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.
git clone --depth 1 https://github.com/monoes/monomindWrote 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/monoes/monomind/modes)<a href="https://agentmods.dev/commands/monoes/monomind/modes"><img src="https://agentmods.dev/badge/commands/monoes/monomind/modes/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/commands/monoes/monomind/modes"><img src="https://agentmods.dev/badge/commands/monoes/monomind/modes.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.00026 | $0.00805 |
| Opus 5.5 | $0.00010 | $0.00322 |
| Sonnet 5.5 | $0.00005 | $0.00161 |
| Haiku 4.5 | $0.00003 | $0.00081 |
Grade A, and why
pair:modes 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 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.
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 — 123 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Pair Programming Modes
Different collaboration patterns for different goals. Choose based on what you're trying to accomplish.
Driver Mode — You Write, Claude Reviews
You do the coding. Claude watches, suggests, and catches issues in real time.
Start it:
"I'm implementing [feature]. Watch what I'm building and review each piece as I share it. Point out issues, security problems, and improvements."
Best for:
- Learning new patterns (you get hands-on + feedback)
- Implementing features you understand but want reviewed
- Debugging when you have a hypothesis to test
Effective prompts during driver mode:
- "Here's what I wrote — what do you think?"
- "I'm about to add validation here. Any pitfalls?"
- "Is this the right pattern for this situation?"
- "Review this function before I move on."
Navigator Mode — Claude Writes, You Guide
Claude does the coding. You provide direction, review output, and control architecture decisions.
Start it:
"Implement [feature]. I'll guide the direction and review each section before you move on. Start with [specific first piece]."
Best for:
- Rapid prototyping
- Boilerplate and scaffolding
- Exploring approaches you haven't used before
- Getting unstuck quickly
Effective prompts during navigator mode:
- "Implement X. Use [pattern/library]."
- "That's good but change [specific thing]."
- "Before writing the next piece, explain your approach."
- "Show me an alternative approach to this."
TDD Mode — Tests First
Write failing tests, then implement just enough to pass, then refactor.
Start it:
"We're doing TDD for [feature]. Write the failing tests first, explain what each test covers, then I'll implement. We refactor together after tests pass."
The cycle:
- Claude writes a failing test — you understand it
- You implement minimal passing code
- Claude reviews the implementation
- Together you refactor
- Repeat
Invoke the TDD skill for full workflow:
Skill("mastermind-debug") # Phase 4: failing test first, then Red-Green-Refactor
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.
- yesterday First seen · 123 lines · 26 tokens per session scan A 24eff31ef141
pair:modes is a command published in the GitHub repository monoes/monomind (23 stars, last pushed yesterday), licensed Apache-2.0. It adds 26 tokens to every session and 805 once invoked, about $0.0001 per session on Opus 5.5. 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 2026-10-26.
Other commands, from other repositories
bugfix
TDD-driven bugfix workflow: tester writes failing test (RED) → developer fixes (GREEN) → developer refactors (REFACTOR) → reviewer validates. Accepts issue number, description, or both. Asks before pushing and creating a PR; --no-pr commits locally without asking.
refactor-sprint
Parallel refactor sprint — fires refactor-cleaner + code-simplifier + type-design-analyzer + tdd-guide simultaneously. Full cleanup in one pass.
session-loop
Automated task consumption loop — parallel TDD implementation, testing, and review per session (session manager procedure).
run
Comprehensive code review using specialized agents — orchestrates code, comments, tests, errors, types, and simplify agents sequentially.
test-coverage-review
You are an expert QA engineer and testing specialist with deep expertise in test-driven development, code coverage analysis, and quality assurance best practices. Your role is to conduct thorough reviews of test implementations to ensure comprehensive coverage and robust quality validation.
checklist
Generate a custom checklist for the current feature based on user requirements.