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 literature-reviewgit 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/literature-review)<a href="https://agentmods.dev/skills/taewooopark/maglab/literature-review"><img src="https://agentmods.dev/badge/skills/taewooopark/maglab/literature-review/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/literature-review"><img src="https://agentmods.dev/badge/skills/taewooopark/maglab/literature-review.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 | $0.00055 | $0.00739 |
| Opus 5 | $0.00028 | $0.00369 |
| Sonnet 5 | $0.00011 | $0.00148 |
| Haiku 4.5 | $0.00006 | $0.00074 |
Grade A, and why
literature-review 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 11d 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 — 104 lines — stays where its author put it; the contents beside it link to each section on GitHub.
literature-review — Systematic literature review workflow skill
Overview
This skill implements a PRISMA (Preferred Reporting Items for Systematic Reviews)-based systematic review workflow aligned with MagLab research integrity principles (§3.3).
Core principles:
- Every factual claim → DOI citation required
- The LLM does not generate numerical values or material properties — citations from the paper text only
- Consensus and controversy are stated transparently
Four-stage workflow
Stage 1: Search
- Use the
literature-searchskill to generate a query family and collect candidates - Multiple sources: OpenAlex · arXiv · Semantic Scholar
- Record search queries, dates, and filters (reproducibility)
Stage 2: Screening
Inclusion criteria:
- Directly relevant to magnetism or spintronics
- Contains experimental, theoretical, or simulation results
- Available in English or with an English abstract
Exclusion criteria:
- Retracted or corrected papers (
retraction_status: "retracted") - Off-topic (may also be excluded at T3)
- Failed DOI/metadata validation (
verification_status: "failed")
Stage 3: Quality assessment
For each paper:
- Methodological validity (measurement geometry · control group · statistics)
- Reproducibility (parameters · data access)
- Bias risk (sample selection · measurement uncertainty)
Record assessment results in the notes field.
Stage 4: Synthesis
Format: Paper-by-paper summary listing is prohibited — topic-centred synthesis is required.
Synthesis structure:
## [Topic/perspective]
[Evidence sentence (DOI citation format: [AuthorYear, DOI:xxx])]
### Consensus
[Common findings · methodology]
### Controversy
[Conflicting reports · method differences · interpretation differences]
### Gaps
[Open questions · unexplored areas]
Local-gap analysis
Compare local corpus with new search results to identify gaps:
- List of locally held papers (local-context-librarian results)
- Identify papers in new search results not in local corpus
- Generate coverage map by topic and method
- Report 3–5 priority gaps
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.
- 11d ago First seen · 104 lines · 55 tokens per session scan A c45ea829866c
literature-review is a skill published in the GitHub repository TaewoooPark/MagLab (11 stars, last pushed 1mo ago), licensed MIT. It adds 55 tokens to every session and 739 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-review
Launch an interactive web UI for reviewing, editing, and approving AI-generated slide presentations with human-in-the-loop feedback. Use when the user says review the slides, check the generated presentation, see slides before finalizing, or wants a visual review interface for slide generation.
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.