latitude-llm: Skill for Claude Code

.agents/skills/managing-maintenance-windows/SKILL.md

managing-maintenance-windows is a skill for Claude Code, Codex from latitude-dev/latitude-llm. It costs 48 tokens per session (682 once invoked), scanned A, original, MIT.

A control for putting Latitude’s public production services into maintenance mode by redirecting visitors to a status page. It can enable, disable, verify, or prepare that redirect.

In plain words
What is it for?
Use it to start or end a maintenance window, preview the infrastructure change, deploy it, and check the public redirects.
Why use it?
It provides a single infrastructure-level way to present a maintenance message when production services need planned downtime.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one. Also seen: installed under .agents/ (shared by several agents).

This is latitude-dev/latitude-llm's own configuration. It tells Claude Code and Codex how to work on latitude-llm itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything latitude-llm configures →

About the project

Latitude is an open-source platform for monitoring AI agents by collecting execution traces, grouping failures, dispatching coding agents to make fixes, and replaying failures to verify them. Teams use it to observe agent behavior, investigate errors, and monitor whether fixes prevent regressions. The catalogue entries include skills, instructions, and an MCP server for working with Latitude.

latitude-dev/latitude-llm · 4,632 stars · on GitHub · latitude.so

Reuse

Borrowing it

Nothing to install: this file belongs to latitude-dev/latitude-llm. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/latitude-dev/latitude-llm/development/.agents/skills/managing-maintenance-windows/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/latitude-dev/latitude-llm

Made for: Claude Code, Codex.

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 managing-maintenance-windows

README.md
[![agentmods](https://agentmods.dev/badge/skills/latitude-dev/latitude-llm/managing-maintenance-windows/github.svg)](https://agentmods.dev/skills/latitude-dev/latitude-llm/managing-maintenance-windows)
Your own site
<a href="https://agentmods.dev/skills/latitude-dev/latitude-llm/managing-maintenance-windows"><img src="https://agentmods.dev/badge/skills/latitude-dev/latitude-llm/managing-maintenance-windows/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.

agentmods 80×15 button for managing-maintenance-windows

Your own site · 80×15
<a href="https://agentmods.dev/skills/latitude-dev/latitude-llm/managing-maintenance-windows"><img src="https://agentmods.dev/badge/skills/latitude-dev/latitude-llm/managing-maintenance-windows.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 48 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 682 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 1 finding. A grade says what 26 rules found in the file — not that it is safe. Third-party audits
  • NVIDIA SkillSpector warn 7 Sept 2026
SkillSpector: 2 findings, up to medium

These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →

  • medium Data Exfiltration · line 31
    Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.
    Fix: Verify the destination URL is trusted and necessary. Remove or replace with documented APIs. Ensure no secrets, tokens, or PII are transmitted.
  • medium Data Exfiltration · line 52
    Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.
    Fix: Verify the destination URL is trusted and necessary. Remove or replace with documented APIs. Ensure no secrets, tokens, or PII are transmitted.
How audits are shown
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 5.1 $0.00048 $0.00682
Opus 5 $0.00024 $0.00341
Sonnet 5 $0.00010 $0.00136
Haiku 4.5 $0.00005 $0.00068

Measured 10d ago against content hash ff584d5b6164, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

managing-maintenance-windows scanned grade A with 1 finding 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.

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

curl -I https://console.latitude.so/
.agents/skills/managing-maintenance-windows/SKILL.md · 79 lines

How it starts

The opening of the file, as written. The whole thing — 79 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Managing maintenance windows

Use this skill when a user asks to enable, disable, verify, or prepare Latitude's production maintenance window.

What maintenance mode does

  • Maintenance mode is an ALB-level switch in infra/lib/alb.ts.
  • When enabled, all public production service hostnames redirect to https://status.latitude.so/: console.latitude.so, api.latitude.so, ingest.latitude.so, and bull-board.latitude.so.
  • The switch is controlled by the Pulumi production config key enableWebMaintenanceRedirect.
  • Do not implement this in apps/web: if a service is unhealthy, app-level redirects may not run.

Enable maintenance mode

From infra/:

pulumi config set enableWebMaintenanceRedirect true --stack production
pulumi preview --stack production
pulumi up --stack production

Then verify from outside the VPC:

curl -I https://console.latitude.so/
curl -I https://api.latitude.so/health
curl -I https://ingest.latitude.so/health
curl -I https://bull-board.latitude.so/

Expected result: all requests return an HTTP redirect with Location: https://status.latitude.so/.

Disable maintenance mode

From infra/:

pulumi config rm enableWebMaintenanceRedirect --stack production
pulumi preview --stack production
pulumi up --stack production

Then verify:

curl -I https://console.latitude.so/
curl -I https://api.latitude.so/health
curl -I https://ingest.latitude.so/health
curl -I https://bull-board.latitude.so/

Expected result: none of the requests redirects to https://status.latitude.so/. Services may return normal responses or auth redirects depending on the requested path.

Safety checklist

Before enabling:

  1. Confirm the user wants all publicly exposed production services redirected.
  2. Confirm https://status.latitude.so/ is live and has the relevant Better Stack maintenance or incident notice.
  3. Run pulumi preview --stack production and check that the ALB HTTPS listener default action and all public host rules change from forwarding to redirecting.
  4. Apply only after the user has approved the production change, unless they already explicitly asked to execute it.

Read the full file on GitHub · 79 lines

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. 10d ago First seen · 79 lines · 48 tokens per session scan A ff584d5b6164

Subscribe to this mod's changes

managing-maintenance-windows is a skill published in the GitHub repository latitude-dev/latitude-llm (4,632 stars, last pushed today), licensed MIT. It adds 48 tokens to every session and 682 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.