slow

slow is a command for coding agents from fridzema/clockwork-mcp. It costs 10 tokens per session (449 once invoked), scanned A, original, MIT.

A command that finds database queries taking more than 100 milliseconds in recent web requests.

In plain words
What is it for?
Use it to inspect the latest request, a number of recent requests, a time window, a URL pattern, or a specific request ID.
Why use it?
It helps locate database work that may be making an application or endpoint slow, across one or many requests.

Command

Part of the clockwork plugin — 4 commands, 1 MCP server shipped together

Install

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.

agentmods
npx agentmods add commands/fridzema/clockwork-mcp/slow
Clone the repo
git clone --depth 1 https://github.com/fridzema/clockwork-mcp

Or install clockwork, the plugin that ships this one along with the rest of its 4 commands, 1 MCP server.

Wrote 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.

agentmods badge for slow

README.md
[![agentmods](https://agentmods.dev/badge/commands/fridzema/clockwork-mcp/slow.svg)](https://agentmods.dev/commands/fridzema/clockwork-mcp/slow)
Your own site
<a href="https://agentmods.dev/commands/fridzema/clockwork-mcp/slow"><img src="https://agentmods.dev/badge/commands/fridzema/clockwork-mcp/slow.svg" alt="Measured on agentmods" height="20"></a>
Per session 10 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 449 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00010 $0.00449
Opus 5 $0.00005 $0.00225
Sonnet 5 $0.00002 $0.00090
Haiku 4.5 $0.00001 $0.00045

Measured 3d ago against content hash 59004e195e9f, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

slow 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 3d 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.

commands/slow.md · 63 lines

What it actually says

Use the analyze_slow_queries MCP tool to find slow database queries.

Scope Options

By default, analyzes only the latest request. Use these options to analyze multiple requests:

  • count: Number of recent HTTP requests (e.g., count: 10)
  • since: Time duration to look back (e.g., since: "1h", since: "30m", since: "2d")
  • all: Analyze all available requests (max 100)
  • uri: Filter by URI pattern (e.g., uri: "/api/users")
  • requestId: Analyze specific request by ID

Examples:

  • Latest request only: analyze_slow_queries (no scope params)
  • Last 10 requests: analyze_slow_queries with count: 10
  • Last hour: analyze_slow_queries with since: "1h"
  • Specific endpoint: analyze_slow_queries with count: 20, uri: "/api/orders"

Output Format

For single request:

Slow Queries (>100ms)

Found N slow queries in request [METHOD] /uri/path

# Duration Query
1 XXX ms SELECT ...

For multiple requests:

Slow Queries (>100ms) - Last N Requests

Analyzed N requests, found M slow queries in K requests

Pattern 1: X occurrences (max XXX ms)

SELECT * FROM table WHERE column = ?

Affected: GET /api/users (3x), POST /api/orders (2x)

Pattern 2: Y occurrences (max XXX ms)

UPDATE table SET column = ? WHERE id = ?

Affected: PUT /api/users/1

Recommendations

  • Add indexes for frequently queried columns
  • Consider caching for repeated queries
  • Use eager loading to reduce query count

If no slow queries are found:

Slow Queries (>100ms)

No slow queries found. All queries executed under 100ms.

Changes

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.

  1. 3d ago First seen · 63 lines · 10 tokens per session scan A 59004e195e9f

Subscribe to this mod's changes

slow is a command published in the GitHub repository fridzema/clockwork-mcp (4 stars, last pushed 7mo ago), licensed MIT. It adds 10 tokens to every session and 449 once invoked, about $0.0001 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.