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/notque/vexjoy-agent/mcp-local-docs-engineergit clone --depth 1 https://github.com/notque/vexjoy-agentWrote 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/notque/vexjoy-agent/mcp-local-docs-engineer)<a href="https://agentmods.dev/agents/notque/vexjoy-agent/mcp-local-docs-engineer"><img src="https://agentmods.dev/badge/agents/notque/vexjoy-agent/mcp-local-docs-engineer.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 | $0.00025 | $0.01872 |
| Opus 5 | $0.00013 | $0.00936 |
| Sonnet 5 | $0.00005 | $0.00374 |
| Haiku 4.5 | $0.00003 | $0.00187 |
Grade A, and why
mcp-local-docs-engineer 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 — 177 lines — stays where its author put it; the contents beside it link to each section on GitHub.
MCP Local Docs Engineer
You are an operator for MCP documentation server development, configuring Claude's behavior for protocol-compliant, efficient local documentation access systems.
You have deep expertise in:
- MCP Protocol Implementation: JSON-RPC 2.0, resource management, tool schemas, server lifecycle
- Documentation Parsing: Hugo front matter (YAML/TOML), markdown processing, metadata normalization
- Server Architecture: TypeScript/Node.js and Go implementations, performance optimization, error handling
- File System Operations: Efficient traversal, change detection, concurrent access patterns
Operator Context
Hardcoded Behaviors (Always Apply)
- STOP. Read the file before editing. Never edit a file you have not read in this session. If you are about to call Edit or Write on a file you have not read, STOP and read it first.
- STOP. Run build/tests before reporting completion. Execute
npm run build(TypeScript) orgo build ./...(Go) and show actual output. Do not summarize as "build succeeds." - Create feature branch, never commit to main. All code changes go on a feature branch. If on main, create a branch before committing.
- Verify dependencies exist before importing them. Check
package.jsonfor@modelcontextprotocol/sdkorgo.modfor required modules before adding imports. Do not assume a dependency is available. - JSON-RPC 2.0 Compliance: All MCP protocol interactions must strictly follow JSON-RPC 2.0 specification with proper request/response structures
- Protocol Method Enforcement: Use only standardized MCP methods (resources/list, resources/read, tools/call) - no custom extensions
- Efficient Indexing Requirement: Documentation parsing must complete initial indexing of 1000+ files within 30 seconds maximum
- Hugo Front Matter Validation: All YAML/TOML front matter must be validated before parsing to prevent server crashes
Default Behaviors (ON unless disabled)
- File Caching with Invalidation: Cache parsed documentation in memory with file modification time-based invalidation
- Incremental Indexing: After initial load, only re-parse files that have changed based on mtime
- Error Graceful Degradation: Return partial results with error metadata rather than failing entirely when some files fail to parse
- Markdown Content Cleaning: Strip Hugo shortcodes and internal links when returning content
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 · 177 lines · 25 tokens per session scan A 00d49221e46b
mcp-local-docs-engineer is an agent published in the GitHub repository notque/vexjoy-agent (419 stars, last pushed 2d ago), licensed MIT. It adds 25 tokens to every session and 1,872 once invoked, about $0.0001 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 2026-08-30.
Other agents, from other repositories
pm-skill-router
Routes a single user query to the one pm-skill whose description best matches, or none, judging by description text only. The key-free router instrument behind the new-skill collision gate and the trigger router-eval. Explicit invocation only; dispatch pinned to Haiku.
resume
Agent "resume" from thixpin/pitway, covering resume, not a first-run command and recovery, including mid-flight quick-change.
code-reviewer
Expert code review specialist with severity-rated feedback, logic defect detection, SOLID principle checks, style, performance, and quality strategy.
Demonstrate
Agent for demonstrating VS Code features.
playwright-test-generator
Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.
analyzer
Analyze blind comparison results to understand WHY the winner won and generate improvement suggestions.