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/jmrplens/gitlab-mcp-server/go-mcp-servergit clone --depth 1 https://github.com/jmrplens/gitlab-mcp-serverWrote 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/jmrplens/gitlab-mcp-server/go-mcp-server)<a href="https://agentmods.dev/instructions/jmrplens/gitlab-mcp-server/go-mcp-server"><img src="https://agentmods.dev/badge/instructions/jmrplens/gitlab-mcp-server/go-mcp-server.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 | $0.03908 | $0.03908 |
| Opus 5 | $0.01954 | $0.01954 |
| Sonnet 5 | $0.00782 | $0.00782 |
| Haiku 4.5 | $0.00391 | $0.00391 |
Grade A, and why
gitlab-mcp-server go-mcp-server.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 4d 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 — 561 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Go MCP Server Development Guidelines
When building MCP servers in Go, follow these best practices and patterns using the official Go SDK (v1.7.0+).
Server Setup
Create an MCP server using mcp.NewServer:
import "github.com/modelcontextprotocol/go-sdk/mcp"
server := mcp.NewServer(
&mcp.Implementation{
Name: "my-server",
Version: "v1.7.0",
},
nil, // or provide mcp.Options
)
Tool Naming Conventions
Use snake_case with a service prefix to avoid conflicts when multiple MCP servers run together:
- Format for this project: individual tools use
gitlab_{action}_{resource}(e.g.,gitlab_create_issue,gitlab_list_projects), while catalog action IDs use{domain}.{action} - Be action-oriented: Start with verbs (
get,list,search,create,update,delete) - Be specific: Avoid generic names that could conflict with other servers
- Descriptions: Must narrowly and unambiguously describe functionality, matching actual behavior
Adding Tools
For ordinary GitLab API actions in this repository, add or update domain-local ActionSpecs and handlers. Do not add package-local RegisterTools functions or ad hoc mcp.AddTool calls; shared projection layers consume the canonical action catalog for meta-tools, dynamic find/execute, gitlab://tools, audits, docs, and individual tool registration.
Each ActionSpec declares a minimum edition (free, premium, or ultimate). Edition gating flows through GITLAB_TIER / --tier and pruneSchemaFieldsByTier in internal/tools/action_catalog.go, which removes premium/ultimate-only actions and prunes per-field schema entries once the active tier resolves. Set the lowest edition that exposes the endpoint correctly and add tier hints in ParameterGuidance when a field is edition-gated. Run go run ./cmd/audit_discovery_completeness/ to confirm each new action has aliases, usage, parameter guidance, and related actions.
For shared projection code or standalone surfaces that intentionally register SDK tools directly, use mcp.AddTool with struct-based input and output for type safety:
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.
- 4d ago First seen · 561 lines · 3,908 tokens per session scan A be5fbd334489
gitlab-mcp-server go-mcp-server.instructions.md is an instructions file published in the GitHub repository jmrplens/gitlab-mcp-server (33 stars, last pushed today), licensed MIT. It adds 3,908 tokens to every session, about $0.0195 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
ollama AGENTS.md
AGENTS.md instructions for ollama/ollama, covering agents.md and building.
ollama CLAUDE.md
Claude Code instructions for ollama/ollama: See AGENTS.md for the shared agent instructions for this repository.
claude-tap AGENTS.md
Instructions for liaohch3/claude-tap, covering maintainer automation notes, agents 索引, documentation boundary, review guidelines and pre-commit hook.
opencodex AGENTS.md
AGENTS.md instructions for lidge-jun/opencodex, covering agents.md, what this project is, repository layout, optional subsystems stay off the core path and the devlog directory.
gollem CLAUDE.md
Instructions for gollem-dev/gollem, covering claude.md, restriction & rules, commands, development and testing and test execution.
goai AGENTS.md
AGENTS.md instructions for zendev-sh/goai, covering agents.md - goai, commands, architecture, key rules and adding providers.