An environment-variable management workflow that keeps variable names, examples, requirements, and usage aligned across a catalog, template, and code.

Use it when adding, renaming, removing, checking, sharing, or supplying environment variables to applications.

It reduces missing, renamed, inconsistent, or accidentally exposed configuration values and checks them without printing secret values.

env — Skill for Claude Code and Codex by me-cedric/agent-compass

Install

Getting it into your agent

It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.

Clone the repo

git clone --depth 1 https://github.com/me-cedric/agent-compass

agentmods

npx agentmods add skills/me-cedric/agent-compass/env

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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/me-cedric/agent-compass/env/github.svg)](https://agentmods.dev/skills/me-cedric/agent-compass/env)

Your own site

<a href="https://agentmods.dev/skills/me-cedric/agent-compass/env"><img src="https://agentmods.dev/badge/skills/me-cedric/agent-compass/env/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.

Your own site · 80×15

<a href="https://agentmods.dev/skills/me-cedric/agent-compass/env"><img src="https://agentmods.dev/badge/skills/me-cedric/agent-compass/env.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 1,425 The whole file, excluding the scripts and references it only reads on demand.

Security scan C 1 finding. A grade says what 26 rules found in the file — not that it is safe.

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.

Model	Per session	Once invoked
Fable 5.1	$0.00048	$0.01425
Opus 5.5	$0.00019	$0.00570
Sonnet 5.5	$0.00010	$0.00285
Haiku 4.5	$0.00005	$0.00143

Measured 10d ago against content hash 14a595ee3111, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade C, and why

env scanned grade C 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.

The scan reads SKILL.md. This mod also ships 1 executable file (assets/zod-catalog.mjs), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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.

Reaches for credential fileshighPrivilege escalation

SSH keys, cloud credentials, git-credentials, .npmrc, /etc/shadow: reading these is how a config file becomes a credential leak.

ac env import env-bundle.age # identity: ~/.ssh/id_ed25519, then id_rsa

packs/env/skills/env/SKILL.md · 121 lines

How it starts

The opening of the file, as written. The whole thing — 121 lines — stays where its author put it; the contents beside it link to each section on GitHub.

env

An env var has three homes: the catalog, the template and the code. Keep them equal.

Rule

A new env var changes the catalog, the template and the code in one task. A rename or a removal does the same. Then run ac env check.

Catalog

env.catalog.json is at the project root. It is optional, but it makes ac env check strict.

{
  "version": 1,
  "vars": [
    {
      "name": "LOG_LEVEL",
      "apps": ["api"],
      "description": "Log verbosity.",
      "default": "info",
      "example": "debug",
      "allowed": ["debug", "info", "warn"],
      "required": { "local": false, "ci": false, "staging": true, "prod": true }
    },
    { "name": "API_TOKEN", "secret": true, "pattern": "^[A-Za-z0-9_-]{20,}$", "required": { "local": true } }
  ]
}

name is UPPER_SNAKE_CASE and is unique.
Use allowed or pattern. Do not use both.
secret: true marks a value that must never reach a client bundle.
required has the keys local, ci, staging and prod.
Put a placeholder in the template. Do not put a real value there.

Check

ac env check          # one line for each finding
ac env check --json   # names, files and line numbers. Never a value.

Exit 1 means an error. A warning exits 0. Act on each finding:

Finding	Meaning	Action
`catalog`	The catalog has a shape error.	Fix `env.catalog.json`.
`public-secret`	A name with a public prefix looks like a secret. The prefixes are `VITE_`, `NEXT_PUBLIC_`, `EXPO_PUBLIC_`, `REACT_APP_`, `NUXT_PUBLIC_` and `PUBLIC_`.	Remove the prefix. Read the value on the server. Rotate it if it shipped.
`undeclared`	Code reads a name that nothing declares.	Add the name to the catalog and the template.
`missing`	A required name has no value, or no template lists it.	Set the value in the local file. Or add the name to the template.
`unreadable`	A tracked env file is missing on disk, or it cannot be read.	Restore the file. Or remove it from git.
`extra`	A file holds a name that nothing declares.	Add the name to the catalog. Or delete it.
`invalid`	A local value breaks `allowed` or `pattern`.	Ask the owner for a valid value.
`overlap`	Two templates share names, and one folder holds the other.	Keep a shared name in the outer template only.
`duplicate`	Two nested templates list the same names.	Delete the inner template.

Read the full file on GitHub · 121 lines

Files

What ships with it

1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

assets/zod-catalog.mjs 2.2 KB runs code

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.

10d ago First seen · 121 lines · 48 tokens per session scan C 14a595ee3111

Subscribe to this mod's changes

env is a skill published in the GitHub repository me-cedric/agent-compass (3 stars, last pushed 4d ago), licensed MIT. It adds 48 tokens to every session and 1,425 once invoked, about $0.0002 per session on Opus 5.5. A static security scan graded it C with 1 finding (reaches for credential files). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-10-18.

DevOps and cloud agent-skills agentic-ai ai ai-agents automation claude

worker-integration

Worker-Agent integration for intelligent task dispatch and performance tracking.

ruvnet/ruflo · 14 tokens

agentmail

Use your assigned AgentMail inbox to read email tasks, explicitly send or reply, and check delivery. Provided automatically by your inbox assignment.

paperclipai/paperclip · 30 tokens

foundry-config-setup

Resolve missing setup caused by a hardcoded Foundry project endpoint or model in a sample. Use when a sample fails because it uses a placeholder/hardcoded projectendpoint (for example "https://your-project.services.ai.azure.com") or a hardcoded model instead of reading them from the environment.

microsoft/agent-framework · 65 tokens

env