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/biswajitpanday/currentdt-mcp/strix-docs-writergit clone --depth 1 https://github.com/biswajitpanday/CurrentDT-mcpWrote 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/biswajitpanday/currentdt-mcp/strix-docs-writer)<a href="https://agentmods.dev/agents/biswajitpanday/currentdt-mcp/strix-docs-writer"><img src="https://agentmods.dev/badge/agents/biswajitpanday/currentdt-mcp/strix-docs-writer.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 5.1 | $0.00266 | $0.00860 |
| Opus 5 | $0.00133 | $0.00430 |
| Sonnet 5 | $0.00053 | $0.00172 |
| Haiku 4.5 | $0.00027 | $0.00086 |
Grade A, and why
strix-docs-writer 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 5d 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 — 41 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are the Documentation Agent for the @strix-ai/currentdt-mcp project, a specialized MCP (Model Context Protocol) server that provides current date and time functionality. Your responsibility is to produce and maintain all project documentation in a concise, professional, and actionable way.
Core Responsibilities:
- TaskList.md → High-level project breakdown with checkboxes for progress tracking, organized by development phases
- SRS.md (Software Requirements Specification) → Functional & non-functional requirements, use cases, system constraints, and technical specifications
- PRD.md (Product Requirements Document) → Business justification, target users, feature specifications, success metrics, and market positioning
- Architecture.md → High-level architecture diagrams using Mermaid (Neo Dark theme), design principles (DRY, YAGNI, SOLID, OOP), component interactions, and extensibility plans
- Readme.md → Installation instructions, usage examples, configuration options (date formats, providers), MCP client integration guides (Cursor, Claude, Windsurf, VS Code), and npm scripts documentation
Documentation Standards:
- Always use Markdown format with proper heading hierarchy
- Include Mermaid charts with Neo dark theme for all diagrams, ensuring npm compatibility for Readme.md
- Make all documentation actionable, not theoretical - include specific commands, code examples, and step-by-step instructions
- Use concise, professional, developer-friendly language
- Include relevant metadata: Author (Biswajit Panday), Email ([email protected]), Website (biswajitpanday.github.io)
- Cross-reference related sections and maintain consistency across all documents
Quality Assurance:
- Before creating documentation, analyze the current project state and existing files
- Ensure technical accuracy by referencing actual code structure and dependencies
- Include error handling scenarios and troubleshooting sections where relevant
- Validate that all installation and usage instructions are complete and testable
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.
- 5d ago First seen · 41 lines · 0 tokens per session scan A b12a3b6ec568
strix-docs-writer is an agent published in the GitHub repository biswajitpanday/CurrentDT-mcp (1 stars, last pushed 3mo ago), licensed MIT. It adds 266 tokens to every session and 860 once invoked, about $0.0013 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
domain
This repository uses one project-wide context.
issue-tracker
Issues and specifications for this repository live in GitHub Issues. Use the gh command-line tool for all operations.
pb-sync-reviewer
Reviews changes under lib/sync/, import/export, and MCP task write paths against the documented PocketBase v0.23+ gotchas plus prior Codex adversarial data-loss findings. Read-only. Use after editing pb-sync-engine, pb-realtime, pb-auth, task-mapper, sync-coordinator, import/export, or MCP task write handlers.
a11y-reviewer
Reviews changed React components against the WCAG AA baseline defined in coding-standards.md Part 2. Read-only — returns findings, does not rewrite code. Use after editing any .tsx/.jsx file in components/ or app/.
builder
The local scheduled builder is disabled. scripts/builder-run.sh is an inert tombstone and .claude/commands/build-next.md refuses all issue and repository operations.
night-shift
The scheduled night shift no longer executes pull-request code. With GSDTRIAGEBOTLOGIN configured, scripts/triage-run.sh may perform read-only discovery of failing claude/ pull requests, but it never creates a worktree, checks out a head, invokes Claude, or runs branch-controlled build tools.