claude-env CLAUDE.md

claude-env CLAUDE.md is an instructions file for coding agents from 1shooperman/claude-env. It costs 314 tokens per session, scanned C, original, MIT.

A set of project instructions for claudenv, a shell tool that switches between Claude Code account environments. It documents supported shells, project rules, GitHub Actions rules, and tests.

In plain words
What is it for?
Use it when developing, testing, or reviewing the claudenv project and its GitHub Actions configuration.
Why use it?
It gives coding agents the repository's constraints before they change code or workflows. This helps avoid incompatible shell features, dependency changes, or incorrect release practices.

Instructions file

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.

agentmods
npx agentmods add instructions/1shooperman/claude-env/claude-md
Clone the repo
git clone --depth 1 https://github.com/1shooperman/claude-env

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 claude-env CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/1shooperman/claude-env/claude-md.svg)](https://agentmods.dev/instructions/1shooperman/claude-env/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/1shooperman/claude-env/claude-md"><img src="https://agentmods.dev/badge/instructions/1shooperman/claude-env/claude-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 314 This file is loaded in full into every session.
When invoked 314 The same file — it is already loaded in full.
Security scan C 1 finding. Scan, not verified.
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 $0.00314 $0.00314
Opus 5 $0.00157 $0.00157
Sonnet 5 $0.00063 $0.00063
Haiku 4.5 $0.00031 $0.00031

Measured 4d ago against content hash 5b6fa126899e, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade C, and why

claude-env CLAUDE.md 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 4d 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.

Recursive force deletehighDestructive command

rm -rf with a variable or a broad path is one typo away from removing the wrong tree.

rm -rf "$CLAUDENV_HOME/envs/test-env"
CLAUDE.md · 35 lines

What it actually says

claudenv

Shell environment switcher for Claude Code accounts.

Key constraints

  • install.sh must stay POSIX sh — no arrays, no select, no process substitution.
  • claudenv.sh targets bash 3.2+ and zsh 5+; arrays, select, and < <(...) are intentional.
  • No external dependencies. No build step.

GitHub Actions constraints

  • Do not pin actions to commit SHAs. Use semver tags (e.g. @v2, @v6). Dependabot keeps tags current.
  • Do not replace apt-installed tools with pinned binary downloads in Dockerfile.dev (e.g. shellcheck stays as apt-get install shellcheck).
  • Do not add update-type guards to dependabot-automerge.yml. All dependabot PRs are auto-merged, not just patch bumps.

Development constraints

  • a new branch and PR should be created per ralph-loop invocation, or any change set.

Testing

source claudenv.sh
claudenv config test-env
claudenv test-env          # prompt should show (test-env)
claudenv deactivate
rm -rf "$CLAUDENV_HOME/envs/test-env"

Test oh-my-zsh prompt integration by sourcing in an active zsh session with a theme loaded.

Post PR creation

After you have created a PR, use the update-docs local claude skill.

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. 4d ago First seen · 35 lines · 314 tokens per session scan C 5b6fa126899e

Subscribe to this mod's changes

claude-env CLAUDE.md is an instructions file published in the GitHub repository 1shooperman/claude-env (2 stars, last pushed 2mo ago), licensed MIT. It adds 314 tokens to every session, about $0.0016 per session on Opus 5. A static security scan graded it C with 1 finding (recursive force delete). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.