Borrowing it
Nothing to install: this file belongs to mronkko/claude-academic-research. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/mronkko/claude-academic-research/main/CLAUDE.mdgit clone --depth 1 https://github.com/mronkko/claude-academic-researchWrote 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/instructions/mronkko/claude-academic-research/claude-md)<a href="https://agentmods.dev/instructions/mronkko/claude-academic-research/claude-md"><img src="https://agentmods.dev/badge/instructions/mronkko/claude-academic-research/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.
<a href="https://agentmods.dev/instructions/mronkko/claude-academic-research/claude-md"><img src="https://agentmods.dev/badge/instructions/mronkko/claude-academic-research/claude-md.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 | $0.07512 | $0.07512 |
| Opus 5.5 | $0.03005 | $0.03005 |
| Sonnet 5.5 | $0.01502 | $0.01502 |
| Haiku 4.5 | $0.00751 | $0.00751 |
Grade B, and why
claude-academic-research CLAUDE.md scanned grade B with 2 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 13d 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.
Reads agent configuration directoriesmediumAgent snooping
.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.
- **Project-local artefacts**: scripts and skills write run-outputs under `.claude/<scope>/` for transient internals (e.g. `.claude/audit/`) and under top-level visible directories for outputs the user is expected to fin Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
- `scripts/pipelines/http_client.py` — shared `requests.Session` with `urllib3.Retry` + `tenacity` wrappers. **Every outbound HTTP call in `scripts/pipelines/` goes through a session from `build_session()`** — either the How it starts
The opening of the file, as written. The whole thing — 138 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md
This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository.
Deferred development ideas — things consciously not done yet but worth revisiting — live in BACKLOG.md. Consult it before starting non-trivial work; the current item may already be captured there with context for why it was deferred.
What this repo is
An academic research plugin for Claude Code and Antigravity — not an application. It ships skills (prose rule-books), pipeline scripts, and templates for academic-research workflows. Claude Code users install via /plugin marketplace add mronkko/claude-academic-research, while Antigravity users install via agy plugin install <url>. Anything you change here is consumed by downstream agentic instances in user projects.
This is primarily a personal-use project. The author is the main user, and that changes the working norm: commit to main directly, and accept that main may be temporarily broken. A red main here is not an incident — do not revert someone else's commit to green it, do not open a branch purely to avoid breaking it, and do not stop mid-task to stabilise something you were not asked to touch. Fix forward. The one cost worth knowing is that CI (ruff check scripts tests templates editorial-tools mcp then pytest tests -v, lint a hard gate) goes red on push and stays red until the next commit, so run both locally when it is cheap; that is courtesy to the next session, not a gate you must pass before committing.
The repo is a marketplace hosting more than one plugin. .claude-plugin/marketplace.json lists them. The main plugin, academic-research, is sourced at the repo root (./) and is what most of this CLAUDE.md describes. A second, smaller plugin, editorial-tools, lives under editorial-tools/ with its own .claude-plugin/plugin.json and skills/ — it ships the suggesting-reviewers skill (peer-reviewer suggestion for journal editors/AEs, with a bundled ORM editorial-board roster). The two are independent installs: the root plugin only scans ./skills/, so editorial-tools/ does not leak into it, and users who install only academic-research never load the editorial skill. Do not assume one-plugin-per-repo.
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.
- 13d ago Changed · +54 tokens per session 0e226352c503
- 21d ago Changed · +9 lines · +2,141 tokens per session b9aa7c8238d6
- 1mo ago Changed · +3 lines · +586 tokens per session 64715afcb4c3
- 1mo ago Changed · +94 tokens per session 49a60eee5164
- 2mo ago First seen · 126 lines · 4,637 tokens per session scan B 50269cc2826d
claude-academic-research CLAUDE.md is an instructions file published in the GitHub repository mronkko/claude-academic-research (29 stars, last pushed yesterday), licensed MIT. It adds 7,512 tokens to every session, about $0.0300 per session on Opus 5.5. A static security scan graded it B with 2 findings (reads agent configuration directories, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
claude-academic-research CLAUDE.md compared with instructions from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| claude-academic-research CLAUDE.mdmronkko/claude-academic-research | Instructions file | 29 | yesterday | MIT | B | 7,512 | 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 |