templates — independently scanned and version-tracked by SaferSkills.
SaferSkills independently audited templates (MCP Server) and scored it 100/100 (green). The audit ran 55 deterministic rules across Security, Supply Chain, Maintenance, Transparency, and Community; it found 0 high-severity and 0 lower-severity findings. The full rule-by-rule trace and per-finding evidence are below. Free, methodology-open.
Findings & checks · 0 flagged
Every scanned point with the score it earned and what moved between them.
First recorded scan — no prior version to compare against.
The primary manifest — the file an agent reads to learn what this artifact does.
My opinionated, docker-ized development environment for Claude Code CLI.
# clone and ignore
cd /path/to/your/project
git clone [email protected]:brianclaridge/.claude.git
# add .claude/ to your .gitignore
echo ".claude" >> .gitignore
# start claude
cd .claude/
task claude
# optional, add .claude as a submodule
git submodule add -b main [email protected]:brianclaridge/.claude.git
git submodule update --init --recursive --remote# run
task claude:fetch
# or
git submodule update --init --remote --merge .claude
# or
git -C .claude checkout main && git -C .claude pull origin main
# nuclear reset
git -C .claude fetch origin
git -C .claude reset --hard origin/main
git -C .claude clean -fdgit submodule deinit -f .claude
rm -rf .git/modules/.claude
git rm -f .claude
git commit -m "Remove .claude submodule"/workspace
├── README.md
├── Taskfile.yml
└── .claude/ # Git submodule
├── settings.json
├── docker-compose.yml
├── directives/ # Behavioral rules (000-080)
├── agents/ # Specialized analysis agents
├── skills/ # Model-invoked capabilities (git-manager)
├── hooks/ # Python event handlers (directive_loader, logger)
├── docker/ # Container build files
├── config/ # confd templates
└── aws/ # AWS SSO utilities~30 seconds. Free. No account. Every finding cites a rule and a line of evidence.