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/agentdank/dank-mcp/agents-mdgit clone --depth 1 https://github.com/AgentDank/dank-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 | $0.01055 | $0.01055 |
| Opus 5 | $0.00528 | $0.00528 |
| Sonnet 5 | $0.00211 | $0.00211 |
| Haiku 4.5 | $0.00105 | $0.00105 |
Grade A, and why
dank-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 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 — 75 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md
Guidance for AI agents (and humans) working on dank-mcp. User-facing documentation lives in README.md; this file is for contributors modifying the code.
What this repo is
dank-mcp is an MCP server that exposes cannabis datasets to LLMs via SQL over DuckDB. It is published under the AgentDank organization.
Current state
- No datasets are bundled. The prior hand-rolled Connecticut (CT) brands handlers were removed in the transition to a generic binding architecture.
- The server registers one MCP tool,
query, which executes arbitrary SQL against DuckDB and returns CSV. - DuckDB is opened with
access_mode=read_onlyand hasSET enable_external_access=falseapplied viadb.RunSafeMode. Both layers matter; don't remove one assuming the other covers it.
Architectural direction
The project is moving from per-dataset Go code toward declarative dataset bindings:
pkg/dank.Registraris the contract new datasets should implement (GetMigrationUp/Down,GetResources,GetTools,Fetch).Binding,ResourceQuery,ToolQuerystructs inpkg/dank/dank.gocarry JSON tags; intent is config-driven wiring rather than bespoke Go per dataset.internal/mcp.ToolMapis amap[string]ToolRegistrationFuncthat lets multiple datasets plug into the server side-by-side.
Layout
main.go— CLI entry; opens DuckDB, migrates, reopens read-only, applies safe mode, registers tools, runs the MCP router.data/— cache paths and.dankroot directory management (EnsureDankPath,GetDankDir, etc.).internal/db/— migrations (duckdb_up.sql,duckdb_safe.sql),RunMigration,RunSafeMode, and theRowsToCSVhelper.internal/mcp/—server.go(router +ToolMappattern) andtool.go(the genericquerytool).pkg/dank/— the binding contracts (currently types only; no implementations yet).
Dataset catalog
Datasets are resolved via a remote catalog.json hosted at:
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 · 75 lines · 1,055 tokens per session scan A 17ab72490e53
dank-mcp AGENTS.md is an instructions file published in the GitHub repository AgentDank/dank-mcp (3 stars, last pushed 4mo ago), licensed MIT. It adds 1,055 tokens to every session, about $0.0053 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
vscode buildNext.instructions.md
Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).
spec-kit AGENTS.md
AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.
codex AGENTS.md
AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.
langchain AGENTS.md
AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).
next.js AGENTS.md
Instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.