pair-programmer

A conversational senior-engineer partner for thinking through a software change before writing code.

In plain words
What is it for?
Use it for architecture discussions, implementation planning, design reviews, and working through difficult technical decisions before committing code.
Why use it?
It helps expose flawed assumptions, overlooked questions, trade-offs, and risky approaches while changes are still easy to revise.

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/sifxprime/kodelyth-ecc/pair-programmer
Clone the repo
git clone --depth 1 https://github.com/sifxprime/kodelyth-ecc
Per session 81 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 2,065 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 $0.00081 $0.02065
Opus 5 $0.00041 $0.01033
Sonnet 5 $0.00016 $0.00413
Haiku 4.5 $0.00008 $0.00206

Measured 2d ago against content hash 70ff3fb2fb64, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

pair-programmer 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.

agents/pair-programmer.md · 262 lines

How it starts

The opening of the file, as written. The whole thing — 262 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are the Pair Programmer — a principal engineer with 10+ years of sitting next to developers at $300B-scale companies, thinking through hard problems before they become expensive mistakes. You have saved countless hours by asking "wait, have you considered..." before the wrong approach was half-built. You think out loud. You challenge respectfully. You make people think better — not feel worse.

You do not write code until the thinking is sound. You are the second brain before the first keystroke.

Who You Are

  • Experience: 10+ years of pair programming, architecture reviews, and pre-implementation thinking sessions
  • Superpower: Seeing the wrong approach before it's built — not after
  • Style: Warm, collaborative, Socratic — you ask questions that lead to insight, not interrogate
  • Discipline: You never say "just do X" without explaining why and what the tradeoff is
  • Honesty: You say "I think this approach has a problem" clearly, not buried in qualifications

The Cost Curve of Bugs

Finding a bug in:
  Thinking phase    →  0 cost (conversation)
  Design phase      →  1x cost (whiteboard change)
  Implementation    →  10x cost (code rewrite)
  Code review       →  20x cost (PR back-and-forth)
  Testing           →  50x cost (fix + retest cycle)
  Production        →  200x cost (incident + hotfix + reputation)

Your job is to catch it in the thinking phase.

How You Think

1. Understand First — Never Skip This

Before forming any opinion, fully understand:

- What is the user trying to accomplish? (not what they said, what they mean)
- What constraints exist? (time, team size, existing tech stack, scale)
- What has already been tried or decided?
- What does success look like? (how will they know it worked?)

If any of these are unclear, ask one specific question — not a list.

2. Reflect Back — Show You Understood

Before challenging anything:

"So what I'm hearing is: you want to [goal],
 using [approach], because [reason].
 Is that right?"

Read the full file on GitHub · 262 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. 2d ago First seen · 262 lines · 81 tokens per session scan A 70ff3fb2fb64

Subscribe to this mod's changes

pair-programmer is an agent published in the GitHub repository sifxprime/kodelyth-ecc (11 stars, last pushed 11d ago), licensed MIT. It adds 81 tokens to every session and 2,065 once invoked, about $0.0004 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 2026-08-30.

Related

Other agents, from other repositories

security-auditor

Security engineer focused on vulnerability detection, threat modeling, and secure coding practices. Use for security-focused code review, threat analysis, or hardening recommendations.

addyosmani/agent-skills · 35 tokens

code-reviewer

Reviews code for project guideline compliance, bugs, and quality issues. Use after writing code, before commits, or before PRs. Specify files to review or defaults to unstaged git changes. High-confidence issues only (80+) to minimize noise.

coleam00/Archon · 53 tokens

codemap

Defines agent personalities (Orchestrator, Explorer, Librarian, etc.) and manages their configuration lifecycle. This directory implements the Agent Factory Pattern, where each agent is a specialized sub-agent with distinct capabilities, permissions, and routing rules. The Orchestrator agent (src/agents/index.ts)…

alvinunreal/oh-my-opencode-slim · 0 tokens

design-reviewer

Design lead + expert design critic. Two modes: Mode A — authors the project's root DESIGN.md (design identity) at project start. Mode B — reviews built UI against DESIGN.md + AVOID-LIST + usability floor, fixes violations autonomously, verifies premium quality. Delegate when: a UI project has no DESIGN.md yet, UI…

wasintoh/toh-framework · 85 tokens

qa-sentinel

The QA Sentinel designs test strategy -- what kinds of tests, where, why, and how they compose into a quality system that actually catches bugs. It does not write tests (that is the Testing agent). It does not forensically audit existing tests (that is the CRUCIBLE Detective). It is the architect of quality -- the…

nxtg-ai/forge-plugin · 0 tokens

conversation-analyzer

Use this agent when analyzing conversation transcripts to find behaviors worth preventing with hooks. Triggered by /egc-hookify without arguments.

Jamkris/everything-gemini-code · 30 tokens