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 skills/elumenotion/guideants/mssql-querynpx skills add Elumenotion/GuideAnts --skill mssql-querygit clone --depth 1 https://github.com/Elumenotion/GuideAntsWrote 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/skills/elumenotion/guideants/mssql-query)<a href="https://agentmods.dev/skills/elumenotion/guideants/mssql-query"><img src="https://agentmods.dev/badge/skills/elumenotion/guideants/mssql-query.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 | $0.00073 | $0.01566 |
| Opus 5 | $0.00036 | $0.00783 |
| Sonnet 5 | $0.00015 | $0.00313 |
| Haiku 4.5 | $0.00007 | $0.00157 |
Grade A, and why
mssql-query 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 — 121 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Queries the stack's SQL Server (mssql-express container) from the
sandbox, using the connection string supplied through the environment
(GA_DB_CONNECTION_STRING — set on the Guide, marked secret). The tool
self-bootstraps pymssql on first use (one pip install), then everything is
local Python.
Database at a glance
Read references/database.md first — it is the persistent understanding of
this database (table names, column gotchas, feature areas, how the tables
join, the enum dictionary, a reading a conversation recipe, usage,
performance, and undone turns, guides, projects, and environments, and a
verified core-query library), so you do not re-derive the schema each session.
The short version: GuideAnts is a Projects > Notebooks workspace. Each
notebook has files (NotebookFiles, versioned ContentFiles) and
conversations (NotebookConversations -> NotebookConversationMessages
ConversationTurns). Guides/Assistants (Assistants,Kind1=Guide) package the way of working; execution isAgentInvocations(->AgentInvocationMessagesfor detail) +JobQueue; cost/telemetry isUsageEvents; file provenance isFileLineageEvents.UsageEventshas a nullable FK to nearly every other table, so it is the key for "what/who/cost" questions. SQL table names are plural (the doc uses singular entity names); verify column details withschema <Table>.
How the instance is wired
The skill runs inside the guideants-ai container, inside the running
compose stack; mssql-express is a sibling service (stock compose: service
mssql-express, image mssql2025-express-fts, publishes 1434:1433 on the
host). The connection string is the ADO.NET one the webapi carries as
ConnectionStrings__DefaultConnection — here it arrives as
GA_DB_CONNECTION_STRING (Guide Environment variable, secret).
Endpoint resolution in the tool: --endpoint → GA_DB_ENDPOINT → the
Server= field of the connection string (only when that host is an IP
literal or localhost; the compose service name mssql-express does not
resolve from the ai container) → default host.docker.internal:1434.
What ships with it
4 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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 · 121 lines · 73 tokens per session scan A 49ca906aa294
mssql-query is a skill published in the GitHub repository Elumenotion/GuideAnts (57 stars, last pushed 2d ago), licensed Apache-2.0. It adds 73 tokens to every session and 1,566 once invoked, about $0.0004 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 2026-09-03.
Other skills, from other repositories
db-migration-helper
Use when generating database migration SQL from model or schema changes — compares current vs desired schema, detects diffs, outputs reversible safe migrations.
redteam-sqli-detail-pack
Domain routing and boundary guidance for authorized SQL injection testing, including union-based, blind, error-based, stacked query, and second-order SQL injection variants. Use when a task belongs to the SQL injection domain and needs scope, evidence, pivot, or exit criteria.
api-canvas
DataCanvas primitive reference — a Tier 3 SQL/analytical workspace for tabular MCP servers, backed by DuckDB. Use when registering tables from upstream APIs, running ad-hoc SQL across them, and exporting results. Covers the acquire → register → query → export flow, per-table TTL, the token-sharing pattern for…
api-mirror
Stand up a persistent, self-refreshing local mirror of a bulk upstream dataset with the MirrorService (@cyanheads/mcp-ts-core/mirror). Use when a server wraps a large or slow API and should query a synced local index (embedded SQLite + FTS5) instead of paginating the live API per request.
multitenant
Architecture multitenant avec approche tiered (Shared/Dedicated Schema/DB), RBAC/ABAC, field-level encryption. Use when working with multitenant applications, tenant isolation, data segregation.
graphql
GraphQL API design, Apollo Federation, schema stitching, resolvers, N+1 query problem. Use when implementing GraphQL API, federation, or optimizing queries.