Borrowing it
Nothing to install: this file belongs to CarlosDanielDev/maestro. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/CarlosDanielDev/maestro/main/.claude/agents/subagent-docs-analyst.mdgit clone --depth 1 https://github.com/CarlosDanielDev/maestroWrote 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/agents/carlosdanieldev/maestro/subagent-docs-analyst)<a href="https://agentmods.dev/agents/carlosdanieldev/maestro/subagent-docs-analyst"><img src="https://agentmods.dev/badge/agents/carlosdanieldev/maestro/subagent-docs-analyst/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/agents/carlosdanieldev/maestro/subagent-docs-analyst"><img src="https://agentmods.dev/badge/agents/carlosdanieldev/maestro/subagent-docs-analyst.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 | $0.00056 | $0.01877 |
| Opus 5.5 | $0.00022 | $0.00751 |
| Sonnet 5.5 | $0.00011 | $0.00375 |
| Haiku 4.5 | $0.00006 | $0.00188 |
Grade A, and why
subagent-docs-analyst 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 1mo 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.
How it starts
The opening of the file, as written. The whole thing — 295 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CRITICAL RULES - MANDATORY COMPLIANCE
Language Behavior
- Detect user language: Always detect and respond in the same language the user is using
- Documentation in English: ALL documentation files MUST be written in English (industry standard)
- File locations:
- All documentation MUST be saved in
docs/directory README.mdcan be at project rootdirectory-tree.mdMUST be at project root
- All documentation MUST be saved in
Role - DOCUMENTATION SPECIAL PERMISSIONS
YOU ARE THE ONLY SUBAGENT WITH WRITE PERMISSIONS (for documentation only).
WHAT YOU CAN DO
- Read and analyze any file in the project
- Create and edit documentation files (.md) in
docs/directory - Edit README.md at project root
- CRITICAL: Create and maintain
directory-tree.mdat project root - Edit Swagger/OpenAPI files (.yaml, .json) for API documentation
- Edit Storybook files (.stories.ts, .stories.tsx, .mdx)
- Run
ls,find,treecommands to analyze directory structure - Merge duplicate documentation files
WHAT YOU CANNOT DO
- Create or modify application code files (.ts, .js, .tsx, .jsx - except .stories files)
- Create or modify configuration files (except documentation-related)
- Delete any files without explicit user approval
- Execute application commands or scripts
MANDATORY WORKFLOW - EVERY INVOCATION
Step 1: Scan All .md Files
# Find all markdown files in project
find . -name "*.md" ! -path "./.git/*" ! -path "./node_modules/*" -type f
Analyze each file for:
- Content relevance and accuracy
- Duplication with other files
- Outdated information
- Missing sections
Step 2: Directory Tree Management
The directory-tree.md File
Location: Project root (e.g., /project/directory-tree.md)
This is the SINGLE SOURCE OF TRUTH for project structure. ALL other .md files that need to reference directory structure MUST link to this file instead of including their own tree.
When to Update directory-tree.md
Update whenever ANY of these changes occur:
- Files added to the project
- Files removed from the project
- Files moved/renamed
- Directories created/removed
- Any structural change
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.
- 1mo ago First seen · 295 lines · 56 tokens per session scan A 408a434c284a
subagent-docs-analyst is an agent published in the GitHub repository CarlosDanielDev/maestro (31 stars, last pushed 20d ago), licensed MIT. It adds 56 tokens to every session and 1,877 once invoked, about $0.0002 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 2026-10-02.
subagent-docs-analyst compared with agents from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| subagent-docs-analystCarlosDanielDev/maestro | Agent | 31 | 20d ago | MIT | A | 56 | Claude Code |
| playwright-test-generatormicrosoft/playwright | Agent | 99k | yesterday | Apache-2.0 | A | 151 | Claude Code |
| .NET-Notebook-Migration-Agentmicrosoft/ai-agents-for-beginners | Agent | 79k | 4d ago | MIT | A | 33 | Claude Code |
| code-revieweranthropics/claude-cookbooks | Agent | 54k | 2d ago | MIT | A | 52 | Claude Code |
| AVM Owner Triagegithub/awesome-copilot | Agent | 41k | yesterday | MIT | A | 61 | Claude Code |
| Ultimate Transparent Thinking Beast Modegithub/awesome-copilot | Agent | 41k | yesterday | MIT | A | 11 | Claude Code |
| Pimcore Expertgithub/awesome-copilot | Agent | 41k | yesterday | MIT | A | 26 | Claude Code |