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.
npx agentmods add commands/random6913/claude-code-superkit/pairgit clone --depth 1 https://github.com/RaNDoM6913/claude-code-superkitWrote 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/commands/random6913/claude-code-superkit/pair)<a href="https://agentmods.dev/commands/random6913/claude-code-superkit/pair"><img src="https://agentmods.dev/badge/commands/random6913/claude-code-superkit/pair.svg" alt="Measured on agentmods" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5 | $0.00018 | $0.01979 |
| Opus 5 | $0.00009 | $0.00989 |
| Sonnet 5 | $0.00004 | $0.00396 |
| Haiku 4.5 | $0.00002 | $0.00198 |
Grade A, and why
pair 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 today.
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.
How it starts
The opening of the file, as written. The whole thing — 210 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Pair Programming
Role
Run an interactive pair-programming session with the user in one of five modes. This command is a dialogue loop: work in small increments, wait for the user at every check-in, and continue until the user ends the session.
Hard Rules
- This is an interactive session — stop and WAIT for the user's reply at every check-in point. Never push through an entire task without user responses.
- Driver mode: never write more than ~50 lines of code without checking in.
- Navigator mode: suggest, don't rewrite — ask before making any edit yourself.
- Review mode: present ONE finding at a time; wait for the user's response before the next.
- Never manufacture issues — if code is clean, say "Looks good". 0 findings is a valid result.
- Debug mode: never guess — trace the actual code path; ask the user for runtime data you cannot see (logs, debugger output, network).
- When the user says "done" or "pause", emit the Session Summary (Output template below) before stopping. No silent exits.
Step 1 — Select Mode
Arguments: $ARGUMENTS
The first word is the mode; the remainder is the task description. If the first word is not a mode name, default to driver and treat the entire input as the task.
| Input | Mode | Who codes | Who reviews |
|---|---|---|---|
driver or empty |
Driver | Claude writes code | User guides direction |
navigator |
Navigator | User writes code | Claude reviews each change |
tdd |
TDD Ping-Pong | Alternating | Default: Claude writes tests, user implements (Option A) |
review |
Review | — | Claude reviews recent changes with dialogue |
debug |
Debug | Collaborative | Claude traces execution, user provides runtime context |
Done when: mode is selected.
Step 2 — Setup
- Read
CLAUDE.mdand relevantdocs/architecture/files (skip silently if absent). - Detect project stack (Go, TypeScript, Python, Rust).
- Identify the scope of work from the task description — ask ONE clarifying question if it is ambiguous.
- Announce the mode and its Rules block (from the matching Mode Playbook below).
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.
- today First seen · 210 lines · 18 tokens per session scan A 7f9ade8312d4
pair is a command published in the GitHub repository RaNDoM6913/claude-code-superkit (2 stars, last pushed 1mo ago), licensed MIT. It adds 18 tokens to every session and 1,979 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 2026-09-03.
Other commands, from other repositories
spec-implement
Take a spec under specs/ and produce an implementation plan, then pause for human-approved adversarial review before writing code. Used as the entry point for spec-first work in this repo.
dev
Use when starting any development task — bug fix, feature, or refactor.
learn-workspace-intent
Run Contorium BYOK workspace intent learning when API keys are configured.
setup-mcp-claude-code
Build and register the Contorium MCP server for Claude Code or Cursor Agent.
start-fresh-session
Start a fresh Contorium AI context session after a major task or workspace shift.
fix
Use for a fast bug fix with minimal ceremony (3 questions, TDD, done).