureWrote 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/masterleopold/book-capture/books)<a href="https://agentmods.dev/commands/masterleopold/book-capture/books"><img src="https://agentmods.dev/badge/commands/masterleopold/book-capture/books.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 | $0.00013 | $0.00231 |
| Opus 5 | $0.00006 | $0.00115 |
| Sonnet 5 | $0.00003 | $0.00046 |
| Haiku 4.5 | $0.00001 | $0.00023 |
Grade A, and why
books 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
Apple Books Capture
Source is pre-selected: books (Apple Books app).
Follow the full pipeline in ${CLAUDE_PLUGIN_ROOT}/commands/capture.md with source = books. Skip the platform selection step.
Apple Books-specific notes:
- Uses left/right arrow keys for page navigation (left = next for RTL/vertical, right = next for LTR/horizontal)
- Automatically detects Books app window via CGWindowList
- Script sends Escape to dismiss any dialogs first
- Book Title is used as the folder ID (sanitized)
- Remind user: open the book in Apple Books to the first page, ensure Accessibility permission
node "${CLAUDE_PLUGIN_ROOT}/scripts/capture-books-app.mjs" "<BookTitle>" [--horizontal] --output-dir "<OUTPUT_DIR>"
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 · 23 lines · 13 tokens per session scan A 42dd5986a375
books is a command published in the GitHub repository masterleopold/book-capture (10 stars, last pushed 1mo ago), licensed MIT. It adds 13 tokens to every session and 231 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
brand-generate
Generate an on-brand document from a saved Brand Profile.
done
Finish a task - document, create PR or merge, close.
notebook-audit
Adversarial consistency audit over the notebook knowledge base — finds contradictions in a document corpus: the same category with conflicting amounts, the same person under two names, the same reference with different values, coverage gaps (unprocessed docs), unparseable amounts. Pure SQL, read-only. Writes…
notebook-status
Check the progress of a /agy:notebook sweep (for long document sets run with --background). Reports % complete, done/pending/failed counts, elapsed time and a rough ETA, and which documents are still pending — so you can resume. Read-only, no agy.
story-add
Add a new canonical STAR story to the behavioral story bank. Two modes — cold (you describe an experience from scratch) and CV-grounded (you point at a PDF resume; Claude reads it, suggests candidates, probes the one you pick).
paper-trail-decide
Inspect a single reference in detail (identity, PDF status, acquisition history with verdicts, citation context in vault, state transitions) and decide its fate. Offers actionable decisions based on the ref's current state.