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 isdaniel/pgtuner_mcp --skill pg-vacuum-tuninggit clone --depth 1 https://github.com/isdaniel/pgtuner_mcpWrote 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/isdaniel/pgtuner_mcp/pg-vacuum-tuning)<a href="https://agentmods.dev/skills/isdaniel/pgtuner_mcp/pg-vacuum-tuning"><img src="https://agentmods.dev/badge/skills/isdaniel/pgtuner_mcp/pg-vacuum-tuning/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/isdaniel/pgtuner_mcp/pg-vacuum-tuning"><img src="https://agentmods.dev/badge/skills/isdaniel/pgtuner_mcp/pg-vacuum-tuning.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 | $0.00049 | $0.03437 |
| Opus 5 | $0.00024 | $0.01718 |
| Sonnet 5 | $0.00010 | $0.00687 |
| Haiku 4.5 | $0.00005 | $0.00344 |
Grade A, and why
pg-vacuum-tuning 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 10d 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 — 352 lines — stays where its author put it; the contents beside it link to each section on GitHub.
PostgreSQL Vacuum Tuning
This skill guides monitoring, troubleshooting, and tuning of PostgreSQL vacuum operations using pgtuner-mcp tools.
When to Use This Skill
Use this skill when the user:
- Asks about autovacuum configuration or tuning
- Reports autovacuum running too slowly or too aggressively
- Mentions transaction ID wraparound warnings
- Sees tables accumulating dead tuples
- Asks "why is autovacuum always running?" or "why isn't autovacuum cleaning my table?"
- Reports table bloat growing over time
- Wants to understand vacuum progress on a long-running operation
- Asks about VACUUM FREEZE or preventing forced shutdowns
MCP Resources Available
pgtuner://settings/autovacuum-- Current autovacuum configuration (lightweight)pgtuner://health/bloat-- Quick bloat assessmentpgtuner://table/{schema}/{table_name}/stats-- Per-table dead tuple counts and vacuum timestamps
Related MCP Prompt
This skill is related to the health_check MCP Prompt (wraparound dimension) and the vacuum aspects of pg-bloat-analysis skill.
Prerequisites
- The pgtuner-mcp server must be connected with a valid
DATABASE_URI - Access to
pg_stat_activity,pg_stat_user_tables,pg_stat_progress_vacuum
Agent Decision Tree
User asks about vacuum
|
+--> "Why is autovacuum always running?"
| --> Start Step 1 (progress), then Step 3 (autovacuum config)
| --> May be normal for high-churn tables. Check if it's completing.
|
+--> "Why isn't my table being vacuumed?"
| --> Start Step 2 (needs_vacuum), then Step 3 (autovacuum config)
| --> Check if scale_factor threshold is too high for large tables
|
+--> "Transaction wraparound warning"
| --> URGENT: Start Step 2 (needs_vacuum), check XID age
| --> IF XID age > 1.2B: Go to Emergency Procedures immediately
|
+--> "How long will this vacuum take?"
| --> Start Step 1 (progress) to see current phase and completion %
|
+--> "General vacuum tuning"
--> Follow Steps 1-4 in order, then Tuning Recommendations
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.
- 10d ago First seen · 352 lines · 49 tokens per session scan A 338819f48fea
pg-vacuum-tuning is a skill published in the GitHub repository isdaniel/pgtuner_mcp (29 stars, last pushed 3mo ago), licensed Apache-2.0. It adds 49 tokens to every session and 3,437 once invoked, about $0.0002 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 skills, from other repositories
amazon aurora dsql
Deprecated compatibility redirect for Aurora DSQL guidance. Use when a request concerns DSQL, Aurora DSQL, distributed SQL, DSQL schemas, migrations, queries, authentication, performance, or application development.
exasol-table-design
Exasol table design for performance: DISTRIBUTE BY, PARTITION BY, zone maps, data types, replication, surrogate keys, and CREATE TABLE syntax.
exasol-udfs
Exasol User-Defined Functions (UDFs) and Scripts: CREATE SCRIPT syntax, language options, SQL-to-language data type mappings, ExaIterator API, BucketFS access, and Script Language Containers.
exasol-import-export
Exasol IMPORT and EXPORT SQL statements: syntax, file formats (CSV, FBV, Parquet), cloud storage (S3, Azure, GCS), connection objects, error handling, and ETL staging patterns.
exasol-system-tables
Exasol system and statistics tables: what they contain, visibility prefixes (EXAALL, EXADBA, EXAUSER), and when to query them directly vs using MCP tools.
exasol-sql-dialect
Exasol SQL dialect specifics: syntax, data types, functions, and common pitfalls for generating correct Exasol SQL.