dialectic

A command that requests a structured UNITARES review for the current AI agent. A dialectic review is a formal exchange used to examine a disagreement, decision, or concern from more than one role.

In plain words
What is it for?
Use it to start a dialectic session for a disagreement, a high-stakes decision, or a request for independent verification, then report whether it was created and its session ID.
Why use it?
It creates a recorded review when the agent needs peer verification or wants to question a verdict. The reason for requesting it helps frame the review appropriately.

Command

Install

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.

agentmods
npx agentmods add commands/cirwel/unitares/dialectic
Clone the repo
git clone --depth 1 https://github.com/cirwel/unitares
Per session 11 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 113 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00011 $0.00113
Opus 5 $0.00005 $0.00056
Sonnet 5 $0.00002 $0.00023
Haiku 4.5 $0.00001 $0.00011

Measured 2d ago against content hash 4ee5359be4b0, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

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 2d 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.

commands/dialectic.md · 10 lines

What it actually says

Call request_dialectic_review for the current agent. If the user didn't provide a reason, ask for a brief explanation of why they want a review (e.g., "disagreement with verdict", "want peer verification", "high-stakes decision").

Report the result — whether a dialectic session was created and the session ID.

If the user is trying to answer an existing dialectic session rather than create one, use /dialectic-respond instead.

Changes

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.

  1. 2d ago First seen · 10 lines · 11 tokens per session scan A 4ee5359be4b0

Subscribe to this mod's changes

dialectic is a command published in the GitHub repository cirwel/unitares (4 stars, last pushed 2d ago), licensed Apache-2.0. It adds 11 tokens to every session and 113 once invoked, about $0.0001 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.