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/kpritam/gremlin-mcp/agents-mdgit clone --depth 1 https://github.com/kpritam/gremlin-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/instructions/kpritam/gremlin-mcp/agents-md)<a href="https://agentmods.dev/instructions/kpritam/gremlin-mcp/agents-md"><img src="https://agentmods.dev/badge/instructions/kpritam/gremlin-mcp/agents-md.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 | $0.02848 | $0.02848 |
| Opus 5 | $0.01424 | $0.01424 |
| Sonnet 5 | $0.00570 | $0.00570 |
| Haiku 4.5 | $0.00285 | $0.00285 |
Grade A, and why
gremlin-mcp AGENTS.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 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 — 330 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AI AGENTS GUIDELINES
1. Title & Purpose
Authoritative operational standard for all AI coding agents (Copilot, Claude, GPT, others) contributing to this repository. Defines mandatory engineering rules, workflow protocol, architectural constraints, and decision heuristics to ensure consistent, safe, high‑quality, effect‑based TypeScript contributions.
2. Scope (What this file governs / What it does not)
Governs: Code generation, refactors, tests, docs authored by AI; architectural changes; effect modeling; schema & Gremlin interactions; error & data modeling; PR structure; automation hygiene. Does NOT govern: Human editorial style guides, product roadmap, infrastructure ops, non-code repository assets. If a conflict exists with LICENSE or SECURITY.md, those take precedence.
3. Core Principles (short list)
- KISS – minimal viable abstraction.
- YAGNI – add complexity only with a concrete second use.
- DRY – no duplicated logic; prefer reuse/composition.
- Purity – isolate side effects at explicit boundaries.
- Explicitness – types, errors, contracts are declared, not inferred from context.
- Determinism – schema generation & transformations must be reproducible.
- Composability – build small effectful units combined via functional operators.
- Safety – no unchecked external data, no silent failures.
- Observability of intent – names reveal purpose; no hidden coupling.
- Focus – each change addresses one coherent concern.
4. Operational Rules (MUST / MUST NOT)
Architecture & Design
MUST:
- Preserve existing layered separation (config / gremlin services / schema / handlers / utils / models).
- Keep modules single‑purpose; split when a file exceeds clearly separated responsibilities (heuristic: > ~300 lines with 2+ conceptual domains).
- Encapsulate traversal construction behind utilities/services; expose intention, not query strings.
- Represent cross‑cutting concerns (config, schema cache, connection) via injectable services.
- Maintain deterministic schema assembly (stable ordering, idempotent recomputation, cache invalidation explicit).
- Introduce an abstraction only after a second concrete call site or clear complexity reduction.
- Ensure new layers or services declare explicit dependency requirements (no implicit global access).
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 · 330 lines · 2,848 tokens per session scan A 1e76634467c6
gremlin-mcp AGENTS.md is an instructions file published in the GitHub repository kpritam/gremlin-mcp (9 stars, last pushed 11mo ago), licensed MIT. It adds 2,848 tokens to every session, about $0.0142 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 instructions, from other repositories
lms-front CLAUDE.md
Claude Code instructions for guillermoscript/lms-front, covering claude.md, project overview, commands, architecture and multi-tenancy.
vespertide AGENTS.md
AGENTS.md instructions for dev-five-git/vespertide, covering vespertide knowledge base, structure, where to look, data flow and conventions.
seekstone CLAUDE.md
Claude Code instructions for shaqmughal/seekstone, covering claude.md, what this repo is, commands, the harness itself (run after npm install) and architecture.
rails_ai_agents AGENTS.md
AGENTS.md instructions for ThibautBaissac/rails_ai_agents, covering project configuration, tech stack, architecture, key commands and tests.
pg-dash CLAUDE.md
Claude Code instructions for indiekitai/pg-dash, covering pg-dash claude.md, 项目结构, 构建与测试, 发版纪律（强制） and 发版检查清单（每次 npm publish 前必须按序执行）.
MCP-SqlServer CLAUDE.md
Claude Code instructions for Aron-Valenzuela/MCP-SqlServer, covering claude.md, project overview, setup (for each user), 1. install dependencies and 2. configure claude desktop.