Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add SkillMedev/academic-researcher --skill systematic-reviewgit clone --depth 1 https://github.com/SkillMedev/academic-researcherWrote 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/skills/skillmedev/academic-researcher/systematic-review)<a href="https://agentmods.dev/skills/skillmedev/academic-researcher/systematic-review"><img src="https://agentmods.dev/badge/skills/skillmedev/academic-researcher/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.
<a href="https://agentmods.dev/skills/skillmedev/academic-researcher/systematic-review"><img src="https://agentmods.dev/badge/skills/skillmedev/academic-researcher/systematic-review.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 | $0.00123 | $0.01741 |
| Opus 5 | $0.00062 | $0.00870 |
| Sonnet 5 | $0.00025 | $0.00348 |
| Haiku 4.5 | $0.00012 | $0.00174 |
Grade A, and why
Systematic Review 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 10d 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.
How it starts
The opening of the file, as written. The whole thing — 104 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Systematic Review
A systematic review answers one focused question by finding, appraising, and synthesizing all relevant studies with a transparent, reproducible method. The costly failure it prevents is post-hoc bias: deciding what counts as evidence after seeing the results. Every eligibility decision is therefore locked in a protocol before the first search runs, and every excluded study leaves a logged reason. Follow PRISMA 2020 throughout.
Operating procedure
Order is mandatory: the protocol must exist before the search, and the search before screening, or the review is not systematic - it is a literature review wearing a lab coat (route that job to literature-review).
Step 1: Gather inputs and frame the PICO question
Collect from the user before starting:
- The research question, decomposed into Population, Intervention/Exposure, Comparison, Outcome. If it has no clear PICO, refuse and help them write one - a question like "is telehealth good?" cannot be reviewed.
- Intended study designs (RCTs only? observational too?).
- Databases available to them (default: PubMed/MEDLINE, Embase, plus one field-specific database - a minimum of 3).
- Team size: two independent screeners are required; if the user is solo, flag this as a methodological limitation up front, not in the discussion section.
- Timeline and whether meta-analysis is intended.
Label any assumed input as a guess and confirm before Step 3.
Step 2: Write and register the protocol
Document eligibility criteria, databases, full search strings, screening process, extraction fields, risk-of-bias tool, and analysis plan. Recommend PROSPERO registration (health topics) or OSF (other fields). Fill this criteria table - every row, every cell, before searching:
INCLUSION / EXCLUSION CRITERIA - [FILL: review title]
Domain | INCLUDE | EXCLUDE (with justification)
---------------|--------------------------------------|------------------------------------------
Population | [FILL: e.g. adults ≥18 with T2DM] | [FILL: e.g. type 1, gestational - different pathology]
Intervention | [FILL: e.g. telehealth coaching ≥8w] | [FILL: e.g. one-off SMS reminders - not coaching]
Comparison | [FILL: e.g. usual care, waitlist] | [FILL: e.g. head-to-head telehealth arms]
Outcome | [FILL: e.g. HbA1c at ≥3 months] | [FILL: e.g. satisfaction-only studies]
Study design | [FILL: e.g. RCTs, cluster RCTs] | [FILL: e.g. case reports, editorials, protocols]
Language | [FILL - restricting is a limitation] | [FILL]
Setting | [FILL] | [FILL]
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.
- 10d ago First seen · 104 lines · 123 tokens per session scan A 104282f3996e
Systematic Review is a skill published in the GitHub repository SkillMedev/academic-researcher (3 stars, last pushed 2mo ago), licensed MIT. It adds 123 tokens to every session and 1,741 once invoked, about $0.0006 per session on Opus 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.
Other skills, from other repositories
Causal Inference
Selects and executes a credible causal identification strategy - RCT, natural experiment, difference-in-differences, regression discontinuity, instrumental variables, or matching - ranked by assumption strength, with a confounder checklist, falsification tests, and a defensible effect estimate. Use when someone asks…
Clinical Summary
Produces structured, faithful clinical summaries - either a patient-record summary with strict chronology, medication reconciliation, and expanded abbreviations, or a clinical-study summary with effect sizes, absolute risks, harms, and limitations. Use when someone asks "summarize this patient chart", "turn these…
Experiment Tracking
Sets up disciplined ML experiment tracking - run logging schemas, artifact versioning, naming conventions, and reproducibility standards - and produces the run-record template a team actually follows. Use when someone asks "how should we track our ML experiments", "why can't we reproduce this result", "how do I set up…
Government & Open Data
Use when a task needs official country-level statistics - "GDP / population / life expectancy / inflation / unemployment for country X over time", "compare indicator Y across countries", or EU-official figures ("Eurostat says…"). World Bank Indicators is the default (no key, every country, 1,400+ series back decades)…
Lab Report Writer
Generate professional lab reports for university courses, scientific research, engineering tests, and medical/material experiments. Supports three input modes (topic/raw data/draft improvement), auto-research with WebSearch, data tables & chart generation, error analysis, and output as docx/markdown. Use when writing…
manuscript-drafter
Draft long-form manuscript sections — abstract, introduction, related work, methods, results, discussion, limitations, conclusion — from a methodology document and an analysis report. Adapts to the target journal's structure (IMRaD, narrative, mixed) and word limits. Preserves the existing manuscript's voice, enforces…