Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/Light0305/Light-skillsnpx agentmods add skills/light0305/light-skills/light-citationWrote 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/light0305/light-skills/light-citation)<a href="https://agentmods.dev/skills/light0305/light-skills/light-citation"><img src="https://agentmods.dev/badge/skills/light0305/light-skills/light-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/light0305/light-skills/light-citation"><img src="https://agentmods.dev/badge/skills/light0305/light-skills/light-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 | $0.00121 | $0.03038 |
| Opus 5 | $0.00060 | $0.01519 |
| Sonnet 5 | $0.00024 | $0.00608 |
| Haiku 4.5 | $0.00012 | $0.00304 |
Grade A, and why
light-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 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 — 272 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Citation — stage 10
Make every author-used reference traceable, real, correctly identified, and honestly connected to the claim it is supposed to support. Treat formatting, metadata existence, publication-integrity facts, and semantic support as four different questions.
Read citation-resource-map.md before a full
manuscript audit. Read
references/registry_contract.md before
producing or consuming the canonical registry. Read
references/locator_audit.md before judging
claim support.
Stage contract
- Consume paper-writing's
light.paper_claims.v1, exact claim/source locators, current claim text hashes, reviewer-bound citation-support hashes, manuscript, figures/tables, supplement, and reference candidates. - Reuse literature-search provenance as input evidence; independently verify the references the author actually keeps.
- Emit
light.citation_registry.v1, BibTeX, CSL JSON, source-level evidence, failure records, claim-edge review, citekey audit, andlight.findings.v1(producer=citation). - Keep stage 10's only critical gate
citation_verify: confirmed missing works and chimeric citations. Metadata conflicts, unavailable sources, claim relevance, formatting, and publication-update alerts are warn/skip. - Fix citation failures inside stage 10.
ROUTEShas no key 10; never invent a back-edge. - Hand
references.bib,citekey-audit.json, registry anddelivery.jsonto typesetting. Typesetting compiles and checks keys; it does not re-decide authenticity.delivery.jsonmust declarestatusand per-deliverablesha256:hashes so typesetting can reject stale or edited handoffs.
Non-negotiable rules
- Never invent a reference, DOI, author, year, venue, citekey, locator or support verdict.
- Never call a network failure, rate limit, 5xx, authentication failure, or index miss “this work does not exist.”
- Assign
CONFIRMED-MISSINGonly when DOI Registration Agency explicitly reports non-existence and Crossref plus DataCite both return 404/410. - Assign
CONFIRMEDonly when registration metadata and at least one independent field source confirm the work. Otherwise retainUNAVAILABLEorUNRESOLVED. - Preserve every source's title/authors/year/venue/identifier value. Select canonical fields from the registration agency; never use fuzzy matching to overwrite the original citation.
- Treat a real DOI paired with conflicting title/authors/year as a possible chimeric citation. Multi-core-field conflict is critical; one ambiguous field mismatch is a warning for manual review.
- Read publication updates in the correct direction: the affected original
carries Crossref
updated-by; the notice carries inverseupdate-to. - Record retraction/correction/expression-of-concern facts and alerts, then hand integrity judgment and wording to research-ethics. Do not rebuild its ethics gate.
- Never equate metadata confirmation or “A cites B” with “B supports claim
C.”
SUPPORTSrequires a locator-backed semantic review. - Keep the core path local/free or public/no-key. OpenAlex and keyed Semantic Scholar are optional coverage enhancements; commercial managers, institutional databases, and browser plugins are never required.
What ships with it
15 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.
- assets/citation_checklist.md 2.1 KB
- citation-resource-map.md 5.1 KB
- references.md 31 KB
- references/locator_audit.md 4.3 KB
- references/registry_contract.md 3.8 KB
- scripts/citation_four_gate.py 25 KB runs code
- scripts/citation_registry.py 39 KB runs code
- scripts/citation_verify_gate.py 46 KB runs code
- scripts/citekey_audit.py 7.4 KB runs code
- scripts/doi_to_any.py 14 KB runs code
- scripts/verify_citation_edge.py 11 KB runs code
- scripts/verify_refs.py 33 KB runs code
- templates/citation_input.json 946 B
- templates/citation-four-gate.example.json 907 B
- templates/claim_citation_review.json 1.3 KB
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 · 272 lines · 121 tokens per session scan A 89e1e6be0c70
light-citation is a skill published in the GitHub repository Light0305/Light-skills (617 stars, last pushed 2mo ago), licensed MIT. It adds 121 tokens to every session and 3,038 once invoked, about $0.0006 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
ml-paper-writing
Write publication-ready ML/AI papers for NeurIPS, ICML, ICLR, ACL, AAAI, COLM. Use when drafting papers from research repos, structuring arguments, verifying citations, or preparing camera-ready submissions. Includes LaTeX templates, reviewer guidelines, and citation verification workflows.
anti-defensive-writing-en
Stops defensive writing across the entire paper lifecycle — writing, revising, cutting, and organizing experiments. Treats the paper as a press conference, not a project summary, lab log, or self-audit: identify the single most publishable strength of the work and build the most favorable, complete, and persuasive…
anti-defensive-writing
A Chinese-language writing guide for presenting a research paper around its strongest supported contribution. It treats the paper as a focused academic presentation rather than a project diary or complete lab record.
paper-writing
Research paper writing assistant that enforces Arpit Gupta's editorial principles, voice profile, and writing workflow. MANDATORY TRIGGERS: Use this skill whenever the user mentions writing a paper, drafting a section, revising a section, editing a paper, reviewing a draft, rewriting an introduction, writing an…
research-writing
A collection of 30 prompt templates for writing and reviewing scientific papers. It covers tasks such as translating, editing, summarizing research, writing sections, creating figure captions, and preparing reviewer replies.
academic-paper-writing-skill
Evidence-first academic research workflow for topic ideation, scholarly search, paper reading, literature and systematic reviews, study and experiment design, statistics and data analysis, scientific figures, manuscript drafting and polishing, citation checks, peer review, rebuttals, submission packages, theses, and…