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.
git clone --depth 1 https://github.com/BigCactusLabs/dead-letterWrote 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/bigcactuslabs/dead-letter/cabinet)<a href="https://agentmods.dev/commands/bigcactuslabs/dead-letter/cabinet"><img src="https://agentmods.dev/badge/commands/bigcactuslabs/dead-letter/cabinet.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 5.1 | $0.00025 | $0.00567 |
| Opus 5 | $0.00013 | $0.00283 |
| Sonnet 5 | $0.00005 | $0.00113 |
| Haiku 4.5 | $0.00003 | $0.00057 |
Grade A, and why
cabinet 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 8d 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.
The source is not reproduced here
A licence we could not identify
The repository carries a LICENSE file, but it is custom or dual enough that GitHub cannot name it and neither can this catalogue. Unknown terms are not permission, so the body is not copied here. Read the licence at the source and decide for yourself.
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.
- 8d ago First seen · 51 lines · 25 tokens per session scan A bacf00ad7b0f
cabinet is a command published in the GitHub repository BigCactusLabs/dead-letter (7 stars, last pushed yesterday), with no licence file. It adds 25 tokens to every session and 567 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
done
Finish a task - document, create PR or merge, close.
archive-mail-rebuild-threads
A command that rebuilds the index connecting archived email files to their conversation threads. It reads the metadata at the top of each Markdown file and recreates the thread index file.
ground
Verify the Evidence Anchors in a document (defaults to the newest plan file).
edit
Edit files non-destructively with the carrel CLI — merge/split/rotate/decrypt PDFs, resize/crop/strip images, find-and-replace in text, set/delete JSON values by dotted path.
inspect
Show rich metadata for a local file (pdf, image, json, csv, xml, html, md, txt, docx, odt, epub, rtf, xlsx) using the carrel CLI.
redact
Redact sensitive strings (emails, phones, SSNs, IPs, card numbers, or custom regexes) from a text file or PDF using the carrel CLI — PDFs are truly rasterized, not just overlaid.