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/mirinodev/maestro/execgit clone --depth 1 https://github.com/mirinodev/maestroWhat 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 | $0.01106 |
| Opus 5 | $0.00000 | $0.00553 |
| Sonnet 5 | $0.00000 | $0.00221 |
| Haiku 4.5 | $0.00000 | $0.00111 |
Grade B, and why
exec scanned grade B with 1 finding 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.
Unrestricted tool accessmediumExcessive agency
A wildcard tool grant or "run any command" leaves no least-privilege boundary at all.
The `exec` command allows you to run any command within the context of one or multiple worktrees without entering their shell environment. This is particularly useful for running build commands, tests, or any other opera How it starts
The opening of the file, as written. The whole thing — 173 lines — stays where its author put it; the contents beside it link to each section on GitHub.
🔸 exec
Execute commands in specific or all orchestra members.
Overview
The exec command allows you to run any command within the context of one or multiple worktrees without entering their shell environment. This is particularly useful for running build commands, tests, or any other operations across your orchestra members.
Usage
mst exec [branch-name] <command> [options]
mst e [branch-name] <command> [options] # alias
Options
-s, --silent- Suppress command output-a, --all- Execute on all orchestra members--fzf- Interactively select orchestra member with fzf-t, --tmux- Execute in new tmux window--tmux-vertical,--tmux-v- Execute in vertical split pane--tmux-horizontal,--tmux-h- Execute in horizontal split pane
Examples
Basic Usage
Execute a command in a specific orchestra member:
# Run tests in feature branch
mst exec feature/awesome npm test
# Build project
mst exec feature/ui npm run build
# Check git status
mst exec hotfix/urgent git status
Execute in All Orchestra Members
Run the same command across all worktrees:
# Install dependencies in all (various formats)
mst exec --all npm install
mst exec -a npm install
# Run linting in all
mst exec --all npm run lint
mst exec -a npm run lint
# Check git status of all
mst exec --all git status --short
mst exec -a git status --short
# Note: When using -a/--all flag, the branch name argument is optional.
# Both of these work:
mst exec dummy npm test --all # 'dummy' is ignored
mst exec -a npm test # More concise
Interactive Selection with fzf
Select which orchestra member to execute in:
# Select and run dev server
mst exec --fzf npm run dev
# Select and run tests
mst exec --fzf npm test
tmux Integration
Execute commands in tmux panes for better workflow:
# Open in new tmux window
mst exec feature/api --tmux npm run watch
# Open in vertical split (side by side)
mst exec feature/ui --tmux-v npm run dev
# Open in horizontal split (top and bottom)
mst exec backend --tmux-h npm run test:watch
# Combine with fzf selection
mst exec --fzf --tmux npm start
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 · 173 lines · 0 tokens per session scan B be80af76444e
exec is a command published in the GitHub repository mirinodev/maestro (9 stars, last pushed 11mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,106 tokens. A static security scan graded it B with 1 finding (unrestricted tool access). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other commands, from other repositories
audit-agents-skills
Audit quality of agents, skills, and commands in a Claude Code project.
security-audit
Comprehensive security audit of your project AND Claude Code configuration. Analyzes secrets exposure, injection surfaces, dependencies, hook security, and produces a scored security posture assessment.
audit-quiz-coverage
Find quiz coverage gaps from recent guide/CHANGELOG/CC-releases changes and propose new questions.
worktree
Create a git worktree for isolated feature/fix work.
sync
Check guide/landing synchronization status.
version
Display current guide and Claude Code versions.