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/yoselabs/a2db/claude-mdgit clone --depth 1 https://github.com/yoselabs/a2dbWrote 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/yoselabs/a2db/claude-md)<a href="https://agentmods.dev/instructions/yoselabs/a2db/claude-md"><img src="https://agentmods.dev/badge/instructions/yoselabs/a2db/claude-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 | $0.00469 | $0.00469 |
| Opus 5 | $0.00234 | $0.00234 |
| Sonnet 5 | $0.00094 | $0.00094 |
| Haiku 4.5 | $0.00047 | $0.00047 |
Grade A, and why
a2db CLAUDE.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
a2db — Agent-to-Database
CLI and MCP server for AI agents to query databases. Two frontends (CLI + MCP), one core.
Architecture
src/a2db/connections.py— ConnectionStore: save/load/list connection TOML filessrc/a2db/drivers.py— DriverRegistry: DSN scheme → DBAPI 2.0 driver resolutionsrc/a2db/sql.py— SQLGlot wrapping: pagination, read-only validationsrc/a2db/executor.py— QueryExecutor: named batch queries with paginationsrc/a2db/schema.py— SchemaExplorer: progressive schema discoverysrc/a2db/formatter.py— Output formatting: TSV and JSON rendererssrc/a2db/cli.py— Click CLI frontend (thin wrapper)src/a2db/mcp_server.py— MCP server frontend (thin wrapper)
Dev Commands
- Full gate:
make check(lint + test + security) - Run tests:
make test(includes coverage, fails under 90%) - Lint:
make lintoragent-harness lint(check only, never modifies files — safe to run anytime) - Fix:
make fixoragent-harness fix(auto-fix, then runs lint to verify) - Coverage diff:
make coverage-diff(changed lines must be 95%+ covered) - Security:
agent-harness security-audit(deps + secrets) - Config check:
agent-harness init(checks project hygiene) - Build:
make build - Bootstrap:
make bootstrap(installs deps, requiresagent-harnessCLI)
Pre-commit hooks run fix then lint automatically on every commit. Never truncate lint or test output — read the full error.
Never
- Never commit
.envfiles or database credentials - Never execute destructive SQL (DROP, TRUNCATE, DELETE without WHERE) without explicit user confirmation
Ask First
- Before changing CLI argument names or command structure (breaking change for users)
- Before adding new dependencies
- Before changing MCP tool signatures (breaking change for MCP clients)
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 · 40 lines · 469 tokens per session scan A 21ed262b4492
a2db CLAUDE.md is an instructions file published in the GitHub repository yoselabs/a2db (2 stars, last pushed 4mo ago), licensed Apache-2.0. It adds 469 tokens to every session, about $0.0023 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-documentation-server copilot-instructions.md
Instructions for andrea9293/mcp-documentation-server, covering mcp documentation server - ai coding agent instructions, architecture overview, core components, server entry point (src/server.ts) and embedding providers (src/embedding-provider.ts).
mcp-server-starrocks CLAUDE.md
Claude Code instructions for StarRocks/mcp-server-starrocks, covering claude.md, project overview, development commands, run the server directly for testing and run with test mode to verify table overview functionality.
gsd-task-manager copilot-instructions.md
Copilot instructions for vscarpenter/gsd-task-manager, covering copilot instructions for gsd task manager, architecture overview, core stack, database schema (v13) and key architectural decisions.
mongodb-mcp AGENTS.md
AGENTS.md instructions for VitalyOstanin/mongodb-mcp, covering repository guidelines, contributor notes, planning workflow, documentation guidelines and language policy.
mcp-database CLAUDE.md
Claude Code instructions for DiegoBulhoes/mcp-database, covering claude.md, commands, architecture, invariants (do not weaken) and adding or changing a tool.
orionbelt-analytics CLAUDE.md
Claude Code instructions for ralforion/orionbelt-analytics, a project described as: Ontology-based MCP server that analyzes database schemas (PostgreSQL, Snowflake, ClickHouse, Dremio) and generates RDF/OWL ontologies with SQL mappings for fan-trap-free Text-to-SQL.