Skip to content
Agentmart
Submit a tool

pair-programmer

Evidence-based code review and architecture assessment.

Skill by krzysztofbury

IndexedMIT
Write a review

Chalk Labs

Need help deploying pair-programmer?

Chalk Labs sets up agents like this inside real teams: connected to your tools, tested on your data, with a human in the loop where it matters.

Book a call

Install

Works with Claude Code, Claude apps, Codex, Cursor, Gemini CLI, GitHub Copilot, VS Code, OpenCode, Goose, Windsurf. Read the repository before you give any tool access to your data.

npx agentmarket install skill/krzysztofbury-pair-programmer

Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.

Get the weekly diff

The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.

We use your email only for this newsletter. Privacy

About

Evidence-based code review and architecture assessment. Use for requested engineering reviews, design trade-offs, or difficult debugging investigations.

Use cases: design

No reviews yet. Installed it? Reviews come from verified installers only. How reviews work

Permissions

What this skill can do and what it asks for, from its SKILL.md. Checked Oct 25, 2026.

Tools
No tools found
Secrets
None asked for
Install scripts
None found

Network hosts it talks to 1

  • codeload.github.com · found in install command

Files it touches

  • ~/.claude/skills/pair-programmer

What's inside

Skill name
pair-programmer
Description
Evidence-based code review and architecture assessment. Use for requested engineering reviews, design trade-offs, or difficult debugging investigations.
License
MIT
Instructions
66 lines in SKILL.md · view on GitHub

Files (1)

  • SKILL.md

SKILL.md (first lines)

# Pair Programmer

Use this priority order: Safety, Performance, Developer Experience.

## Code Review

1. Read the relevant implementation, tests, and configuration before reporting
   findings.
2. Lead with concrete correctness, security, data-loss, concurrency, and
   resource-bound risks.
3. Then assess meaningful performance risks and maintainability.
4. Cite the file and line, explain the impact, and offer a grounded fix.
5. Report no findings when the evidence does not support one.

## Debugging

1. Gather the error, reproduction conditions, and relevant code.
2. State a falsifiable hypothesis before changing anything.
3. Verify the hypothesis with a focused test, trace, or inspection.
4. Make the smallest correct change when implementation is authorized.
5. Add or update a regression test when it protects the failing behavior.

## Architecture

- Do not assume the stack, scale, latency target, or data sensitivity.
- Surface decisive trade-offs: simplicity versus flexibility, latency versus
  cost, and safety versus delivery speed.
- Prefer a reversible first step and state the conditions that require a more
  complex design.

## Checklist

### Safety

1. Control flow has defined completion or cancellation behavior.
2. Bound queues, retries and external work where exhaustion or hangs are risks.
3. Runtime input and state use explicit validation and error handling, not
   assertions that can be disabled.
4. Error paths preserve context without leaking secrets or personal data.
5. Concurrent access, idempotency, and partial failures are considered.
6. Destructive operations stay within the user's authorized scope.

### Performance

7. I/O and remote work are batched where it reduces real cost.
8. Proven hot paths avoid unnecessary allocation, queries, and serialization.
9. Caches, limits, and pagination have invalidation and failure behavior.

### Developer Experience

10. Names communicate intent and units where relevant.
11. Functions have focused responsibilities and a readable control flow.
12. Comments explain non-obvious decisions.
13. The project formatter, type checker, linter, and relevant tests pass.

## Operating Rules

- Reviews and explanations are read-only. A request to fix or implement
  authorizes the scoped change without a second approval ritual.
- Follow adopted project conventions. Report style findings only when tied to
  a project rule or a concrete maintenance problem.
- Verify libraries and APIs against current official documentation when their
  behavior may have changed.
- Do not invent file paths, metrics, test results, or project conventions.

From krzysztofbury/llm-powerup, MIT.

More from krzysztofbury/llm-powerup

Signals

Stars
0
Forks
0
Open issues
0
Last commit (this folder)
Oct 7, 2026 (23 days ago)

From GitHub (fetched Oct 24, 2026).

Details

License
MIT
First seen
Oct 24, 2026
Last checked
Oct 24, 2026

More from krzysztofbury

Done for you

Rather not set it up yourself?

Chalk Labs scopes, builds and runs agents for your team: the task audit, the eval harness, the integrations and the weekly ops report. Fixed scope, priced before we start.

See how we build AI agents →Read the case studies

Chalk Labs is a two-founder AI and growth studio. We build AI agents, CRMs and MVPs for Web3 and AI companies, and have shipped 50+ product and token launches.

launches shipped
50+
launches shipped
media placements
500+
media placements
founders on every account
2
founders on every account

Press we've placed: Forbes · CoinDesk · Decrypt · Cointelegraph · The Block

Rahil Jain, Co-founder, Chalk Labs. Ex-Goldman Sachs engineer. You talk to the person who builds it.

Get pair-programmer running in your business

Tell us what you want to automate. A founder replies within one working day with a plan, not a pitch deck.

Goes to the Chalk Labs founders, not the newsletter. Privacy

Need help deploying pair-programmer?

CallGet help
Cite this page

pair-programmer skill. Agent Mart. https://agentmart.dev/skills/krzysztofbury-pair-programmer (last updated 2026-10-24)