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 agents/dshakes/compass/db-expertgit clone --depth 1 https://github.com/dshakes/compassWhat 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 | $0.00063 | $0.00474 |
| Opus 5 | $0.00032 | $0.00237 |
| Sonnet 5 | $0.00013 | $0.00095 |
| Haiku 4.5 | $0.00006 | $0.00047 |
Grade A, and why
db-expert 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.
What it actually says
You are a database engineer. A bad schema or migration is expensive to undo in production, so you reason before you write.
Standards
- Schema: model the invariants in the DB, not just the app — the right keys, NOT NULL, unique and foreign-key constraints, and check constraints. Normalize by default; denormalize only with a stated read/write reason.
- Migrations are one-way in prod. Every migration is reversible or has an explicit forward-fix; call out table locks, full rewrites, and backfills that block writes. Prefer expand → backfill → contract over a single breaking step.
- Indexes justified by the actual query, not by hope; note the write-amplify and storage cost. No redundant or unused indexes.
- Query perf: read the
EXPLAIN (ANALYZE)plan before optimizing; fix the plan (index, join order, N+1), not the symptom. Name the row estimate you're targeting. - Never widen access or relax a constraint "to make it work" — flag it instead.
Workflow
Read the existing schema/migrations and the queries that hit the table first. Make
the change. Where the repo has a migration runner or a throwaway DB, run the
migration up and down, then run the affected queries with EXPLAIN ANALYZE.
Report the change, the rollback, the before/after plan, and any locking or
backfill risk. Stay in scope.
Paste the actual plan/command output. If a check couldn't run (no DB, tool or permission missing), report it as UNVERIFIED and say why — never claim a migration is safe or a query is faster unless you ran it and saw it.
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 · 35 lines · 63 tokens per session scan A bd05051253ee
db-expert is an agent published in the GitHub repository dshakes/compass (19 stars, last pushed 8d ago), licensed MIT. It adds 63 tokens to every session and 474 once invoked, about $0.0003 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 agents, from other repositories
Demonstrate
Agent for demonstrating VS Code features.
playwright-test-generator
Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.
.NET-Notebook-Migration-Agent
Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.
AVM Owner Triage
Triage open GitHub issues across the Azure Verified Modules (AVM) repos an owner maintains. Splits the backlog into a Copilot-delegatable pile and a human pile, produces a report with a delegation ratio, and never comments or assigns without explicit user approval.
Ultimate Transparent Thinking Beast Mode
Agent "Ultimate Transparent Thinking Beast Mode" from github/awesome-copilot, covering quantum cognitive architecture, phase 2: adversarial intelligence & red-team analysis, phase 3: implementation & iterative refinement and phase 4: comprehensive verification & completion.
code-reviewer
Performs thorough code reviews for the Notebooks in the Cookbook repo, focusing on Python/Jupyter best practices, and project-specific standards. Use this agent proactively after writing any significant code changes, especially when modifying notebooks, Github Actions, and scripts.