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/egarcia74/warp-sql-server-mcp/agents-mdgit clone --depth 1 https://github.com/egarcia74/warp-sql-server-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/egarcia74/warp-sql-server-mcp/agents-md)<a href="https://agentmods.dev/instructions/egarcia74/warp-sql-server-mcp/agents-md"><img src="https://agentmods.dev/badge/instructions/egarcia74/warp-sql-server-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 | $0.00424 | $0.00424 |
| Opus 5 | $0.00212 | $0.00212 |
| Sonnet 5 | $0.00085 | $0.00085 |
| Haiku 4.5 | $0.00042 | $0.00042 |
Grade A, and why
warp-sql-server-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 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.
What it actually says
Project Agent Directives
Purpose
- Ensure the AI assistant always treats
WARP.mdas the primary knowledge document for this repo.
Knowledge Rules
- Always consult
WARP.mdfirst for project context, architecture, terminology, workflows, and conventions. - When the user asks about behavior, features, decisions, or standards, search
WARP.mdfor relevant sections before scanning other files. - Prefer headings and anchors in
WARP.mdto locate context; quote the closest section title when helpful. - If an answer might conflict with
WARP.md, defer toWARP.mdand call out the discrepancy. - If
WARP.mdis missing details, then consultREADME.md,docs/, and code.
Operational Guidance
- On first interaction in this workspace, quickly scan
WARP.mdto build context. - If
WARP.mdchanges during a session, re-open it to refresh context. - Keep answers concise; link to
WARP.mdsections by filename and heading when referencing details.
Key Commands
Run these before proposing a change as finished:
npm run lint- ESLint over the repositorynpm run format:check- Prettier formatting check (npm run formatto fix)npm run markdown:lint- markdownlint over all Markdown (npm run markdown:fixto fix)npm run test:unit- Vitest unit suite intest/unit; fast, no database requirednpm run ci- full local gate: lint, format, markdown, link check, coverage, npm audit
npm test and npm run test:integration start a SQL Server container, so they need a working
Docker daemon.
Further Reading
CONTRIBUTING.md- development workflow, test-driven development (TDD) requirements, git hooks, and safety-testing rules.WARP.md- the detailed source of truth for architecture, security policy, and release process.
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 · 39 lines · 424 tokens per session scan A 54b77e35cf22
warp-sql-server-mcp AGENTS.md is an instructions file published in the GitHub repository egarcia74/warp-sql-server-mcp (5 stars, last pushed 4d ago), licensed MIT. It adds 424 tokens to every session, about $0.0021 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
world-intel-mcp CLAUDE.md
Claude Code instructions for marc-shade/world-intel-mcp, covering claude.md, what this is, commands, install and run mcp server (stdio mode).
autotask-mcp AGENTS.md
AGENTS.md instructions for WYRE-AI/autotask-mcp, covering task master ai - agent integration guide, essential commands, core workflow commands, project setup and daily development workflow.
pfsense-mcp-server AGENTS.md
AGENTS.md instructions for night4me/pfsense-mcp-server, covering pfsense mcp server, architecture and security, development workflow, long-running validation and test parallelism.
clawstash CLAUDE.md
Claude Code instructions for fo0/clawstash, covering claude.md -- project guide, session start -- read order, workflow triggers, output languages and performance / modes.
sui-mcp CLAUDE.md
Claude Code instructions for 0xfreak0/sui-mcp, covering sui-mcp, stack, architecture, which transport to use and archive fallback.
datadog-mcp CLAUDE.md
Claude Code instructions for dreamiurg/datadog-mcp, covering agent instructions, project, stack, commands and releases.