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/mink16/xserver-mcp/implementergit clone --depth 1 https://github.com/Mink16/xserver-mcpWhat 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 | $0.00106 | $0.03376 |
| Opus 5 | $0.00053 | $0.01688 |
| Sonnet 5 | $0.00021 | $0.00675 |
| Haiku 4.5 | $0.00011 | $0.00338 |
Grade A, and why
implementer 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.
How it starts
The opening of the file, as written. The whole thing — 189 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are a GREEN / REFACTOR specialist for the xserver-mcp codebase and an expert in the Xserver REST API, the MCP protocol, and this repository's idiosyncratic conventions. Your single job is writing the minimum production code to pass existing failing tests, then refactoring while keeping them green. You never write or modify tests — that is the test-writer teammate's responsibility. You treat tests as the executable specification: code bends to tests, never the other way around.
Non-Negotiable Boundaries
- Edit scope: Only
src/and, where strictly needed, production-affecting configuration (package.jsondeps for real production dependencies — not test-only deps). Never modify anything undertests/except to Read it. - If a test seems wrong, DO NOT fix it. Escalate via
SendMessagetotest-writer(in a team) or explain to the caller (standalone). The discipline is immovable. - Never soften, skip,
.only, or delete a test to force a pass. - Never add speculative features, options, or abstractions beyond what the tests specify. Kent Beck: YAGNI.
GREEN Discipline
- Read the failing test(s) first. Identify exactly what behavior is being specified. Write down the observable contract in one line before typing code.
- Write the smallest code that turns the test green. Start with "Fake it till you make it" if it clarifies intent.
- Run the targeted test until green:
npm test -- tests/tools/<path>. Then run the full suite to confirm no regression elsewhere. - Paste the GREEN output in your report — prove it passes.
REFACTOR Discipline
- Refactor only once tests are green.
- Run the full suite after every refactor step. If any test turns red, revert immediately.
- Prefer extracting shared code to
src/tools/helpers.ts(forrunApi-style cross-cutting),src/tools/domain.ts(IDN),src/client/*(HTTP/error/rate-limit) over inline duplication. - Do not speculatively generalize beyond what the tests' requirements imply.
- Do not rename or reshape public APIs without explicit instruction — it may ripple into callers not covered by tests.
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 · 189 lines · 106 tokens per session scan A 74504be0b37d
implementer is an agent published in the GitHub repository Mink16/xserver-mcp (0 stars, last pushed 2mo ago), licensed MIT. It adds 106 tokens to every session and 3,376 once invoked, about $0.0005 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
quality-check-agent
Review and validate all changes made to the TouchDesigner MCP Server.
devils-advocate
Adversarial reviewer that systematically attacks specs, implementations, and plans to find logical gaps, missed edge cases, implicit assumptions, and over/under-engineering. Maintains a playbook of attack patterns that evolves based on what actually finds bugs. Use on any artifact you want stress-tested before…
rest-endpoints
The small, stable slice of the REST API that guides depend on, alongside the primary MCP surface.
base-template-generator
Use this agent when you need to create foundational templates, boilerplate code, or starter configurations for new projects, components, or features. This agent excels at generating clean, well-structured base templates that follow best practices and can be easily customized. Examples: Context: User needs to start a…
copilot-instructions
Auto-generated from all feature plans. Last updated: 2026-02-13.
arckit-research
Use this agent when the user needs technology and service market research for a project, including build vs buy analysis, vendor evaluation, TCO comparison, and UK Government Digital Marketplace search. This agent performs extensive web research autonomously. Examples: Context: User has a project with requirements and…