systematic-review

systematic-review is a skill for Claude Code from mronkko/claude-academic-research. It costs 125 tokens per session (25,176 once invoked), scanned A, original, MIT.

A workflow for carrying out a systematic literature review, a structured search and evaluation of research papers using the PRISMA reporting approach.

In plain words
What is it for?
Use it to search for papers, screen titles or full texts, record study information, code evidence, and prepare review outputs.
Why use it?
It organizes searching, screening, coding, and exporting evidence so a research review follows a repeatable process.

Skill for Claude Code

Written for Claude Code: ${CLAUDE_PLUGIN_ROOT variable. Also seen: mentions CLAUDE.md; mentions subagents; positional $N argument.

Runs only inside its plugin — its command needs a path that Claude Code sets for a plugin’s own hooks and for nothing else. Install the plugin, not this.

Part of the academic-research plugin — 11 skills, 1 plugin shipped together

Good fit Use it to search for papers, screen titles or full texts, record study information, code evidence, and prepare review outputs.

Compare 6 skills from other repositories ↓
Install

Getting it into your agent

This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.

Claude Code
/plugin marketplace add mronkko/claude-academic-research
Claude Code
/plugin install academic-research

Made for: Claude Code.

Or install academic-research, the plugin that ships this one along with the rest of its 11 skills, 1 plugin.

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 systematic-review

README.md
[![agentmods](https://agentmods.dev/badge/skills/mronkko/claude-academic-research/systematic-review/github.svg)](https://agentmods.dev/skills/mronkko/claude-academic-research/systematic-review)
Your own site
<a href="https://agentmods.dev/skills/mronkko/claude-academic-research/systematic-review"><img src="https://agentmods.dev/badge/skills/mronkko/claude-academic-research/systematic-review/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 systematic-review

Your own site · 80×15
<a href="https://agentmods.dev/skills/mronkko/claude-academic-research/systematic-review"><img src="https://agentmods.dev/badge/skills/mronkko/claude-academic-research/systematic-review.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 125 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 25,176 The whole file, excluding the scripts and references it only reads on demand.
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 $0.00125 $0.25176
Opus 5 $0.00063 $0.12588
Sonnet 5 $0.00025 $0.05035
Haiku 4.5 $0.00013 $0.02518

Measured 7d ago against content hash b935acd6c957, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

systematic-review 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 7d 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.

direct `urllib.request.urlopen("http://127.0.0.1:23119/...")` or
skills/systematic-review/SKILL.md · 1,890 lines

How it starts

The opening of the file, as written. The whole thing — 1,890 lines — stays where its author put it; the contents beside it link to each section on GitHub.

systematic-review

Glossary: unfamiliar with PRISMA, MCP, BBT, ABS, DOI, ISSN, SFX, TDM, CSL, stage tag, or FE-code? See skills/_glossary.md for one-line definitions of every acronym this skill uses.

Pre-flight (ALWAYS run first)

Before any step below, verify the plugin has been configured:

python3 "${CLAUDE_PLUGIN_ROOT:-.}/scripts/setup/check_configured.py"

If the result is NOT CONFIGURED, stop immediately and tell the user:

The academic-research project has not been set up on this machine yet. Run the setup skill or setup wizard first to configure API keys (Zotero, Elsevier, WoS, Anthropic, Gemini, Semantic Scholar), MCP servers, and permission rules. Do not attempt an SLR before that.

Do not call MCP tools, run pipeline scripts, or proceed with any stage of the procedure. Running the setup skill/wizard is the required first step.

If the result is configured, proceed.


Autonomous runs

When the user asks for autonomous execution — "work autonomously", "run the whole thing", "don't ask me, just do it", "go" — that is a real instruction and it is honoured. It changes when you ask, not whether.

Consolidate every confirmation into one up-front proposal, and make that proposal before the first paid inference call. Not per stage. The pipeline's gates (scope, model, cost) exist so a human decides before money and methodology are committed; asking six times during a run the user has walked away from does not achieve that, and skipping them silently — which is what happened in the session that prompted this section — achieves the opposite of it.

The single proposal must contain:

  1. Scope summary — the brief from .claude/systematic-review/scope.md, condensed to what a reader needs to say yes or no: construct, population, questions, databases, year range, journal set.
  2. Proposed model per stage, with the comparison that justifies it (see "Choosing the screening model" — newest of the required tier, never a dated snapshot when a newer sibling exists).
  3. Item counts, once the search and import have run — they are not gated, so you will have real numbers rather than an estimate.
  4. Projected LLM cost, from an actual --dry-run of the screening stage. Not a guess, and not omitted because the dry run was awkward — the dry run is one command and its cost line is the number the user is being asked to approve.

Read the full file on GitHub · 1,890 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. 7d ago Changed · +159 lines b935acd6c957
  2. 11d ago First seen · 1,731 lines · 125 tokens per session scan A 13a2756a76ed

Subscribe to this mod's changes

systematic-review is a skill published in the GitHub repository mronkko/claude-academic-research (23 stars, last pushed 7d ago), licensed MIT. It adds 125 tokens to every session and 25,176 once invoked, about $0.0006 per session on Opus 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 2026-08-30.

Related

Other skills, from other repositories

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

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…

microsoft/ai-agents-for-beginners · 200 tokens

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…

vercel/next.js · 95 tokens

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…

vercel/next.js · 83 tokens

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…

vercel/next.js · 170 tokens

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…

vercel/next.js · 103 tokens