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.
git clone --depth 1 https://github.com/julianobarbosa/claude-code-skillsnpx agentmods add skills/julianobarbosa/claude-code-skills/direnvWrote 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.
[](https://agentmods.dev/skills/julianobarbosa/claude-code-skills/direnv)<a href="https://agentmods.dev/skills/julianobarbosa/claude-code-skills/direnv"><img src="https://agentmods.dev/badge/skills/julianobarbosa/claude-code-skills/direnv/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.
<a href="https://agentmods.dev/skills/julianobarbosa/claude-code-skills/direnv"><img src="https://agentmods.dev/badge/skills/julianobarbosa/claude-code-skills/direnv.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.00066 | $0.03360 |
| Opus 5 | $0.00033 | $0.01680 |
| Sonnet 5 | $0.00013 | $0.00672 |
| Haiku 4.5 | $0.00007 | $0.00336 |
Grade A, and why
direnv 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.
How it starts
The opening of the file, as written. The whole thing — 597 lines — stays where its author put it; the contents beside it link to each section on GitHub.
direnv Skill
This skill provides comprehensive guidance for working with direnv, covering installation, configuration, stdlib functions, and best practices for per-project environment management.
When to Use This Skill
Use this skill when:
- Installing and configuring direnv on macOS or Linux
- Creating or modifying
.envrcfiles for projects - Setting up per-project environment variables
- Configuring language-specific layouts (Python, Node.js, Ruby, Go, Perl)
- Integrating direnv with Nix or Nix Flakes
- Managing secrets and environment configuration for teams
- Troubleshooting environment loading issues
- Creating custom direnv extensions
Core Concepts
What is direnv?
direnv is a shell extension that loads and unloads environment variables based on the current directory. When you cd into a directory with a .envrc file, direnv automatically loads the environment. When you leave, it unloads the changes.
Security Model
direnv uses an allowlist-based security approach:
- New or modified
.envrcfiles must be explicitly allowed withdirenv allow - Prevents automatic execution of untrusted scripts
- Use
direnv denyto revoke access
How It Works
- Shell hook intercepts directory changes
- Checks for
.envrcfile in current or parent directories - If allowed, executes
.envrcin a bash subshell - Captures exported variables and applies them to current shell
Installation
macOS (Homebrew - Recommended)
brew install direnv
Linux
# Ubuntu/Debian
sudo apt install direnv
# Fedora
sudo dnf install direnv
# Arch
sudo pacman -S direnv
# Binary installer (any system)
curl -sfL https://direnv.net/install.sh | bash
Verify Installation
direnv version
Shell Configuration
Add the hook to your shell's config file. This is required for direnv to function.
Zsh (~/.zshrc)
eval "$(direnv hook zsh)"
With Oh My Zsh:
plugins=(... direnv)
Bash (~/.bashrc)
What ships with it
3 files 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.
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 · 597 lines · 66 tokens per session scan F 580ad2f8d95f
direnv is a skill published in the GitHub repository julianobarbosa/claude-code-skills (10 stars, last pushed 14d ago), licensed MIT. It adds 66 tokens to every session and 3,360 once invoked, about $0.0003 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.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…
next-partial-prefetching-adoption
Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…