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/alyiox/mcp-mssql/agents-mdgit clone --depth 1 https://github.com/alyiox/mcp-mssqlWrote 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/alyiox/mcp-mssql/agents-md)<a href="https://agentmods.dev/instructions/alyiox/mcp-mssql/agents-md"><img src="https://agentmods.dev/badge/instructions/alyiox/mcp-mssql/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 | $0.00685 | $0.00685 |
| Opus 5 | $0.00342 | $0.00342 |
| Sonnet 5 | $0.00137 | $0.00137 |
| Haiku 4.5 | $0.00068 | $0.00068 |
Grade A, and why
mcp-mssql 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.
How it starts
The opening of the file, as written. The whole thing — 99 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Agent Instructions
Rules AI agents must follow when working in this repository.
Commit messages
Use Conventional Commits.
Header
- Format:
<type>(optional scope): summary - Use lowercase types (
feat,fix,ci,chore,docs) - Use scopes when relevant
- Write summaries in lowercase, imperative mood
Body
- Leave a blank line after the header
- Explain why, not what
- Use imperative, present tense
- Wrap lines at ~72 characters
The body is optional for trivial changes.
Release tags
- Use the bare version as the tag name — no
vprefix (e.g.1.0.0-beta.3, notv1.0.0-beta.3) - Tags must be annotated (
git tag -a) with a structured release-notes message
Commits (automation)
When generating commits via a shell:
- Do not pass generated messages directly to
git commit -m - Write the commit message to a file or standard input
- Use
git commit -F <file>orgit commit -F - - Disable shell expansion when writing commit messages
This avoids issues with backticks, quotes, and other shell-expanded characters in generated commit messages.
Attribution
All commits must include an Assisted-by trailer line:
Assisted-by: AGENT_NAME:MODEL_VERSION [TOOL1] [TOOL2]
- AGENT_NAME — the AI tool or framework used (e.g.
Claude,Cursor,Copilot) - MODEL_VERSION — the specific model version (e.g.
claude-opus-4-6) - [TOOL1] [TOOL2] — optional, space-separated list of specialized analysis tools used in the change (e.g.
coccinelle,sparse,smatch,clang-tidy) - Do not list everyday tools like
git,gcc,make, or editors
Example:
Assisted-by: Claude:claude-opus-4-6 coccinelle sparse
Code style
Follow existing project conventions.
- Match formatting, naming, and file structure already in use
- Do not reformat unrelated code
- Prefer small, focused changes
- Avoid introducing new patterns without clear benefit
Language-specific rules
- If a formatter or linter exists, follow it
- Respect
.editorconfigwhen present - Do not disable lint rules without justification
- Prefer explicit, readable code over clever abstractions
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 · 99 lines · 685 tokens per session scan A 17e49767ab3b
mcp-mssql AGENTS.md is an instructions file published in the GitHub repository alyiox/mcp-mssql (7 stars, last pushed 3d ago), licensed MIT. It adds 685 tokens to every session, about $0.0034 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
bjorn-skills CLAUDE.md
Claude Code instructions for Vingedal/bjorn-skills, covering claude.md, what this repo is, commands, architecture: how one skill is wired in three places and adding a skill.
sql-sentinel CLAUDE.md
Instructions for tkmawarire/sql-sentinel, covering claude.md, project overview, build commands, restore and build and run the server.
blockrun-mcp AGENTS.md
AGENTS.md instructions for BlockRunAI/blockrun-mcp, covering blockrun mcp, commands, project structure, key dependencies and install in codex.
openrouter-mcp-multimodal AGENTS.md
AGENTS.md instructions for stabgan/openrouter-mcp-multimodal, covering agent instructions, before you ship, releasing (read this before publishing), short version and version files (must all match package.json).
intervals-icu-mcp CLAUDE.md
Instructions for hhopke/intervals-icu-mcp, covering claude.md, project overview, development commands, architecture (quick reference) and tool categories.
ai-toolkit AGENTS.md
AGENTS.md instructions for pipefy/ai-toolkit, covering repository guidelines, documentation map, project structure, import namespace migration: pipefysdk → pipefy and src/pipefysdk/init.py (transitional shim).