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 skills add coltonbearden/carrel --skill mail-archivegit clone --depth 1 https://github.com/coltonbearden/carrelWrote 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/skills/coltonbearden/carrel/mail-archive)<a href="https://agentmods.dev/skills/coltonbearden/carrel/mail-archive"><img src="https://agentmods.dev/badge/skills/coltonbearden/carrel/mail-archive/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/coltonbearden/carrel/mail-archive"><img src="https://agentmods.dev/badge/skills/coltonbearden/carrel/mail-archive.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00088 | $0.00790 |
| Opus 5.5 | $0.00035 | $0.00316 |
| Sonnet 5.5 | $0.00018 | $0.00158 |
| Haiku 4.5 | $0.00009 | $0.00079 |
Grade A, and why
mail-archive 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 1mo 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.
How it starts
The opening of the file, as written. The whole thing — 53 lines — stays where its author put it; the contents beside it link to each section on GitHub.
From a mail export to a searchable archive
.eml and .mbox are first-class carrel file types: inspect, convert, index/search, pack, refs and the carrel-guard Read hook all read them with the standard library — no binary needed. Run carrel mail --help and carrel doctor before composing flags; only mail pst needs an external tool (readpst); its exit-3 message carries the install hint for the platform you are on — relay that rather than guessing a package manager.
1. Get one message per file (optional but recommended)
carrel mail split archive.mbox --out-dir ~/mail/2026 --json # {n}_{date}_{subject}.eml per message
carrel mail pst export.pst --out-dir ~/mail/outlook # Outlook → one .eml per message, folders kept
One file per message makes every later step addressable: a search hit, a tag, a note and a reference all point at a single .eml.
2. Index and search
carrel --root ~/mail index # eml/mbox are indexed like any document
carrel --root ~/mail search 'invoice AND overdue' --type eml
carrel --root ~/mail pack ~/mail/2026 --query 'renewal' --top 10 -o ctx.md
--type eml narrows to messages; the indexed text is headers + body + attachment names, so a search for an attachment's file name finds the message that carried it.
3. Threads and attachments
carrel mail threads ~/mail/2026 --json # Message-ID / In-Reply-To / References → conversations
carrel mail attachments ~/mail/2026/*.eml --out-dir ~/mail/attachments --json
Attachment records carry sha256, so carrel dedupe ~/mail/attachments finds the copies every reply re-attached.
4. Cross-reference with the rest of the desk
carrel --root ~/desk refs ~/desk --tag # invoice / PO / IBAN numbers → ref:<kind>:<value> tags
carrel --root ~/desk tag find ref:invoice:inv-2026-0042 # the invoice PDF, the remittance email, the bank export
carrel --root ~/desk refs ~/desk --link # the same grouping without writing tags
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.
- 1mo ago Changed scan B → A 07c43629a823
- 1mo ago First seen · 53 lines · 88 tokens per session scan B a5179ed4b571
mail-archive is a skill published in the GitHub repository coltonbearden/carrel (2 stars, last pushed 3d ago), licensed MIT. It adds 88 tokens to every session and 790 once invoked, about $0.0004 per session on Opus 5.5. 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 2026-09-11.
Other skills, from other repositories
ade
Parse documents and extract schema-shaped data with the ADE (Agentic Document Extraction) v2 APIs through the ade CLI. A local job-item store makes every run idempotent, resumable, and citable — repeat runs are free, interrupted runs resume, and every answer can cite element ids with visual evidence.
document-processing
Use when the deliverable is a document's bytes or its literal content — text/tables out of PDFs, AcroForm fill and flatten, page merge/split, PDF/DOCX from templates, OCR of image-only scans. NOT schema-typed fields pulled from text (that is structured-extraction), NOT signature routing (e-signature) or spreadsheet…
officecli
Create, analyze, proofread, and modify Office documents (.docx, .xlsx, .pptx) using the officecli CLI tool. Use when the user wants to create, inspect, check formatting, find issues, add charts, or modify Office documents.
paddleocr-doc-parsing
A document-parsing tool configuration for extracting structured Markdown or JSON from complex PDFs and document images, including tables, formulas, charts, and multi-column pages.
gws-sheets
Google Sheets: Read and write spreadsheets.
recipe-create-presentation
Create a new Google Slides presentation and add initial slides.