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/Emlembow/skillsWrote 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/emlembow/skills/research-loop)<a href="https://agentmods.dev/plugins/emlembow/skills/research-loop"><img src="https://agentmods.dev/badge/plugins/emlembow/skills/research-loop/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/emlembow/skills/research-loop"><img src="https://agentmods.dev/badge/plugins/emlembow/skills/research-loop.svg" alt="Reviewed on agentmods" width="80" height="20"></a>Grade A, and why
research-loop 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.
What it actually says
{
"name": "research-loop",
"description": "Runs guarded metric-driven experiments with holdout gates, immutable evidence provenance, and replay-safe recovery.",
"version": "1.1.0",
"author": {
"name": "Emlembow"
},
"repository": "https://github.com/Emlembow/skills",
"license": "MIT"
}
What it installs
The manifest is a name and a version. 1 skill travel with it, and installing the plugin installs all of them — 114 tokens a session between them. Each is measured on its own page, and each can be installed alone.
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 · 11 lines scan A 7ccd60c83d8b
research-loop is a plugin published in the GitHub repository Emlembow/skills (2 stars, last pushed 9d ago), licensed MIT. 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
adversarial-spec
Iteratively refine product specs through multi-model debate until consensus. Claude actively participates alongside GPT, Gemini, Grok, and other models. Includes interview mode, early agreement verification, and optional Telegram integration.
pdf-guard
Prevents PDF context crashes with extraction enforcement and cumulative read tracking.
diligence
Make Claude do a better job of providing verifiably correct technical information by default.
section-508
Expert Section 508 compliance advisor for US federal ICT accessibility — VPAT/ACR completion, WCAG 2.0 AA audits, remediation planning, PDF accessibility, procurement language, keyboard and screen reader testing, undue burden assessments, and agency compliance workflows.
suede-code
Code quality subset: one-pass review plus an A-F ship verdict (suede-code), deep findings with TypeScript, React, Next.js, OWASP, and database checklists (suede-code-review), a grade-only verdict with instant-F triggers and grade caps (suede-code-grader), and CI branch protection that gates the merge (suede-ci-gate).
skill-creator-pro
Create, test, and iteratively improve Claude Code skills with the official lean coaching loop, an eval harness for benchmarking with variance analysis, automated description-trigger optimization, and a user-started autonomous output-quality optimizer.