Borrowing it
Nothing to install: this file belongs to alfadur7/llm-wiki-newsroom. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/alfadur7/llm-wiki-newsroom/main/.claude/skills/scholarly-citation/SKILL.mdgit clone --depth 1 https://github.com/alfadur7/llm-wiki-newsroomWrote 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/alfadur7/llm-wiki-newsroom/scholarly-citation)<a href="https://agentmods.dev/skills/alfadur7/llm-wiki-newsroom/scholarly-citation"><img src="https://agentmods.dev/badge/skills/alfadur7/llm-wiki-newsroom/scholarly-citation/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/alfadur7/llm-wiki-newsroom/scholarly-citation"><img src="https://agentmods.dev/badge/skills/alfadur7/llm-wiki-newsroom/scholarly-citation.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00092 | $0.01531 |
| Opus 5 | $0.00046 | $0.00766 |
| Sonnet 5 | $0.00018 | $0.00306 |
| Haiku 4.5 | $0.00009 | $0.00153 |
Grade A, and why
scholarly-citation 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 12d 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 — 48 lines — stays where its author put it; the contents beside it link to each section on GitHub.
scholarly-citation
Verifiable-attribution craft drawn from scholarly/scientific citation traditions (citation classification, typing, anchoring). It ensures every claim in this wiki is atomized, evidence-graded, attributed to a speaker, typed by citation meaning, and anchored to a source location — and therefore traceable. Unlike the three borrowed traditions (narrative, exec summary, encyclopedic neutrality), this craft synthesizes external sources into an atomic-claim schema and is the project's signature. criteria.json is the SoT for each criterion's definition, comparator, and source; wiki-global state (page existence·hub type·section titles) is injected by the orchestrator (tools/_lint/source.py). The schema literals (## Key Claims, [fact], cites: etc.) are the wiki's actual schema markers and section headers.
Claim atomization & grading (cit.grade-marker · cit.atomic · cit.composite-split)
One claim, one line, one utterance. Each line of ## Key Claims (Key Claims) marks an evidence grade — [fact] (primary source), [analysis] (secondary analysis), [forecast] (forecast). Putting two subjects' claims on one line (joined by "and"/"&" or a comma series spanning two hubs; ko: the conjunctions 와/및), or chaining verb phrases on one line ("…did, and …did"; ko: ~했고, ~했다), breaks atomicity.
Claimant attribution (cit.claimant-link · cit.claimant-valid · cit.speaker-link)
Every claim is bound to who said it. The slot right after the grade marker names the speaker — a [[wikilink]] when they have a page, their plain-text real name and role when they fall below the page-creation threshold. What WP:ASF requires is the named source; the wikilink is one means to it, so demanding a link from a speaker who cannot have a page only pushes the author to link some other entity. Anonymous or collective subjects ("the government"·"industry sources"; ko 정부는·업계에서는) stay forbidden in either form ("avoid stating opinions as facts"; attribute them to a named source), as does naming in plain text a page that does exist. A blockquote names its speaker (APA author-date principle — identify the cited author), wikilinked when that speaker has a page. A speaker with no page stays plain text with their role spelled out. Any target that is linked must exist as a real page.
What ships with it
2 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.
- 12d ago First seen · 48 lines · 92 tokens per session scan A c44e2ffed0d8
scholarly-citation is a skill published in the GitHub repository alfadur7/llm-wiki-newsroom (85 stars, last pushed yesterday), licensed MIT. It adds 92 tokens to every session and 1,531 once invoked, about $0.0005 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
binder-modeling
Binder data modeling — define entity types, fields, relations, constraints, views, and navigation. Use when asked to "create a type", "add a field", "define a schema", "set up relations", "model entities", "create a view", "set up navigation", "render entities as files", or design a binder workspace schema.
binder-app
Build a small HTTP app (dashboard, kanban board, admin panel, custom UI) on top of an existing Binder workspace. Use when asked to "create an app", "build a dashboard", "show records in a chart", "make a kanban/board", "build an admin panel", or "add a UI on top of binder".
binder-import
Import external data into a Binder workspace. Handles CSV, JSON, YAML, Markdown files, and directories of Markdown. Use when asked to "import data", "load records from a file", "ingest documents", "migrate data into binder", or bulk-create records from an external source.
binder-cli
Binder CLI for knowledge graph operations — CRUD, search, schema inspection, transaction import, docs rendering. Use when asked to "query binder", "search records", "create a record", "check the schema", "import transactions", "undo changes", or work with a binder workspace.
capture-task
Capture a new task — create a draft or pending Task record from a rough idea or detailed spec. Use when asked to "add a task", "log a bug", "create a task", or "add to backlog".
refine-backlog
Refine the backlog — screen drafts, remove duplicates, fill in missing details, classify, link, and move to pending.