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/andezdev/tokenlite-mysql-mcp/agents-mdgit clone --depth 1 https://github.com/andezdev/tokenlite-mysql-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/andezdev/tokenlite-mysql-mcp/agents-md)<a href="https://agentmods.dev/instructions/andezdev/tokenlite-mysql-mcp/agents-md"><img src="https://agentmods.dev/badge/instructions/andezdev/tokenlite-mysql-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 | $0.01164 | $0.01164 |
| Opus 5 | $0.00582 | $0.00582 |
| Sonnet 5 | $0.00233 | $0.00233 |
| Haiku 4.5 | $0.00116 | $0.00116 |
Grade A, and why
tokenlite-mysql-mcp AGENTS.md scanned grade A with 0 findings against 26 rules in 11 categories โ prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency โ measured 3d 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 โ 67 lines โ stays where its author put it; the contents beside it link to each section on GitHub.
๐ค AI Agents Guide: TokenLite MySQL MCP
Notice to LLMs, Agents, and Coding Assistants: If you are reading this file, you have been connected to the TokenLite MySQL MCP Server. This server is heavily protected and optimized to prevent hallucinations, reduce context window bloat, and block dangerous operations.
Tool names are prefixed with the database name (e.g.,
mydb_search_schema,mydb_execute_safe_query). If a customTOOL_PREFIXis set, that prefix is used instead.You MUST follow the rules below strictly.
๐จ Golden Rules
-
NEVER use
SHOW TABLESorDESCRIBEmanually.- Rule: You MUST use the
search_schematool instead. - Why:
search_schemaprovides a compressed, heuristic-based Graph (Auto-Join Context) that gives you the DDL of the requested table and its implicitly related tables. It also injects business semantics frommetadata.json.
- Rule: You MUST use the
-
NEVER manually query
information_schema.- Rule: If a query fails because of a missing column or table (e.g.,
ER_BAD_FIELD_ERROR), you MUST use therefresh_schematool to rebuild the internal graph, and then usesearch_schemaagain. Do not attempt to queryinformation_schemadirectly.
- Rule: If a query fails because of a missing column or table (e.g.,
-
NEVER write business metrics SQL manually (when templates are configured).
- Rule: If
templates.jsonis loaded,search_schemawill include a reminder to use thequery_templatesprompt before writing analytical SQL (e.g., LTV, Revenue, Active Users). - Why: The company has predefined, vetted SQL templates. Hallucinating metrics leads to incorrect dashboards.
- Rule: If
-
DO NOT add
LIMITto your exploratory queries.- Rule: When using
execute_safe_query, the server will automatically inject aLIMITat the AST level (default:MCP_QUERY_ROW_LIMIT=500). Do not manually appendLIMITunless you need a very specific offset pagination. - Truncation: If results reach the applied
LIMIT, the CSV output includes a-- rows: N (truncated at LIMIT X)footer. Do not assume you have the full dataset.
- Rule: When using
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.
- 3d ago First seen ยท 67 lines ยท 1,164 tokens per session scan A aaefcf2f8050
tokenlite-mysql-mcp AGENTS.md is an instructions file published in the GitHub repository andezdev/tokenlite-mysql-mcp (0 stars, last pushed 22d ago), licensed MIT. It adds 1,164 tokens to every session, about $0.0058 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
mcp-toolbox GEMINI.md
Gemini CLI instructions for googleapis/mcp-toolbox, covering mcp toolbox context & style guide, project overview, tech stack, key directories and development workflow.
agentos CLAUDE.md
Claude Code instructions for rivet-dev/agentos, covering agentos, boundaries, security model, sqlite schema ownership and runtime and registry.
mcp-toolbox AGENTS.md
AGENTS.md instructions for googleapis/mcp-toolbox, a project described as: MCP Toolbox for Databases is an open source MCP server for databases.
ii-agent CLAUDE.md
Instructions for Intelligent-Internet/ii-agent, covering ii-agent project guide, project overview, architecture, domain structure and orm base & id conventions.
reflect-open CLAUDE.md
Claude Code instructions for team-reflect/reflect-open: See AGENTS.md for the full project overview, tech stack, database tables, code conventions, and development cycle.
sortie copilot-instructions.md
Copilot instructions for sortie-ai/sortie, covering sortie coding & review standards, 1. layered imports (downward only; violation is critical), 2. concurrency safety, 3. workspace path safety (critical: security boundary) and 4. persistence (sqlite).