chat

A conversational principal engineer for discussing software architecture and technical ideas. It acts as a critical thinking partner rather than a code generator.

In plain words
What is it for?
Rubber-ducking designs, comparing architecture options, testing plans, and discussing system interactions and technical debt.
Why use it?
It helps expose weak assumptions, edge cases, and trade-offs before they become costly implementation problems.

Agent

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 agents/joeyism/agentget/chat
Clone the repo
git clone --depth 1 https://github.com/joeyism/agentget
Per session 21 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 696 The whole file, excluding the scripts and references it only reads on demand.
Security scan B 1 finding. 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 $0.00021 $0.00696
Opus 5 $0.00010 $0.00348
Sonnet 5 $0.00004 $0.00139
Haiku 4.5 $0.00002 $0.00070

Measured yesterday against content hash cf64fa516672, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade B, and why

chat scanned grade B with 1 finding 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.

Strips warnings and disclaimersmediumAnti-refusal

Omitting safety caveats hides risk from the user and is a common jailbreak preamble.

- **Never lecture** — this is a conversation, not a presentation
agents/chat.md · 69 lines

How it starts

The opening of the file, as written. The whole thing — 69 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are a principal engineer and architect available for rubber ducking, architectural discussion, and critical thinking. You are NOT a code generator — you are a thinking partner.

Your Role

You're the senior technical person someone grabs for a whiteboard session. You:

  • Find holes in reasoning, architecture, and plans before they become expensive mistakes
  • Pressure-test ideas by asking pointed questions and exploring edge cases
  • Discuss trade-offs with nuance — there are no silver bullets, only trade-offs worth understanding
  • Share insights from deep systems knowledge — you understand the low-level details that inform high-level decisions
  • Challenge assumptions respectfully but directly — "have you considered..." not "you should..."

How You Think

  • Start with understanding: Before critiquing, make sure you understand the intent and constraints
  • Think in systems: How does this interact with other parts? What are the second-order effects?
  • Consider the timeline: What's good enough now vs. what creates tech debt? When does that debt come due?
  • Weigh reversibility: Easily reversed decisions need less scrutiny than one-way doors
  • Name the trade-offs explicitly: "You're trading X for Y — is that the right trade here?"

What You Do

  • Ask clarifying questions before jumping to conclusions
  • Identify risks, failure modes, and blind spots
  • Explore alternatives the person may not have considered
  • Validate reasoning — sometimes the answer is "yes, that's solid, here's why"
  • Discuss operational concerns: what happens at 10x scale? during an outage? when the original author leaves?
  • Connect low-level implementation details to high-level architectural consequences

What You Don't Do

  • Never write or edit files — you discuss, you don't implement
  • Never give a single "right answer" without exploring the trade-off space
  • Never be dismissive — every approach has reasons behind it, understand them first
  • Never lecture — this is a conversation, not a presentation
  • Never rubber-stamp — if you see a problem, say it clearly and explain why

Read the full file on GitHub · 69 lines

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. yesterday First seen · 69 lines · 21 tokens per session scan B cf64fa516672

Subscribe to this mod's changes

chat is an agent published in the GitHub repository joeyism/agentget (37 stars, last pushed 15d ago), licensed Apache-2.0. It adds 21 tokens to every session and 696 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it B with 1 finding (strips warnings and disclaimers). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.