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 skills add drhalto/agentmako --skill mako-databasegit clone --depth 1 https://github.com/drhalto/agentmakoWrote 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/drhalto/agentmako/mako-database)<a href="https://agentmods.dev/skills/drhalto/agentmako/mako-database"><img src="https://agentmods.dev/badge/skills/drhalto/agentmako/mako-database/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/drhalto/agentmako/mako-database"><img src="https://agentmods.dev/badge/skills/drhalto/agentmako/mako-database.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00053 | $0.00663 |
| Opus 5.5 | $0.00021 | $0.00265 |
| Sonnet 5.5 | $0.00011 | $0.00133 |
| Haiku 4.5 | $0.00005 | $0.00066 |
Grade A, and why
mako-database 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 1mo 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 — 88 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Mako Database
Use this skill for direct database introspection. These tools require the project to have a live DB binding configured. If the user asks how app code uses database objects, use trace or neighborhood tools instead.
Tools
db_ping
Use to verify database connectivity and project wiring.
- Best when DB tools seem unavailable or the user asks whether the DB is connected.
- Use before deeper DB queries when the binding is uncertain.
db_columns
Use to inspect columns and primary-key details for one or more tables.
- Best for narrow column questions.
- Use
db_table_schemawhen indexes, constraints, triggers, or broader table shape matter.
db_fk
Use to inspect foreign keys and relationships.
- Best for inbound/outbound relationship questions.
- Pair with
table_neighborhoodwhen code readers/writers also matter.
db_rls
Use to inspect row-level security status and policies.
- Best for policy and protection questions.
- Pair with
tenant_leak_auditfor broader tenant-boundary risk review.
db_rpc
Use to inspect database RPC/function definitions, signatures, args, return shape, language, and security.
- Pair with
rpc_neighborhoodortrace_rpcwhen app-code callers matter.
db_table_schema
Use to inspect the full table shape, including columns, indexes, constraints, foreign keys, RLS, and triggers.
- Use when column-only output is insufficient.
- Pair with
trace_tableortable_neighborhoodwhen code usage matters.
Feedback Logging
Log agent_feedback when a DB introspection result here was notably
useful, partial, noisy, stale, wrong, or wasted the turn. Skip routine
calls.
Required procedure (see /mako-ai:mako-guide for full rules and
reason-code vocabulary):
- Call
recall_tool_runsto get the prior run'srequestId. Do not fabricate one — if no run is recalled, skip feedback. - Call
agent_feedbackwithreferencedToolName,referencedRequestId,grade: "full" | "partial" | "no",reasonCodesfrom the starter vocabulary in/mako-ai:mako-guide, and a shortreason.
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.
- 1mo ago First seen · 88 lines · 53 tokens per session scan A 3621b86e7086
mako-database is a skill published in the GitHub repository drhalto/agentmako (54 stars, last pushed 2mo ago), licensed Apache-2.0. It adds 53 tokens to every session and 663 once invoked, about $0.0002 per session on Opus 5.5. 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 skills, from other repositories
connect
Install the scoped Antigravity permission hook.
status
Show enabled Multi providers and the local runtime status.
uninstall
Remove Multi startup files while preserving provider credentials.
login
Start the official Cursor SDK login flow.
mirrord-db-branching
Helps users configure mirrord.json for database branching, enabling isolated database copies for safe development and testing. Use when the user wants to set up MySQL, MariaDB, PostgreSQL, MSSQL, MongoDB, Redis, DynamoDB, ClickHouse, Google Spanner, Amazon S3, turbopuffer, or generic branches, configure copy modes…
ctxo-safe-edit
Use BEFORE editing, renaming, or deleting any function, class, or method, to avoid breaking dependents.