What is cite-guard CLAUDE.md?

A repository instruction document for CiteGuard, an open-source tool that checks whether academic references were retracted, corrected, or flagged for review. It explains the project's purpose, constraints, data sources, and file layout.

Use it as guidance when working on CiteGuard's citation checker, MCP server, reference-status data, or repository structure.

It gives coding agents the project context needed to make changes without violating its design rules or misunderstanding its research terminology.

How lonexreb/cite-guard configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to lonexreb/cite-guard. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file

curl -O https://raw.githubusercontent.com/lonexreb/cite-guard/main/CLAUDE.md

Clone the repo

git clone --depth 1 https://github.com/lonexreb/cite-guard

Made for: Claude Code.

Wrote 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.

README.md

[![agentmods](https://agentmods.dev/badge/instructions/lonexreb/cite-guard/claude-md/github.svg)](https://agentmods.dev/instructions/lonexreb/cite-guard/claude-md)

Your own site

<a href="https://agentmods.dev/instructions/lonexreb/cite-guard/claude-md"><img src="https://agentmods.dev/badge/instructions/lonexreb/cite-guard/claude-md/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.

Your own site · 80×15

<a href="https://agentmods.dev/instructions/lonexreb/cite-guard/claude-md"><img src="https://agentmods.dev/badge/instructions/lonexreb/cite-guard/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 1,260 This file is loaded in full into every session.

When invoked 1,260 The same file — it is already loaded in full.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

Origin original No closer match found in the catalogue.

Token cost

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	$0.01260	$0.01260
Opus 5.5	$0.00504	$0.00504
Sonnet 5.5	$0.00252	$0.00252
Haiku 4.5	$0.00126	$0.00126

Measured 2mo ago against content hash 7e46f9a07712, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

cite-guard CLAUDE.md 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 2mo 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.

CLAUDE.md · 108 lines

How it starts

The opening of the file, as written. The whole thing — 108 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CLAUDE.md — CiteGuard

Guidance for Claude Code when working in this repository.

What this project is

CiteGuard is an open, OpenAlex-native citation-integrity layer for the open-science community. It flags references that are retracted, corrected, or subject to an expression of concern — the nuance OpenAlex's single is_retracted boolean cannot express — and surfaces this to librarians, research-integrity officers, systematic reviewers, and authors.

It ships as two surfaces over one core:

An evals-backed MCP server — the primary deliverable. Tools: check_references, get_editorial_status, watch_institution.
A reference-list checker — paste a DOI / upload a .bib → per-reference status.

The differentiator vs. prior art (RetractoBot, scite, Feet of Clay) is that this is free, fully open, OpenAlex-native, and evals-backed. RetractoBot could not build this openly because no open citation database existed at the time; OpenAlex now fills that gap.

Non-negotiable design constraints

Free-tier-aware by default. OpenAlex API keys are mandatory (since Feb 13, 2026). Free tier ≈ $1/day. /works?search= costs 10× a single-record lookup. Architect around cheap ID-based lookups, not bulk search. Use the free monthly snapshot subset for anything bulk; use the live API only for incremental/targeted checks.
Conservative labeling. A false "retracted" flag harms real authors — this is the exact bug OpenAlex shipped. Never over-claim. Distinguish retraction vs. correction vs. expression of concern vs. hijacked-journal. When status is ambiguous, say so.
Evals are a first-class deliverable, not an afterthought. Every core capability needs a gold-set test with reported precision/recall. The eval harness IS the moat.
CC0 / open ethos. Attribute Retraction Watch (via Crossref) and OpenAlex. Keep the project reproducible and well-documented (README, architecture docs, Zenodo DOI).

Data sources

OpenAlex API — works, authors, institutions, citation graph. Requires API key (env OPENALEX_API_KEY), plus a polite-pool mailto.
Retraction Watch dataset — now open via Crossref. Ingest the dump; it carries the update-nature nuance (retraction / correction / expression of concern) that we normalize into our own editorial-status model.
Crossref REST API — DOI normalization and cross-checking.

Read the full file on GitHub · 108 lines

Changes

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.

2mo ago First seen · 108 lines · 1,260 tokens per session scan A 7e46f9a07712

Subscribe to this mod's changes

cite-guard CLAUDE.md is an instructions file published in the GitHub repository lonexreb/cite-guard (0 stars, last pushed 3mo ago), licensed MIT. It adds 1,260 tokens to every session, about $0.0050 per session on Opus 5.5. 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.

Research Scientific bibliometrics citation-integrity crossref doi mcp mcp-server

cite-guard CLAUDE.md next to 6 instructions from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
cite-guard CLAUDE.mdlonexreb/cite-guard	Instructions file	0	3mo ago	MIT	A	1,260	Claude Code
vscode buildNext.instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	9,719	GitHub Copilot
next.js AGENTS.mdvercel/next.js	Instructions file	143k	yesterday	MIT	A	7,461	Codex, OpenCode
langchain AGENTS.mdlangchain-ai/langchain	Instructions file	149k	yesterday	MIT	A	4,680	Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	5,516	GitHub Copilot
vscode copilot-instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	3,093	GitHub Copilot
deepseek-harness AGENTS.mddeepseek-ai/deepseek-harness	Instructions file	274k	2d ago	MIT	A	4,313	Codex, OpenCode

cite-guard: Instructions file for Claude Code