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/tse-wei-chen/hs-sql-agent/agents-mdgit clone --depth 1 https://github.com/tse-wei-chen/hs-sql-agentWhat 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 | $0.00855 | $0.00855 |
| Opus 5 | $0.00428 | $0.00428 |
| Sonnet 5 | $0.00171 | $0.00171 |
| Haiku 4.5 | $0.00085 | $0.00085 |
Grade A, and why
hs-sql-agent 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 — 65 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md
Repo Structure
- Backend: ASP.NET Core (net10.0) in
backend/src/. Main entrypoint:ToolBox/ToolBox.csproj. - Frontend: Nuxt 4 (pnpm) in
frontend/. Source dir isapp/(not defaultapp.vueroot). - Submodule:
backend/src/Modules/SqlKata.Serviceis a git submodule. Rungit submodule update --init --recursiveafter clone. - Storage: SQLite at runtime in
data/hsqlagent.db(mounted via Docker volume).
Commands
Backend
# Run locally
cp backend/src/ToolBox/appsettings.Example.json backend/src/ToolBox/appsettings.json
dotnet run --project backend/src/ToolBox
# Run all tests (requires Docker for Testcontainers)
dotnet test backend/src/UnitTest/SqlAgent.Test/SqlAgent.Test.csproj
dotnet test backend/src/UnitTest/Admin.Test/Admin.Test.csproj
# Run single test
dotnet test backend/src/UnitTest/SqlAgent.Test/SqlAgent.Test.csproj --filter "FullyQualifiedName~SqliteStrategyTests"
Frontend
cd frontend
pnpm install # uses [email protected] (enforced via packageManager field)
pnpm dev # http://localhost:3000, proxies /api to :8080
pnpm test # vitest with happy-dom
pnpm generate # static build to dist/ (used in Docker)
Docker
cp .env.example .env # set HMAC_KEY and JWT_KEY (32+ bytes each)
docker-compose up -d
Frontend is pre-built and served as static files from ToolBox.dll's wwwroot/.
Gotchas
- Solution file:
backend/hs-sql-agent.slnx(slnx format, not classic .sln). Backend uses central package management viaDirectory.Packages.props. - Frontend aliases:
@and~both resolve tofrontend/app/(seevitest.config.ts). - Testcontainers tests:
SqlAgent.Testspins up real DB containers (Sqlite, Postgres, MySql, SqlServer, Oracle, Firebird). Docker must be running. - Nuxt config:
ssr: false, dev proxy/api/**→http://localhost:8080/api/**. - Env vars: Backend reads from both
appsettings.jsonand environment variables (Docker Compose overrides). execute_dml_sqltool signature: Takesstring sqlfrom the caller.McpServer serverandCancellationToken cancellationTokenare injected by the MCP framework automatically (not caller-provided).
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 · 65 lines · 855 tokens per session scan A 9feb532171ea
hs-sql-agent AGENTS.md is an instructions file published in the GitHub repository tse-wei-chen/hs-sql-agent (11 stars, last pushed 2d ago), licensed Apache-2.0. It adds 855 tokens to every session, about $0.0043 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 2026-08-30.
Other instructions, from other repositories
db-mcp-server CLAUDE.md
Instructions for vika2603/db-mcp-server, covering claude.md, build and development commands, architecture, layer structure and key design patterns.
whodb AGENTS.md
AGENTS.md instructions for clidey/whodb, covering whodb development guide, git commits — hard rule, terminology, non-negotiable rules and behavioral guidelines.
graphjin AGENTS.md
AGENTS.md instructions for dosco/graphjin, covering graphjin agent guide, architectural overview, directory structure & responsibilities, build commands and coding guidelines.
whodb CLAUDE.md
Claude Code instructions for clidey/whodb, a project described as: Where data access meets operational intelligence.
Chat2DB AGENTS.md
AGENTS.md instructions for OtterMind/Chat2DB, covering chat2db community agent contract, context, product invariants, repository map and structural code navigation.
MCP-PostgreSQL-Ops copilot-instructions.md
Instructions for call518/MCP-PostgreSQL-Ops, covering architecture overview, core components, key patterns, in functions.py and development workflows.