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/urav06/dialecticWrote 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/urav06/dialectic/claude)<a href="https://agentmods.dev/plugins/urav06/dialectic/claude"><img src="https://agentmods.dev/badge/plugins/urav06/dialectic/claude/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/urav06/dialectic/claude"><img src="https://agentmods.dev/badge/plugins/urav06/dialectic/claude.svg" alt="Reviewed on agentmods" width="80" height="20"></a>Grade A, and why
dialectic 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": "dialectic",
"description": "A computational argumentation system for structured AI debates using Toulmin argument framework. Create debate motions, run multi-exchange debates between AI agents, and generate comprehensive reports with argument visualization.",
"version": "0.1.0",
"author": {
"name": "Urav Maniar",
"email": "[email protected]"
},
"homepage": "https://github.com/urav06/dialectic",
"repository": "https://github.com/urav06/dialectic",
"license": "MIT",
"keywords": [
"debate",
"philosophy",
"toulmin",
"reasoning",
"critical-thinking",
"logic",
"argumentation"
]
}
What it installs
The manifest is a name and a version. 1 skill, 3 commands, 2 agents travel with it, and installing the plugin installs all of them — 94 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 · 22 lines scan A 53d8a7767d2c
dialectic is a plugin published in the GitHub repository urav06/dialectic (6 stars, last pushed 10mo 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
lid-experimental
Experimental LID skills with opt-in installation and explicit lifecycle (promotion or retirement). Layers on top of linked-intent-dev and arrow-maintenance.
polygraph
A polygraph for your state machine. The agent does the hard part for you: it instruments your code, builds any test doubles needed to run it, and captures real execution traces — then has an LLM derive a transition-function spec from the source (default: a SAM v2 strict-profile module with named…
superstack
An agent-based software-development system that guides work from a short request to a tested, demonstrated piece of software. It uses checkpoints for planning and verification and explains conclusions in plain language.
compact-manager
Warns the main session as its own context fills, captures a wake packet before compaction, and reorients the session after it — so an autonomous orchestrator survives past one context window.
great-pm
A full product team for a solo PM or founder. Specialist agents run the product loop — discovery, strategy, prioritization, specs, launch, measurement — while the human confirms a small number of gates.
conductor
Reliable verified commands for Claude Code. Each tool routes through a deterministic verify + retry + fallback loop, and stochastic commands run hermetic claude sub-calls so ambient context can't pollute results.