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.
git clone --depth 1 https://github.com/88plug/scientific-methodWrote 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/plugins/88plug/scientific-method/scientific-method)<a href="https://agentmods.dev/plugins/88plug/scientific-method/scientific-method"><img src="https://agentmods.dev/badge/plugins/88plug/scientific-method/scientific-method/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/plugins/88plug/scientific-method/scientific-method"><img src="https://agentmods.dev/badge/plugins/88plug/scientific-method/scientific-method.svg" alt="Reviewed on agentmods" width="80" height="20"></a>Grade A, and why
scientific-method 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.
The source is not reproduced here
A licence we could not identify
The repository carries a LICENSE file, but it is custom or dual enough that GitHub cannot name it and neither can this catalogue. Unknown terms are not permission, so the body is not copied here. Read the licence at the source and decide for yourself.
What it installs
The manifest is a name and a version. 1 skill, 7 commands, 5 agents, 1 hook travel with it, and installing the plugin installs all of them — 1,167 tokens a session between them. Each is measured on its own page, and each can be installed alone.
- Skill scientific-method A 440 tokens
- Command council A 24 tokens
- Command peer-review A 23 tokens
- Command falsify A 12 tokens
- Command invent A 26 tokens
- Command investigate A 15 tokens
- Command ledger A 17 tokens
- Command verdict A 16 tokens
- Agent experiment-designer A 122 tokens
- Agent peer-reviewer A 141 tokens
- Agent refuter A 111 tokens
- Agent council-member A 121 tokens
- Agent meta-reviewer A 99 tokens
- Hook SessionStart A not measured
What ships with it
1 file beside plugin.json in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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 First seen · 36 lines scan A ec7f62aabc6f
scientific-method is a plugin published in the GitHub repository 88plug/scientific-method (1 stars, last pushed 1mo ago), with no licence file. Its token cost is not measured: this kind of file is read by the harness, not the model. 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 plugins, from other repositories
research-poster
Turn a PDF abstract into a polished, fully-editable scientific conference poster (.pptx + PDF + preview) with native editable PowerPoint charts, verified citations, big readable typography, and a render-and-QA loop.
ml-intern
Paper-grounded ML research and open-problem attack for Claude Code. Crawls arXiv and citation graphs, reads whole papers in parallel subagents, mechanically verifies every quote, archives a model's real code locally and grounds later sessions in it, and runs falsifiable attacks on hard unsolved problems.
clinical-trial-design
End-to-end clinical trial design assistant. R-backed computation, MCP tools, skill for design reasoning. Covers Phase 2 and Phase 3 confirmatory designs.
qector
Local QECTOR quantum error correction plugin for Claude Code and Claude Desktop with strict math skills, focused agents, and qector-decoder-v3 MCP servers.
aej-applied-economics-skills
Agent skill stack for manuscripts targeted at the American Economic Journal: Applied Economics (AEJ: Applied) — the American Economic Association's quarterly journal for empirical applied microeconomics with credible causal identification, spanning labor, development, health, education, public, urban, environmental…
recall
Durable, fully-local project memory for Claude Code. Logs every session to .recall/history.md and condenses it into .recall/context.md with a local Python summarizer (TF-IDF + TextRank) — no API key, no external model, nothing leaves your machine. New sessions resume from the saved context.