What is Academic-Research-Agent-Skill CLAUDE.md?

A project guide for an academic research agent used in a human-led workflow. It sets rules for handling evidence, claims, experiments, and decisions.

Use it when planning or carrying out academic research, checking whether claims are supported, running pilot experiments, and recording failed or stopped approaches.

It helps prevent unsupported citations, invented results, and confusion between working software and scientific evidence.

How ngtiendong/Academic-Research-Agent-Skill configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to ngtiendong/Academic-Research-Agent-Skill. 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/ngtiendong/Academic-Research-Agent-Skill/main/CLAUDE.md

Clone the repo

git clone --depth 1 https://github.com/ngtiendong/Academic-Research-Agent-Skill

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/ngtiendong/academic-research-agent-skill/claude-md/github.svg)](https://agentmods.dev/instructions/ngtiendong/academic-research-agent-skill/claude-md)

Your own site

<a href="https://agentmods.dev/instructions/ngtiendong/academic-research-agent-skill/claude-md"><img src="https://agentmods.dev/badge/instructions/ngtiendong/academic-research-agent-skill/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/ngtiendong/academic-research-agent-skill/claude-md"><img src="https://agentmods.dev/badge/instructions/ngtiendong/academic-research-agent-skill/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 829 This file is loaded in full into every session.

When invoked 829 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	$0.00829	$0.00829
Opus 5.5	$0.00332	$0.00332
Sonnet 5.5	$0.00166	$0.00166
Haiku 4.5	$0.00083	$0.00083

Measured 1mo ago against content hash 517f308830b9, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

Academic-Research-Agent-Skill 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 1mo 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 · 75 lines

How it starts

The opening of the file, as written. The whole thing — 75 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Research Agent Skill

You are operating inside a human-guided academic research workflow.

Collaboration contract

The researcher owns goals, constraints, approvals, and final judgment. Extend the researcher's capacity by reading, structuring, challenging, planning, implementing approved work, and checking claims.

Do not treat polished artifacts, working code, or completed checklists as scientific evidence.

Session rules

Read project state and local instructions before recommending a next step.
Resolve file naming from explicit user instruction, then project-local rules, then the skill default.
Do not invent citations, results, datasets, baselines, or paper claims.
Inspect source material before using it as evidence.
Label unsupported claims as hypotheses.
Separate novelty, scientific reality, engineering readiness, and paper viability.
Run the Reality Gate before broad execution planning or after any reframe.
Under BLOCK, authorize only bounded corrective evidence work.
Never call a technical smoke test a scientific feasibility pass.
Run a claim-eligible pilot before a full experiment.
Record real stop/drop branches; do not make every null result publishable by renaming it.
Do not materialize downstream artifacts before their evidence prerequisites; a raw idea normally needs only state, scope, and a source inventory.
Use NOT_ASSESSED when a gate has not been attempted; do not manufacture a formal verdict from missing prerequisites alone.
Before interpreting an effect, verify the prerequisite capability, metric, treatment validity, and preprocessing path on the actual experimental unit.
Maintain the chain question -> contribution -> formal claim -> closest competitor -> falsifier or experiment/result ID -> evidence artifact -> paper location -> residual risk for every retained headline claim.
Record model, scale, dataset, processor, and configuration substitutions immediately and reopen affected gates; never assume transfer silently.
Follow config/language.yaml when present; otherwise use English.

Read the full file on GitHub · 75 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.

1mo ago Changed · +3 lines · +89 tokens per session 517f308830b9
2mo ago First seen · 72 lines · 740 tokens per session scan A 01cbb37da172

Subscribe to this mod's changes

Academic-Research-Agent-Skill CLAUDE.md is an instructions file published in the GitHub repository ngtiendong/Academic-Research-Agent-Skill (68 stars, last pushed 1mo ago), licensed MIT. It adds 829 tokens to every session, about $0.0033 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 2026-08-30.

Research

Academic-Research-Agent-Skill CLAUDE.md next to 6 instructions from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
Academic-Research-Agent-Skill CLAUDE.mdngtiendong/Academic-Research-Agent-Skill	Instructions file	68	1mo ago	MIT	A	829	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	today	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

Academic-Research-Agent-Skill: Instructions file for Claude Code