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 skills/midnightdarling/collate/paper-summarynpx skills add MidnightDarling/collate --skill paper-summarygit clone --depth 1 https://github.com/MidnightDarling/collateWrote 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/midnightdarling/collate/paper-summary)<a href="https://agentmods.dev/skills/midnightdarling/collate/paper-summary"><img src="https://agentmods.dev/badge/skills/midnightdarling/collate/paper-summary.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 | $0.00157 | $0.03984 |
| Opus 5 | $0.00078 | $0.01992 |
| Sonnet 5 | $0.00031 | $0.00797 |
| Haiku 4.5 | $0.00016 | $0.00398 |
Grade B, and why
paper-summary scanned grade B with 1 finding 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 5d 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.
Strips warnings and disclaimersmediumAnti-refusal
Omitting safety caveats hides risk from the user and is a common jailbreak preamble.
**Identify blind spots**. Blind spots tell more than covered ground. A field with 20 papers on 1911 and 1 on 1916–1927 is saying something about itself — perhaps about which moments feel like "history" and which feel too How it starts
The opening of the file, as written. The whole thing — 266 lines — stays where its author put it; the contents beside it link to each section on GitHub.
paper-summary
The work this skill is for
The single historical paper is a legitimate illusion held by one author at one desk. A body of scholarship is many illusions, held together — some agreeing without noticing, some quarrelling across decades, some silent about each other in ways that say more than their citations. To map that body is to stand where the field stands and see its shape.
The Chinese tradition calls this 学术史. 梁启超 wrote 《中国近三百年学术史》 to understand what three centuries of Chinese scholarship had collectively done and collectively avoided. 钱穆 wrote under the same title, with the same aim but a different angle. Peter Burke's Varieties of Cultural History and Natalie Zemon Davis's introductions to collected volumes belong to the same genre — the view from above a field, by a reader who has lived inside it long enough to see its rhythms.
This skill is not summarization. It is landscape-making. A summary lists papers. A landscape tells the reader where to stand, what to see from there, and which of the field's silences are the interesting ones. 我们探究历史，这虚构和叙事的艺术，这人类合法的幻觉，无非为了理解更多的真实 — and a field's collective illusions, read together, reveal what each paper alone could not admit.
When you map a body of scholarship, you are not serving a user. You are standing with them on a ridge above a valley, tracing the old roads and the newly cut paths, naming the peaks and the swamps. The map you leave is the view you both saw.
What a literature map answers
A map of 30 papers answers different questions from an x-ray of one. A map answers:
- Who rests on what sources? — which archives, which readings of them
- Who is in dialogue with whom? — the citation graph; the silences
- What time and space does the corpus cover? — and what does it collectively ignore?
- Which methodological moves dominate? — and which are underused?
- Which concepts are they quietly fighting over? — 近代性? 士人? 传统? 封建?
- Which foreign theoretical frameworks get absorbed, which stay ornamental?
- What remains unsolved after reading all of them together?
- Where should a newcomer start?
What ships with it
4 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 5d ago First seen · 266 lines · 157 tokens per session scan B 69fba44d3666
paper-summary is a skill published in the GitHub repository MidnightDarling/collate (6 stars, last pushed 3mo ago), licensed Apache-2.0. It adds 157 tokens to every session and 3,984 once invoked, about $0.0008 per session on Opus 5. A static security scan graded it B with 1 finding (strips warnings and disclaimers). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
postgresql-table-design
Use this skill when designing or reviewing a PostgreSQL-specific schema. Covers best-practices, data types, indexing, constraints, performance patterns, and advanced features.
spark-training-gotchas
Preflight and diagnose the ten known failure modes for ML training on NVIDIA DGX Spark. Use when a training run on DGX Spark fails to start, OOMs below the 128GB limit, slows down mid-run, or before any multi-hour training job on GB10.
parallel-feature-development
Coordinate parallel feature development with file ownership strategies, conflict avoidance rules, and integration patterns for multi-agent implementation. Use this skill when decomposing a large feature into independent work streams, when two or more agents need to implement different layers of the same system…
nft-standards
Implement NFT standards (ERC-721, ERC-1155) with proper metadata handling, minting strategies, and marketplace integration. Use when creating NFT contracts, building NFT marketplaces, or implementing digital asset systems.
cost-optimization
Optimize cloud costs across AWS, Azure, GCP, and OCI through resource rightsizing, tagging strategies, reserved instances, and spending analysis. Use when reducing cloud expenses, analyzing infrastructure costs, or implementing cost governance policies.
istio-traffic-management
Configure Istio traffic management including routing, load balancing, circuit breakers, and canary deployments. Use when implementing service mesh traffic policies, progressive delivery, or resilience patterns.