agentmods.dev

replication-radar: Instructions file for Claude Code

CLAUDE.md

replication-radar CLAUDE.md is an instructions file for Claude Code from ScienceLiveHub/replication-radar. It costs 1,342 tokens per session, scanned A, original, MIT.

Project-specific instructions for Replication Radar, a web app and MCP server that uses the OpenAIRE Graph—a research-publication database—to find papers worth independently repeating and assess existing checks.

In plain words
What is it for?
It guides work on the client-side web app, its Python MCP server, OpenAIRE searches, replication verdicts, and FAIR-software scoring.
Why use it?
It gives an AI coding assistant the project's purpose, architecture, deployment details, and rules so changes fit the existing app and research workflow.

Instructions file for Claude Code

Written for Claude Code: the file is CLAUDE.md. Also seen: mentions CLAUDE.md.

This is ScienceLiveHub/replication-radar's own configuration. It tells Claude Code how to work on replication-radar itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything replication-radar configures →

not rated 0repo 12d ago A scan 1,342 tokens original MIT
View source ↗ ScienceLiveHub/replication-radar openaire-hackathon.netlify.app
Reuse

Borrowing it

Nothing to install: this file belongs to ScienceLiveHub/replication-radar. 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/ScienceLiveHub/replication-radar/main/CLAUDE.md
Clone the repo
git clone --depth 1 https://github.com/ScienceLiveHub/replication-radar

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.

agentmods badge for replication-radar CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/sciencelivehub/replication-radar/claude-md/github.svg)](https://agentmods.dev/instructions/sciencelivehub/replication-radar/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/sciencelivehub/replication-radar/claude-md"><img src="https://agentmods.dev/badge/instructions/sciencelivehub/replication-radar/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.

agentmods 80×15 button for replication-radar CLAUDE.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/sciencelivehub/replication-radar/claude-md"><img src="https://agentmods.dev/badge/instructions/sciencelivehub/replication-radar/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 1,342 This file is loaded in full into every session.
When invoked 1,342 The same file — it is already loaded in full.
Security scan A 1 finding. 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.

ModelPer sessionOnce invoked
Fable 5.1 $0.01342 $0.01342
Opus 5.5 $0.00537 $0.00537
Sonnet 5.5 $0.00268 $0.00268
Haiku 4.5 $0.00134 $0.00134

Measured 2mo ago against content hash fbf3af5b2ca1, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

replication-radar CLAUDE.md scanned grade A with 1 finding 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.

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

- **Verify before building.** Probe an API live (curl / a Node snippet) BEFORE wiring it in. We wasted effort
CLAUDE.md · 61 lines

How it starts

The opening of the file, as written. The whole thing — 61 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CLAUDE.md — Replication Radar (project brief for Claude)

Read this before working. It's the heads-up for any Claude session on this repo.

What this is

Replication Radar — a tool that makes the OpenAIRE Graph more useful for replication. Search a research topic → impact-ranked papers worth replicating + whether each has been independently checked (with the verdict) + a FAIR-software score for the replications.

  • Live web app: https://openaire-hackathon.netlify.app (auto-deploys on push to main)
  • Also an MCP server (pip install replication-radar) exposing the same engine to agents.
  • OpenAIRE AI Hackathon, Theme B (Build). CC-BY. Deadline 2026-08-20; community vote 21–29 Aug.
  • Authors: Anne Fouilloux (+ Jean Iaquinta, who owns a complementary citation-graph angle via the Alien-gateway MCP).

Architecture

  • site/ — the web app (static: index.html, app.js, style.css, verdicts.json). Pure client-side; deployed by Netlify (netlify.toml → publish = "site"). This is the main artifact.
  • src/replication_radar/ — the MCP server (server.py = FastMCP; radar.py/openaire.py/verdicts.py = core). On PyPI.
  • scripts/build_verdicts.py — rebuilds the bundled verdict index from local FORRT chains (fallback data).
  • STORY.md — the 1–2pp CC-BY hackathon story. STALE — needs rewriting to match the current app (see Next).

How the app works — all GROUNDED, all CORS-enabled, NO auth/keys

  1. Impact ranking — public OpenAIRE Graph API https://api.openaire.eu/graph/v1/researchProducts (type=publication|software|dataset), indicators.citationImpact (BIP! classes C1=top 0.01% … C5). Dedup id = doi_dedup___::md5(lowercased-doi). Free-text is AND-ed; keep queries short.
  2. Verdict overlay (author-agnostic, LIVE) — SPARQL on https://query.knowledgepixels.com/repo/full. Two queries joined on the nanopub trusty hash (STRAFTER(STR(?x),"/np/")):
    • Outcomes: ?np ntpl:wasCreatedFromTemplate <https://w3id.org/np/RA2zljn0Nw9SadppOyxZoh-_Rxosslrq-vYG-p9SttnJE> → slt:hasValidationStatus (Validated/PartiallySupported/Contradicted) + slt:hasOutcomeRepository.
    • CiTO: template <https://w3id.org/np/RA43F9EoOuzF0xoNUnCMNyFsfIqlsuWDdPHCnN0wCdCAw>; the CiTO's subject is the Outcome np, cito:<rel> → original DOI. (ntpl: <https://w3id.org/np/o/ntemplate/>, slt: <https://w3id.org/sciencelive/o/terms/>, np: <http://www.nanopub.org/nschema#>.) Bundled verdicts.json = offline fallback only.
  3. FAIR-software — fair-software.eu 5 recs + usage, live from GitHub API + Software Heritage API (+ Zenodo API fallback to find the GitHub repo when OpenAIRE lacks codeRepositoryUrl). Only ever run on a replication we ACTUALLY have a repo URL for. GitHub unauth limit = 60/hr.

Read the full file on GitHub · 61 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.

  1. 2mo ago First seen · 61 lines · 1,342 tokens per session scan A fbf3af5b2ca1

Subscribe to this mod's changes

replication-radar CLAUDE.md is an instructions file published in the GitHub repository ScienceLiveHub/replication-radar (0 stars, last pushed 12d ago), licensed MIT. It adds 1,342 tokens to every session, about $0.0054 per session on Opus 5.5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Research
Related

replication-radar CLAUDE.md compared with instructions from other repositories

replication-radar CLAUDE.md next to 6 instructions from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
replication-radar CLAUDE.mdScienceLiveHub/replication-radarInstructions file012d agoMITA1,342Claude Code
vscode buildNext.instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA9,719GitHub Copilot
next.js AGENTS.mdvercel/next.jsInstructions file143kyesterdayMITA7,461Codex, OpenCode
langchain AGENTS.mdlangchain-ai/langchainInstructions file149kyesterdayMITA4,680Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA5,516GitHub Copilot
vscode copilot-instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA3,093GitHub Copilot
deepseek-harness AGENTS.mddeepseek-ai/deepseek-harnessInstructions file274k2d agoMITA4,313Codex, OpenCode