claude-devcontainer CLAUDE.md

claude-devcontainer CLAUDE.md is an instructions file for coding agents from ChrisSc/claude-devcontainer. It costs 1,825 tokens per session, scanned B, original, MIT.

Repository instructions for claude-sandbox, a Docker-based development container that provides a contained home for Claude Code.

In plain words
What is it for?
Use them when building or running this container, checking architecture support, handling startup order, maintaining Unix line endings, or configuring its firewall and Docker environment.
Why use it?
They explain how the container is built and started, plus details that prevent failures across Linux, macOS, and Windows environments.

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/chrissc/claude-devcontainer/claude-md
Clone the repo
git clone --depth 1 https://github.com/ChrisSc/claude-devcontainer

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-devcontainer CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/chrissc/claude-devcontainer/claude-md.svg)](https://agentmods.dev/instructions/chrissc/claude-devcontainer/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/chrissc/claude-devcontainer/claude-md"><img src="https://agentmods.dev/badge/instructions/chrissc/claude-devcontainer/claude-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 1,825 This file is loaded in full into every session.
When invoked 1,825 The same file — it is already loaded in full.
Security scan B 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 $0.01825 $0.01825
Opus 5 $0.00912 $0.00912
Sonnet 5 $0.00365 $0.00365
Haiku 4.5 $0.00183 $0.00183

Measured 3d ago against content hash 7920e10749e1, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade B, and why

claude-devcontainer CLAUDE.md scanned grade B 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 3d 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.

Asks for rootmediumPrivilege escalation

A mod that escalates privileges can change anything on the machine, not only the project.

`ENTRYPOINT` = `entrypoint.sh`, in order: (1) `sudo init-firewall.sh`,
CLAUDE.md · 107 lines

How it starts

The opening of the file, as written. The whole thing — 107 lines — stays where its author put it; the contents beside it link to each section on GitHub.

claude-sandbox

A modernized, security-sandboxed dev container that is a self-contained home for Claude Code. Container definition + config, not an app — the deliverable is the image and its startup behavior; there's nothing to run on the host. Everything lives in .devcontainer/.

What this repo is (and isn't)

  • Target runtime: any Docker host on arm64 or amd64 — native Linux, Docker Desktop on macOS, or Windows WSL2. Support is gated on arch, not OS (everything runs in a Linux container; install-tools.sh errors on non-arm64/amd64). Builds native to the host arch — no platform: pin (would force slow emulation). Native Linux runs the firewall fully (iptables/ipset in-kernel); macOS/Windows add a Docker Desktop VM layer — the source of the inode-pinned bind-mount and WSL2-vs-Hyper-V firewall caveats.
  • Scripts must stay LF (enforced by .gitattributes + a defensive sed 's/\r$//' in the Dockerfile); CRLF from a Windows checkout breaks the entrypoint with bad interpreter: …^M. The firewall needs Docker's WSL2 backend on Windows (NET_ADMIN + iptables/ipset); the legacy Hyper-V backend won't load the rules.

Build & run

docker compose -f .devcontainer/compose.yaml up -d --build   # or: make up
docker exec -it claude-code zsh -l                            # or: make shell

Compose project (group) = claude; container = claude-code. Makefile targets are self-documented — each carries a trailing ## … description.

Startup order (load-bearing)

ENTRYPOINT = entrypoint.sh, in order: (1) sudo init-firewall.sh, (2) seed-claude.sh, (3) claude update (bounded by timeout, non-fatal), (4) init-aws-toolkit.sh, (5) init-cron.sh, then execs the compose command (sleep infinity). Ordering matters — the firewall must be up before the auto-update reaches downloads.claude.ai, before the AWS skill catalog is fetched, and before cron jobs fire; the AWS step runs after the update so it drives the current claude CLI. The VS Code path re-runs firewall + update + aws-toolkit + cron via devcontainer.json postStartCommand as an idempotent safety net.

Read the full file on GitHub · 107 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. 3d ago First seen · 107 lines · 1,825 tokens per session scan B 7920e10749e1

Subscribe to this mod's changes

claude-devcontainer CLAUDE.md is an instructions file published in the GitHub repository ChrisSc/claude-devcontainer (2 stars, last pushed 4d ago), licensed MIT. It adds 1,825 tokens to every session, about $0.0091 per session on Opus 5. A static security scan graded it B with 1 finding (asks for root). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.