latitude-llm: Skill for Claude Code

.agents/skills/env-configuration/SKILL.md

env-configuration is a skill for Claude Code, Codex from latitude-dev/latitude-llm. It costs 28 tokens per session (899 once invoked), scanned A, original, MIT.

A project guide for adding, reading, and validating environment variables, which are configuration values supplied outside application code. It defines a LAT_ naming convention, updates .env.example, and uses startup parsers such as parseEnv.

In plain words
What is it for?
Adding application settings, reading optional or required values, maintaining the example environment file, and validating configuration when the app starts.
Why use it?
It prevents configuration names from colliding with other services and keeps required settings documented and checked at startup.

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 · 4,631 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/env-configuration/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 env-configuration

README.md
[![agentmods](https://agentmods.dev/badge/skills/latitude-dev/latitude-llm/env-configuration.svg)](https://agentmods.dev/skills/latitude-dev/latitude-llm/env-configuration)
Your own site
<a href="https://agentmods.dev/skills/latitude-dev/latitude-llm/env-configuration"><img src="https://agentmods.dev/badge/skills/latitude-dev/latitude-llm/env-configuration.svg" alt="Measured on agentmods" height="20"></a>
Per session 28 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 899 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. 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: 1 finding, up to high

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 →

  • high Privilege Escalation · line 45
    Code accesses credential files (SSH keys, AWS credentials, etc.). This could indicate credential theft attempts.
    Fix: Remove references to credential paths. Use environment variables or secrets managers. For docs, use placeholder paths (e.g., /path/to/config). Never load .env or token files in production code paths.
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 $0.00028 $0.00899
Opus 5 $0.00014 $0.00449
Sonnet 5 $0.00006 $0.00180
Haiku 4.5 $0.00003 $0.00090

Measured 8d ago against content hash 381699f6e86b, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

env-configuration 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 8d 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.

.agents/skills/env-configuration/SKILL.md · 67 lines

How it starts

The opening of the file, as written. The whole thing — 67 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Environment configuration

When to use: Adding or reading env vars, updating .env.example, or validating config at startup with parseEnv / parseEnvOptional.

LAT_ prefix convention

All application environment variables must be prefixed with LAT_ so they do not collide with third-party services, Docker, or common names.

Use LAT_ for:

  • Database URLs and pool settings (LAT_DATABASE_URL, LAT_PG_POOL_MAX, …)
  • Service endpoints the app reads (LAT_CLICKHOUSE_URL, LAT_REDIS_HOST, …)
  • App ports (LAT_API_PORT, LAT_WEB_PORT, LAT_INGEST_PORT)
  • Auth, email, OAuth, billing, CORS (LAT_BETTER_AUTH_SECRET, LAT_MAILPIT_HOST, …)
  • Any new variable consumed by Latitude application code

Do not use LAT_ for:

  • NODE_ENV
  • Docker-only init variables (POSTGRES_USER, CLICKHOUSE_USER, …)
  • Config read only by container images (Weaviate, Redis in compose, etc.)
  • Browser-exposed Vite vars: use VITE_LAT_* (Vite requires the VITE_ prefix)

Reference: .env.example lists Docker “Services” vs “Latitude Application” (LAT_*) variables.

.env.example maintenance

Every new variable must appear in .env.example:

  • Required: uncommented with a sensible local default (e.g. LAT_API_PORT=3001)
  • Optional: commented with a placeholder (e.g. # LAT_STRIPE_SECRET_KEY=sk_test_xxx)

Keep the self-host surfaces in sync

Self-hosters configure Latitude through these env vars, so adding, renaming, or removing one means updating more than .env.example. Whenever you touch a LAT_* var, also reflect it in:

  1. The configuration reference docs/deployment/configuration.mdx — so operators know what the var does — unless it is specific to Latitude's own cloud deployment, which stays out of the self-host docs: payments/Stripe, marketing/lifecycle email (Loops), support chat (Intercom), and internal analytics/observability vendors (PostHog, Datadog/OTEL export, GTM, Framer, ipinfo). General app/infra/auth/AI/email-transport vars all belong in the reference.
  2. The Helm chart charts/latitude/ — decide where the var belongs:
    • non-secret → templates/configmap.yaml (and a values.yaml knob if it's a first-class setting);
    • secret → templates/secret.yaml and the chart README's existingSecret key list;
    • optional/rare → no template change needed; the documented config.extraEnv / secrets.extra pass-through already covers it.

Read the full file on GitHub · 67 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. 8d ago First seen · 67 lines · 28 tokens per session scan A 381699f6e86b

Subscribe to this mod's changes

env-configuration is a skill published in the GitHub repository latitude-dev/latitude-llm (4,631 stars, last pushed today), licensed MIT. It adds 28 tokens to every session and 899 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 2026-08-30.