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.
npx agentmods add skills/smana/cloud-native-ref/commitnpx skills add Smana/cloud-native-ref --skill commitgit clone --depth 1 https://github.com/Smana/cloud-native-refWhat 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 | $0.00033 | $0.00781 |
| Opus 5 | $0.00016 | $0.00391 |
| Sonnet 5 | $0.00007 | $0.00156 |
| Haiku 4.5 | $0.00003 | $0.00078 |
Grade C, and why
commit 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 yesterday.
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.
find . -type d \( -name ".terraform" -o -name ".terragrunt-cache" \) -exec rm -rf {} + 2>/dev/null How it starts
The opening of the file, as written. The whole thing — 106 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Commit Skill
Run pre-commit validation and create well-formatted commits with conventional format.
When to Use
- Pre-commit hooks needed
- Terraform files involved (needs cache cleanup)
- Want emoji reference for commit types
For simple commits without hooks: use Claude's native git capability.
Usage
/commit # Run pre-commit, then commit
/commit --no-verify # Skip pre-commit hooks
Project Rule
No Co-Authored-By lines - per CLAUDE.md, never include co-authoring footers.
Workflow
1. Pre-commit Validation (unless --no-verify)
Automatic setup (silent, no user confirmation):
- Clean Terraform temporary files:
find . -type d \( -name ".terraform" -o -name ".terragrunt-cache" \) -exec rm -rf {} + 2>/dev/null find . -name ".terraform.lock.hcl" -delete 2>/dev/null - Create virtual environment if needed:
uv venv - Install pre-commit:
uv pip install pre-commit - Install hooks:
pre-commit install
Run validation:
pre-commit run --all-files
If checks fail: analyze errors, provide recommendations, stop commit process.
2. Commit Format
<emoji> <type>: <description>
| Type | Emoji | Use Case |
|---|---|---|
feat |
✨ | New feature |
fix |
🐛 | Bug fix |
docs |
📝 | Documentation |
refactor |
♻️ | Code restructuring |
perf |
⚡️ | Performance |
test |
✅ | Tests |
chore |
🔧 | Tooling/config |
ci |
🚀 | CI/CD |
security |
🔒️ | Security fixes |
See references/emoji-guide.md for full emoji list.
3. Create Commit
git commit -m "$(cat <<'EOF'
<emoji> <type>: <description>
[Optional body explaining why]
EOF
)"
Pre-commit Failure Fixes
| Category | Fix |
|---|---|
| Terraform validation | Run terraform init in affected directories |
| Formatting | Re-run pre-commit (auto-fixes many issues) |
| Security issues | Manual review required |
| KCL formatting | Run kcl fmt in module directory |
| YAML/JSON syntax | Manual correction needed |
| Large files | Remove or use Git LFS |
What ships with it
1 file 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.
- yesterday First seen · 106 lines · 33 tokens per session scan C f6b01f64f0c0
commit is a skill published in the GitHub repository Smana/cloud-native-ref (99 stars, last pushed 2d ago), licensed Apache-2.0. It adds 33 tokens to every session and 781 once invoked, about $0.0002 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 2026-08-30.
Other skills, from other repositories
geoserver-cloud
Use when deploying GeoServer on Kubernetes as cloud-native microservices with auto-scaling, service discovery, and centralized configuration. GeoServer Cloud: break monolithic GeoServer into independently scalable WMS/WFS/WCS services.
Cloud Security & Container Hardening
AWS/Azure/GCP security auditing, container and Kubernetes hardening, Infrastructure as Code scanning, and cloud compliance assessment.
kubernetes-agent
Kubernetes production patterns — manifests, resource sizing, health probes, scaling, secrets, networking, and troubleshooting.
container-security
Performs a container and Kubernetes security review against the CIS Docker Benchmark v1.6.0, CIS Kubernetes Benchmark v1.9.0, and NIST SP 800-190. Auto-invoked when reviewing Dockerfiles, Kubernetes manifests, Helm charts, or container orchestration configurations. Evaluates image security, runtime hardening, RBAC…
r00-anthropics-skills--devops
☁️ DevOps & Cloud Infrastructure skill suite derived from anthropics/skills. CI/CD pipelines, container orchestration, IaC, monitoring and incident response. Provides 10 specialised commands for devops, cloud, docker workflows.
r00-vincenthopf-My-Claude-Code--devops
☁️ DevOps & Cloud Infrastructure skill suite derived from vincenthopf/My-Claude-Code. CI/CD pipelines, container orchestration, IaC, monitoring and incident response. Provides 10 specialised commands for devops, cloud, docker workflows.