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 instructions/strausmann/mcp-dockhand/gemini-reviewgit clone --depth 1 https://github.com/strausmann/mcp-dockhandWrote 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/instructions/strausmann/mcp-dockhand/gemini-review)<a href="https://agentmods.dev/instructions/strausmann/mcp-dockhand/gemini-review"><img src="https://agentmods.dev/badge/instructions/strausmann/mcp-dockhand/gemini-review.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 | $0.00283 | $0.00283 |
| Opus 5 | $0.00142 | $0.00142 |
| Sonnet 5 | $0.00057 | $0.00057 |
| Haiku 4.5 | $0.00028 | $0.00028 |
Grade A, and why
mcp-dockhand gemini-review.instructions.md 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 6d 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.
Copies of this mod
1 near-identical copy found in the catalogue:
- mcp-dockhand gemini-review.instructions.md — 100% identical, 0 lines differ
What it actually says
Gemini Code Assist Review Instructions
This repository wraps the Dockhand REST API (https://github.com/finsys/dockhand) into MCP tools.
Upstream Verification (CRITICAL)
For every MCP tool change, verify against the upstream Dockhand source:
- API Routes:
src/routes/api/**/+server.tsin finsys/dockhand defines the actual endpoints - HTTP Methods: Each
+server.tsexports named functions (GET, POST, PUT, DELETE, PATCH) - Request Bodies: Check what the route handler actually parses from the request
- Hawser Protocol:
internal/protocol/messages.goin finsys/hawser for agent communication
If an MCP tool uses a different HTTP method or parameter name than the upstream source, flag as HIGH.
Code Quality Checks
- All path parameters must use
encodePath()(path injection prevention) - All Zod parameters must have
.describe()annotations - No
Record<string, unknown>— use explicit typed parameters additionalConfig/additionalSettingsmerged BEFORE explicit fields- No unnecessary API calls (don't fetch just to read connectionType)
- Tests must actually validate what they claim (no loose string matching)
- API schema (
docs/dockhand-api-schema.json) must stay deterministic
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.
- 6d ago First seen · 29 lines · 283 tokens per session scan A 379f2557ddf8
mcp-dockhand gemini-review.instructions.md is an instructions file published in the GitHub repository strausmann/mcp-dockhand (37 stars, last pushed yesterday), licensed MIT. It adds 283 tokens to every session, about $0.0014 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 instructions, from other repositories
better-godot-mcp AGENTS.md
AGENTS.md instructions for n24q02m/better-godot-mcp, covering agents.md - better-godot-mcp, build / lint / test commands, run a single test file, run a single test by name and mise shortcuts.
mcp-python-exec-sandbox CLAUDE.md
Claude Code instructions for lu-zhengda/mcp-python-exec-sandbox, covering claude.md, project, stack, structure and commands.
health-mcp CLAUDE.md
Claude Code instructions for ojimpo/health-mcp, covering health-mcp — health-ojimpo 読み取り専用mcpサーバー, 概要, 構成, 運用情報 and 登録.
openrouter-mcp-multimodal AGENTS.md
AGENTS.md instructions for stabgan/openrouter-mcp-multimodal, covering agent instructions, before you ship, releasing (read this before publishing), short version and version files (must all match package.json).
Plonk AGENTS.md
AGENTS.md instructions for ostapondo/Plonk, covering agent rules, layout, adding a module, build & verify and code style.
minecraft-dev-mcp AGENTS.md
Instructions for MCDxAI/minecraft-dev-mcp, covering agent handbook – minecraft dev mcp, project snapshot, what agents should prioritize, architecture wayfinder (src/) and available mcp tools (for llm surfaces).