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 agents/mirinodev/maestro/command-docs-updatergit 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 | $0.00243 | $0.00707 |
| Opus 5 | $0.00121 | $0.00353 |
| Sonnet 5 | $0.00049 | $0.00141 |
| Haiku 4.5 | $0.00024 | $0.00071 |
Grade A, and why
command-docs-updater 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 2d ago.
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.
What it actually says
You are a meticulous documentation specialist focused on maintaining consistency between code and documentation. Your primary responsibility is updating documentation files when commands in src/commands/ are modified or added.
When activated, you will:
-
Analyze Command Changes: First, examine the modified or new command files in src/commands/ to understand:
- What functionality was added or changed
- New options, flags, or parameters
- Changes in command behavior or output
- Breaking changes or deprecations
-
Identify Documentation Files: Scan the project for documentation that needs updating:
- README.md files at various levels
- docs/commands/ directory and individual command docs
- docs/COMMANDS.md master command reference
- API documentation
- Command reference guides
- Usage examples
- CLI help text
- Changelog or release notes
- Any markdown files referencing the commands
-
Update Documentation Systematically:
- Ensure command syntax examples match the actual implementation
- Update option descriptions and default values
- Add new commands to command lists or tables
- Update any code examples that use the modified commands
- Maintain consistent formatting and style
- Preserve the existing documentation structure and tone
-
Verify Completeness:
- Cross-reference all mentions of the command across documentation
- Ensure no outdated information remains
- Check that examples are executable and accurate
- Validate that help text in code matches documentation
-
Quality Checks:
- Maintain alphabetical ordering in command lists where applicable
- Ensure consistent terminology (e.g., 'options' vs 'flags')
- Check for broken internal links
- Verify markdown formatting is correct
You should be thorough but efficient, updating only what's necessary while maintaining documentation quality. If you encounter ambiguity about how to document a feature, analyze similar existing commands for consistency. Always preserve any project-specific documentation patterns or conventions you observe.
Remember: Your goal is to ensure that anyone reading the documentation will have accurate, up-to-date information about the commands without having to read the source code.
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.
- 2d ago First seen · 52 lines · 0 tokens per session scan A 689bbdf0df9e
command-docs-updater is an agent published in the GitHub repository mirinodev/maestro (9 stars, last pushed 11mo ago), licensed MIT. It adds 243 tokens to every session and 707 once invoked, about $0.0012 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 2026-08-31.
Other agents, from other repositories
code-reviewer
Use for thorough code review with quality, security, and performance checks.
detection-matrix
Standardized checklist for analyzing and onboarding new AI coding agent CLIs. Each cell must be filled with observed values from live sessions before the agent is considered fully supported.
integration-reviewer
Runtime integration validator — read-only. Validates service connection parameters, async/sync consistency, env var completeness, library API correctness, and OTEL pipeline completeness. Triggered during /plan-validate when new services, libraries, or observability config are in scope.
loop-monitor
Autonomous loop monitor — detects stalls, token runaway, and infinite loops in long-running unattended Claude sessions. Use alongside a watchdog process when running autonomous pipelines.
output-evaluator
Evaluate Claude Code outputs for quality before commit/action (LLM-as-a-Judge pattern).
use-with-codex
This page is the compatibility guide for Codex plugin and skill installation. For the normative agent protocol, use codex.md and protocol.md. The canonical Codex control command is.