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/bengous/claude-code-pluginsWrote 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/bengous/claude-code-plugins/understanding)<a href="https://agentmods.dev/plugins/bengous/claude-code-plugins/understanding"><img src="https://agentmods.dev/badge/plugins/bengous/claude-code-plugins/understanding/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/bengous/claude-code-plugins/understanding"><img src="https://agentmods.dev/badge/plugins/bengous/claude-code-plugins/understanding.svg" alt="Reviewed on agentmods" width="80" height="20"></a>Grade A, and why
understanding 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 yesterday.
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": "understanding",
"version": "1.1.3",
"description": "Understand a topic, a bug, or a Claude Code workflow: minimal explanations, root-cause diagnosis, execution traces",
"author": {
"name": "Augustin BENGOLEA",
"email": "[email protected]"
},
"homepage": "https://github.com/bengous/claude-code-plugins/tree/main/understanding",
"repository": "https://github.com/bengous/claude-code-plugins",
"license": "MIT",
"keywords": [
"explain",
"troubleshoot",
"diagnosis",
"pedagogy",
"investigation",
"workflow-trace"
]
}
What it installs
The manifest is a name and a version. 3 commands travel with it, and installing the plugin installs all of them — 61 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.
- yesterday Changed ada7b3c3e436
- 26d ago Changed 9de968012a2a
- 27d ago Changed 0f01eebf8980
- 1mo ago Changed · +1 lines 659c1cf05a66
- 1mo ago First seen · 20 lines scan A fa62382aede3
understanding is a plugin published in the GitHub repository bengous/claude-code-plugins (5 stars, last pushed today), 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 2026-09-03.
Other plugins, from other repositories
github-actions
GitHub Actions CI tools: investigate failing runs via gh + a structured snapshot helper.
devflow
Development workflow skills: scope triage, planning, plan execution inline or through subagents, test-driven development, root-cause debugging, code review, verification, and branch finishing.
unslop
Review and revise writing, code and websites that read as generic AI output. Three scanners for prose, source code and web design, guidance for what a scanner can't see, and a method for building a voice profile from your own writing.
quiz-me
Gates code changes behind an interactive quiz: Claude investigates, tests your understanding of root cause and fix, and only implements once you pass.
duet
Claude Code plugin for reflection, code quality, writing, and design.
humanizer
Rewrite AI-sounding text so it reads like the writer without changing what it says.