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/airmcp-com/mcp-standards/modesgit clone --depth 1 https://github.com/airmcp-com/mcp-standardsWrote 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/airmcp-com/mcp-standards/modes)<a href="https://agentmods.dev/commands/airmcp-com/mcp-standards/modes"><img src="https://agentmods.dev/badge/commands/airmcp-com/mcp-standards/modes.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 | $0.00000 | $0.01619 |
| Opus 5 | $0.00000 | $0.00809 |
| Sonnet 5 | $0.00000 | $0.00324 |
| Haiku 4.5 | $0.00000 | $0.00162 |
Grade A, and why
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.
This is a copy
100% identical to modes — 0 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
How it starts
The opening of the file, as written. The whole thing — 348 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Pair Programming Modes
Detailed guide to pair programming modes and their optimal use cases.
Driver Mode
In driver mode, you write the code while the AI acts as navigator.
Usage
claude-flow pair --start --mode driver
Responsibilities
You (Driver):
- Write the actual code
- Implement solutions
- Make immediate decisions
- Handle syntax and structure
AI (Navigator):
- Provide strategic guidance
- Spot potential issues
- Suggest improvements
- Review in real-time
- Track overall direction
Best For
- Learning new patterns
- Implementing familiar features
- Quick iterations
- Hands-on debugging
Example Session
claude-flow pair --start \
--mode driver \
--agent senior-navigator \
--review \
--verify
Commands in Driver Mode
/suggest - Get implementation suggestions
/review - Request code review
/explain - Ask for explanations
/optimize - Request optimization ideas
/patterns - Get pattern recommendations
Navigator Mode
In navigator mode, the AI writes code while you provide guidance.
Usage
claude-flow pair --start --mode navigator
Responsibilities
You (Navigator):
- Provide high-level direction
- Review generated code
- Make architectural decisions
- Ensure business requirements
AI (Driver):
- Write implementation code
- Handle syntax details
- Implement your guidance
- Manage boilerplate
- Execute refactoring
Best For
- Rapid prototyping
- Boilerplate generation
- Learning from AI patterns
- Exploring solutions
Example Session
claude-flow pair --start \
--mode navigator \
--agent expert-coder \
--test \
--language python
Commands in Navigator Mode
/implement - Direct implementation
/refactor - Request refactoring
/test - Generate tests
/document - Add documentation
/alternate - See alternative approaches
Switch Mode
Automatically alternates between driver and navigator roles.
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 · 348 lines · 0 tokens per session scan A 99c0d6ae0849
modes is a command published in the GitHub repository airmcp-com/mcp-standards (3 stars, last pushed 9mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,619 tokens. A static security scan graded it A with 0 findings. It is 100% identical to modes, differing in 0 lines, and is treated as a copy.
Other commands, from other repositories
todo
The quality-gated task list: tasks with real descriptions, testable acceptance criteria, and evidence — a task only closes when the controller agrees it is done.
restart
Prepare for a fresh session by saving all current context, progress, and decisions.
pr
Prepare and open a pull request the senior way: gate, template, scrubbed, everything visible.
plan
Turn an approved spec into an implementation plan an engineer with zero context could execute — with a quality controller that blocks placeholders and hollow tasks.
catchup
This command was migrated to a skill in Claude Code 2.1.3. See: examples/skills/catchup/SKILL.md.
audit
Onboard an existing codebase: every domain's checks over the whole tree, then a triaged plan to bring it in line.