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 skills add Zandereins/schliff --skill bad-skillgit clone --depth 1 https://github.com/Zandereins/schliffWrote 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/zandereins/schliff/bad-skill)<a href="https://agentmods.dev/skills/zandereins/schliff/bad-skill"><img src="https://agentmods.dev/badge/skills/zandereins/schliff/bad-skill/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/zandereins/schliff/bad-skill"><img src="https://agentmods.dev/badge/skills/zandereins/schliff/bad-skill.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 | $0.00002 | $0.00289 |
| Opus 5 | $0.00001 | $0.00144 |
| Sonnet 5 | $0.00000 | $0.00058 |
| Haiku 4.5 | $0.00000 | $0.00029 |
Grade A, and why
deploy-helper 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 9d 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.
What it actually says
Deploy Helper
This skill helps with deployment stuff. It probably works for most deployment scenarios and you might want to use it when you need to deploy things.
What It Does
The deploy helper assists with deploying applications. It can maybe help with:
- Setting up deployment configurations
- Running deploy commands
- Checking if the deployment worked
- Handling some common deployment issues
How To Use
- Tell Claude you want to deploy something
- The skill will probably suggest some commands
- You should run the commands it suggests
- Check if everything is working
Configuration
You might want to set up some environment variables. The configuration depends on your setup and you could consider using a config file or maybe environment variables.
Make sure to save your configuration somewhere safe. Don't forget to test your deployment before going to production.
Deployment Steps
It is important to note that deployments can fail for various reasons. As mentioned above, you should always test your deployment. Keep in mind that different environments may behave differently.
The tool will help you with:
- Docker deployments (probably)
- Cloud deployments
- Local deployments
- Maybe serverless too
Troubleshooting
If something goes wrong, you might want to check the logs. Be careful when debugging production issues. Remember to commit your changes before deploying.
Always test your changes. Be aware that rollbacks may be necessary.
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.
- 9d ago First seen · 46 lines · 2 tokens per session scan A e232b6c4e66d
deploy-helper is a skill published in the GitHub repository Zandereins/schliff (15 stars, last pushed today), licensed MIT. It adds 2 tokens to every session and 289 once invoked, about $0.0000 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 2026-08-30.
Other skills, from other repositories
pypi-release
This skill should be used when releasing tunacode-cli to PyPI. It keeps the existing local release checks, then hands the actual PyPI upload to a GitHub Actions workflow that uses the repository's PYPIAPITOKEN secret.
skillcheck
Validates and scores SKILL.md files against the agentskills.io specification; use when linting skills for cross-agent compatibility, description quality, or capability graph structure.
pytorch-training
Train and optimize deep learning models with PyTorch. Use when building neural networks, implementing training loops, or optimizing model performance.
scikit-learn
Classical machine learning with scikit-learn. Use when building classification, regression, clustering models, or implementing feature engineering pipelines.
pandas-analysis
Data manipulation and analysis with pandas. Use when cleaning data, performing aggregations, merging datasets, or building analysis pipelines.
tensorflow-keras
Build and train models with TensorFlow and Keras. Use when implementing production ML models, using tf.data pipelines, or deploying with TF Serving.