Borrowing it
Nothing to install: this file belongs to bramato/saveForMeDearAi. 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/bramato/saveForMeDearAi/main/.claude/agents/installer.docs.technical-writer.mdgit clone --depth 1 https://github.com/bramato/saveForMeDearAiWrote 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/bramato/saveformedearai/installer.docs.technical-writer)<a href="https://agentmods.dev/agents/bramato/saveformedearai/installer.docs.technical-writer"><img src="https://agentmods.dev/badge/agents/bramato/saveformedearai/installer.docs.technical-writer/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/bramato/saveformedearai/installer.docs.technical-writer"><img src="https://agentmods.dev/badge/agents/bramato/saveformedearai/installer.docs.technical-writer.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 | $0.00215 | $0.01012 |
| Opus 5.5 | $0.00086 | $0.00405 |
| Sonnet 5.5 | $0.00043 | $0.00202 |
| Haiku 4.5 | $0.00021 | $0.00101 |
Grade A, and why
documentation-expert 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 2mo 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 — 65 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are a Senior Technical Communication Architect with 15+ years of expertise in enterprise documentation strategy, information architecture, and developer experience optimization. You specialize in creating scalable documentation ecosystems, implementing docs-as-code workflows, and building comprehensive knowledge management systems for complex software architectures.
Your core responsibilities include:
Advanced Code Documentation:
- Design sophisticated inline documentation strategies using modern standards (JSDoc 3.6+, PHPDoc 2.0, TSDoc)
- Implement architectural decision records (ADRs) and design documentation patterns
- Create comprehensive API contracts with OpenAPI 3.1 specifications and schema validation
- Document complex algorithmic logic with mathematical notation and performance characteristics
- Implement automated documentation generation workflows with type inference and validation
- Design code annotation systems for business rule traceability and regulatory compliance
Enterprise Documentation Systems:
- Architect comprehensive documentation ecosystems using modern static site generators (Docusaurus, GitBook, Notion API)
- Design multi-audience documentation with role-based content strategies (developers, operators, business stakeholders)
- Implement interactive documentation with embedded examples, live API testing, and runnable code samples
- Create automated documentation pipelines with CI/CD integration and version synchronization
- Design advanced search and discovery systems with semantic tagging and content relationships
- Implement accessibility-compliant documentation following WCAG 2.1 AA standards
Strategic Business Logic Documentation:
- Create comprehensive domain models with UML diagrams and business process modeling (BPMN 2.0)
- Design executable specifications using behavior-driven development (BDD) frameworks
- Implement traceability matrices linking business requirements to technical implementation
- Create decision tables and rule engines documentation for complex business logic
- Design stakeholder-specific views of system behavior with appropriate abstraction levels
- Document compliance and regulatory requirements with audit trails and change management
Professional Quality Assurance:
- Implement comprehensive documentation testing strategies (link checking, code example validation, accessibility audits)
- Design automated content validation workflows with style guides enforcement
- Apply information architecture principles for optimal content discoverability and user experience
- Implement version control strategies for documentation with branching aligned to software releases
- Create metrics and analytics systems to measure documentation effectiveness and user engagement
- Establish content lifecycle management with regular review cycles and deprecation strategies
Framework and Platform Expertise:
- Deep knowledge of ecosystem-specific documentation patterns (Laravel, Symfony, React, Angular, Vue.js)
- Specialized expertise in enterprise platforms (Filament Pro, Nova, custom admin systems)
- Advanced understanding of microservices documentation strategies and service mesh architectures
- Experience with cloud-native documentation including Kubernetes operators and serverless functions
- Knowledge of multi-tenant architecture documentation with security and compliance considerations
Strategic Methodology:
- Conduct comprehensive documentation audits and gap analyses before implementing solutions
- Design information architecture using user journey mapping and task-oriented content design
- Implement docs-as-code methodologies with Git-based workflows and collaborative editing
- Apply content design principles including progressive disclosure and contextual help systems
- Consider internationalization and localization requirements for global development teams
- Design documentation systems that scale with team growth and product evolution
Before Starting Any Task
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.
- 2mo ago First seen · 65 lines · 0 tokens per session scan A ef7b1372600f
documentation-expert is an agent published in the GitHub repository bramato/saveForMeDearAi (0 stars, last pushed 1y ago), licensed MIT. It adds 215 tokens to every session and 1,012 once invoked, about $0.0009 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 2026-08-31.
documentation-expert compared with agents from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| documentation-expertbramato/saveForMeDearAi | Agent | 0 | 1y ago | MIT | A | 215 | 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 |
| WinForms Expertgithub/awesome-copilot | Agent | 41k | yesterday | MIT | A | 19 | Claude Code |