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 TaewoooPark/MagLab --skill cover-lettergit clone --depth 1 https://github.com/TaewoooPark/MagLabWrote 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/taewooopark/maglab/cover-letter)<a href="https://agentmods.dev/skills/taewooopark/maglab/cover-letter"><img src="https://agentmods.dev/badge/skills/taewooopark/maglab/cover-letter/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/taewooopark/maglab/cover-letter"><img src="https://agentmods.dev/badge/skills/taewooopark/maglab/cover-letter.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 | $0.00064 | $0.00817 |
| Opus 5 | $0.00032 | $0.00409 |
| Sonnet 5 | $0.00013 | $0.00163 |
| Haiku 4.5 | $0.00006 | $0.00082 |
Grade A, and why
cover-letter 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 10d 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 — 94 lines — stays where its author put it; the contents beside it link to each section on GitHub.
cover-letter — Journal submission cover letter skill
Overview
This skill drafts a ≤250 word cover letter for journal manuscript submission, aligned with MagLab research integrity principles (§3.3) and the Appendix C bundle comms workflow.
Core principles:
- Body must be ≤250 words (excluding salutation and sign-off).
- The AI constructs novelty statements only from the author-provided
key_resultsinput. - The AI never invents results, citations, or claims beyond the provided inputs.
- All personalisation fields (editor name, affiliation, email) are marked
[FILL]. - Output always begins with
HUMAN REVIEW REQUIRED. - The letter is never auto-sent — it is written to a file for human review.
Agent: maglab.authoring.comms.cover_letter.CoverLetterAgent
CLI command: maglab comms cover-letter
Inputs
| Key | Type | Required | Description |
|---|---|---|---|
journal |
str | Yes | Target journal name (e.g. "Physical Review Letters") |
title |
str | Yes | Manuscript title |
key_results |
list[str] or str | Yes | 1–3 key results to highlight in the novelty statement |
related_pubs |
list[str] | No | Related published papers by the authors |
Output
A CommsResult with:
text: Cover letter (≤250 words) starting withHUMAN REVIEW REQUIRED.fill_markers: List of[FILL]positions requiring author personalisation.word_count: Approximate word count (logged as a warning if >250).
Letter structure
HUMAN REVIEW REQUIRED
[FILL: Dear Editor-in-Chief / Dr. [FILL: editor name],]
We submit our manuscript "[title]" for consideration in [journal].
[Novelty statement based on key_results — 1–2 sentences]
[Relationship to related_pubs — 1 sentence, if provided]
All authors have read and approved the manuscript.
The manuscript is not under consideration elsewhere.
[FILL: Corresponding author name, affiliation, email]
Workflow
- Collect the manuscript title, target journal, and 1–3 key results.
- Run
maglab comms cover-letteror invokeCoverLetterAgent.draft(inputs). - Review every
[FILL]field — fill in editor name and corresponding author details. - Verify the word count is ≤250 words.
- Submit the letter alongside the manuscript via the journal portal.
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.
- 10d ago First seen · 94 lines · 64 tokens per session scan A 75de6c68fb4d
cover-letter is a skill published in the GitHub repository TaewoooPark/MagLab (11 stars, last pushed 1mo ago), licensed MIT. It adds 64 tokens to every session and 817 once invoked, about $0.0003 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 skills, from other repositories
slidecraft
Convert PowerPoint (PPTX) files to HTML and back, analyze PPTX structure, generate slide decks from topics via LLM, pre-cache CDN assets, or launch the interactive review web UI. Use this when the user wants to work with PowerPoint presentations -- convert ppt to html, html to pptx, inspect pptx contents, or generate…
dos-dispatch-loop
Run recurring dos-dispatch cycles, switching to dos-replan when the backlog drains and stopping on the kernel's loop verdict. Use for unattended dispatch->replan->dispatch work across disjoint lanes.
dos-goal-fleet
Launch multiple goal-scoped workers in waves, each with a witness-gated stop condition and dos arbitrate file-tree safety. Use when an operator asks to run several independent goals in parallel and fold only verified ships.
dos-goal-gate
Ground a keep-working goal in evidence the worker did not author by wiring dos hook stop to refuse false done claims. Use for one self-stopping agent or loop worker; use dos-witness-claim for fold barriers.
slidecraft-to-html
Convert PowerPoint PPTX files to HTML for web display, RAG ingestion, or AI processing. Use when the user says convert this ppt to html, turn this presentation into a web page, extract content from PowerPoint for an AI pipeline, or wants to view slides in a browser.
dos-self-improve
Run the DOS self-improvement loop: propose a candidate, verify it in an isolated worktree, measure suite/truth/metric gates, and keep only confirmed gains. Use for recursive improvement; use dos-enforce-tune for policy knobs.