envskill

envskill is a skill for Claude Code, Codex from buhaistrikalo/envskill. It costs 27 tokens per session (573 once invoked), scanned A, a copy of envskill, MIT.

A command-line boundary for using API keys and other environment secrets without exposing their values to commands or chat.

In plain words
What is it for?
It is for listing secret names, checking whether a required name exists, securely setting missing values, and running commands with selected environment variables.
Why use it?
It prevents secrets from being printed or pasted into conversations and limits commands to only the named credentials they need.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

Good fit It is for listing secret names, checking whether a required name exists, securely setting missing values, and running commands with selected environment variables.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/buhaistrikalo/envskill/bundled_skill
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.

Any agent
npx skills add buhaistrikalo/envskill --skill bundled_skill
Clone the repo
git clone --depth 1 https://github.com/buhaistrikalo/envskill

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 envskill

README.md
[![agentmods](https://agentmods.dev/badge/skills/buhaistrikalo/envskill/bundled_skill/github.svg)](https://agentmods.dev/skills/buhaistrikalo/envskill/bundled_skill)
Your own site
<a href="https://agentmods.dev/skills/buhaistrikalo/envskill/bundled_skill"><img src="https://agentmods.dev/badge/skills/buhaistrikalo/envskill/bundled_skill/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 envskill

Your own site · 80×15
<a href="https://agentmods.dev/skills/buhaistrikalo/envskill/bundled_skill"><img src="https://agentmods.dev/badge/skills/buhaistrikalo/envskill/bundled_skill.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 27 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 573 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.
Origin 100% copy Near-identical to another mod 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 $0.00027 $0.00573
Opus 5 $0.00014 $0.00287
Sonnet 5 $0.00005 $0.00115
Haiku 4.5 $0.00003 $0.00057

Measured 10d ago against content hash b81ebbbd08a4, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

envskill 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.

Origin

This is a copy

100% identical to envskill — 0 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.

src/envskill/bundled_skill/SKILL.md · 69 lines

How it starts

The opening of the file, as written. The whole thing — 69 lines — stays where its author put it; the contents beside it link to each section on GitHub.

envskill

Use envskill as the boundary between secret values and commands that need them.

First-time setup

If the CLI or store is not configured, ask the user to run the guided setup:

envskill setup

It initializes the owner-only store, detects supported agent hosts, installs this skill, and performs a value-free verification. To import an explicitly selected legacy dotenv file without displaying its values, use:

envskill setup --agent all --import ~/.env

Existing secret names are kept by default. Only add --overwrite when the user explicitly wants imported names to replace existing ones. A different existing skill copy is never replaced unless --force is explicitly supplied.

Workflow

  1. Discover names with envskill list. This command prints names only.

  2. Check a required name with envskill has NAME.

  3. Run the target command with the narrowest credential scope:

    envskill run --only NAME1,NAME2 -- command args...
    
  4. If a variable is missing, tell the user its name and ask them to run:

    envskill set NAME
    

    The command prompts for the value without echoing it. Never ask the user to paste a secret into chat.

Hard Rules

  • Never open, read, search, copy, summarize, or commit the envskill store.
  • Never reveal values through env, printenv, set, shell expansion, logs, or debug output.
  • Never use envskill run --all unless the user explicitly requests broad exposure.
  • The child starts with a minimal functional environment. Use --inherit NAME only when the target command requires a specific non-secret parent variable or capability.
  • Never place secret values in command arguments, prompts, source files, patches, or test fixtures.
  • A successful command is proof of availability. Do not inspect the injected value afterward.
  • If a command fails, report the variable name or command error, not credential contents.

Rotation

envskill reads its store on every invocation. After the user runs envskill set NAME, retry the original command through envskill run; restarting the agent is unnecessary.

Read the full file on GitHub · 69 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 · 69 lines · 27 tokens per session scan A b81ebbbd08a4

Subscribe to this mod's changes

envskill is a skill published in the GitHub repository buhaistrikalo/envskill (6 stars, last pushed 16d ago), licensed MIT. It adds 27 tokens to every session and 573 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it A with 0 findings. It is 100% identical to envskill, differing in 0 lines, and is treated as a copy.