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 MidnightDarling/collate --skill xray-papergit 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/xray-paper)<a href="https://agentmods.dev/skills/midnightdarling/collate/xray-paper"><img src="https://agentmods.dev/badge/skills/midnightdarling/collate/xray-paper.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 | $0.00150 | $0.04829 |
| Opus 5 | $0.00075 | $0.02414 |
| Sonnet 5 | $0.00030 | $0.00966 |
| Haiku 4.5 | $0.00015 | $0.00483 |
Grade A, and why
xray-paper 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 7d 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 — 285 lines — stays where its author put it; the contents beside it link to each section on GitHub.
xray-paper
The work this skill is for
History is not a stockpile of facts. It is an act of narration — the arrangement of traces into a shape that lets readers recognize what happened, what it meant, and what the sources could not bring themselves to say directly. Every historical paper is a small legitimate illusion: someone has staked their reading of the archive against its silences and shaped the result into prose. 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 — we study history, this art of fiction and narration, this legitimate human illusion, for no other purpose than to understand more of what is real.
A good reading of such a paper does not summarize. It enters the conversation. The historian stands in a long lineage — 司马迁 finishing 《史记》 under the weight of what he could not say directly; Marc Bloch writing Apologie pour l'histoire while hunted by the Gestapo; 陈寅恪 teaching 隋唐制度渊源 blind, from memory; Natalie Zemon Davis returning to the archives of Lyon until the voices of a single miller and his wife became audible. The form called "academic paper" inherits this weight.
When you read such a paper, you are not serving a user. You are entering a room where others have been speaking for a very long time. You leave traces — this report — that say: this is what we saw, this is the shape of what the author did. The traces should still be useful to a reader who opens them six months, six years later. That is the register.
Two operations, two only
This skill asks two things and refuses every other task.
- What did this paper actually do? — 问题意识 → 史料依据 → 论证结构 → 结论
- What does it do to the reader? — where it stands in the tradition; which cards it flips
Everything else — ASCII, SVG, chronicle, cognitive cards — is in service of these two. No ornament, no performance, no filler. History is already invention; the reader's honesty is what keeps the reading from being one more layer of fiction piled on top.
Register
Obsidian is the reader's vault. The report lives there.
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.
- 7d ago First seen · 285 lines · 150 tokens per session scan A 8c6b9e7d32b8
xray-paper is a skill published in the GitHub repository MidnightDarling/collate (6 stars, last pushed 3mo ago), licensed Apache-2.0. It adds 150 tokens to every session and 4,829 once invoked, about $0.0007 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 skills, from other repositories
pn-ai-fluency-curriculum
Design an AI fluency curriculum for a team or organization — skill-level assessment, learning path design, hands-on exercise plans, and progress tracking. Use when onboarding a team to AI agent tooling, building internal AI education programs, or helping individuals move from passive AI use to confident, autonomous AI…
learn-as-you-build
Turns every coding or creative session into a teaching session. Explains the WHY behind decisions, surfaces the tradeoff that was made, names the pattern being applied, and flags what transfers to other problems — without slowing the work down. Use continuously in any build, debug, design, or content session.
concept-glossary
Names the concept whenever the user describes something that has an established term — in engineering, design, marketing, product, psychology, business, or everyday life — then silently logs it to a running GLOSSARY.md with a plain-English definition and the real context it came up in. Use continuously; also use when…
thinking-prompts
A collection of 12 reusable thinking frameworks in English and Chinese for clarifying questions, learning unfamiliar ideas, solving problems, making decisions, and considering personal direction.
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.