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/JeanDiable/academic-research-pluginnpx agentmods add skills/jeandiable/academic-research-plugin/citation-assistantWrote 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/jeandiable/academic-research-plugin/citation-assistant)<a href="https://agentmods.dev/skills/jeandiable/academic-research-plugin/citation-assistant"><img src="https://agentmods.dev/badge/skills/jeandiable/academic-research-plugin/citation-assistant/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/jeandiable/academic-research-plugin/citation-assistant"><img src="https://agentmods.dev/badge/skills/jeandiable/academic-research-plugin/citation-assistant.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 | $0.00127 | $0.02497 |
| Opus 5 | $0.00063 | $0.01248 |
| Sonnet 5 | $0.00025 | $0.00499 |
| Haiku 4.5 | $0.00013 | $0.00250 |
Grade A, and why
citation-assistant 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 — 206 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Overview
The citation-assistant skill automatically finds uncited claims in LaTeX manuscripts, searches for the right papers, fetches official BibTeX entries (never fabricates), and inserts \cite{} commands at the right locations. This eliminates the manual process of hunting down citations for statements, methods, datasets, and claims that lack proper attribution.
The skill uses a multi-stage pipeline:
- Parse the LaTeX source to extract text content and existing citations
- Identify statements that need citations but lack them
- Generate targeted search queries for each identified location
- Search academic databases (Semantic Scholar, DBLP, arXiv)
- Fetch official BibTeX entries for the best-matching papers
- Insert citations into the .tex files using the appropriate commands
- Merge all BibTeX entries into a unified references file
Input
One or more .tex file paths provided as arguments. The skill automatically:
- Detects existing
.bibfiles in the same directory as the.texfiles - Parses
\bibliography{}and\addbibresource{}commands to locate referenced bibliography files - Reads all provided
.texfiles and any detected.bibfiles to understand the current citation state
Setup
Install required dependencies using:
pip install -r BASE_DIR/scripts/requirements.txt
Ensure the following Python scripts are available in the BASE_DIR/scripts/ directory:
paper_search.py— searches Semantic Scholar and DBLPbibtex_utils.py— fetches and merges BibTeX entries
Workflow
Step 1: Parse LaTeX
Read all provided .tex files using the Read tool. Extract:
- All existing
\cite{},\citep{}, and\citet{}commands and their citation keys - All
\bibliography{}and\addbibresource{}references to locate bibliography files - The full text content with LaTeX commands stripped for analysis
- Note the citation command style used in the document (to match in subsequent insertions)
Step 2: Identify Uncited Statements
What ships with it
3 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.
- 10d ago First seen · 206 lines · 127 tokens per session scan A 7a9a52db90da
citation-assistant is a skill published in the GitHub repository JeanDiable/academic-research-plugin (21 stars, last pushed 5mo ago), licensed MIT. It adds 127 tokens to every session and 2,497 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
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…
next-partial-prefetching-adoption
Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…