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 causify-ai/helpers --skill tutorial_in_60_mins.propagate_docker_changesgit clone --depth 1 https://github.com/causify-ai/helpersWrote 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/causify-ai/helpers/tutorial_in_60_mins.propagate_docker_changes)<a href="https://agentmods.dev/skills/causify-ai/helpers/tutorial_in_60_mins.propagate_docker_changes"><img src="https://agentmods.dev/badge/skills/causify-ai/helpers/tutorial_in_60_mins.propagate_docker_changes/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/causify-ai/helpers/tutorial_in_60_mins.propagate_docker_changes"><img src="https://agentmods.dev/badge/skills/causify-ai/helpers/tutorial_in_60_mins.propagate_docker_changes.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 | $0.00011 | $0.00488 |
| Opus 5.5 | $0.00004 | $0.00195 |
| Sonnet 5.5 | $0.00002 | $0.00098 |
| Haiku 4.5 | $0.00001 | $0.00049 |
Grade A, and why
tutorial_in_60_mins.propagate_docker_changes 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 15d 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
Overview
<SRC_DIR>=class_project/project_template
This skill supports two modes:
- Full sync: Make all Docker files across projects match project_template
- Last-commit sync: Propagate only the changes from the most recent commit in project_template
Mode A: Full sync
- Find each target directory
<DST_DIR>: every directory underclass_project/(other than<SRC_DIR>itself) that already has aDockerfile> find class_project -mindepth 2 -maxdepth 2 -name Dockerfile \ -not -path "class_project/project_template/*" - For each
<DST_DIR>found this way - Make the Docker files
<DST_DIR>/docker_*.sh,<DST_DIR>/Dockerfile,<DST_DIR>/run_jupyter.shas similar as possible to the corresponding ones in<SRC_DIR>- The goal is to reuse functions and factored out code (e.g., from
class_project/project_template/utils.sh)
- The goal is to reuse functions and factored out code (e.g., from
- If you are not sure about what the changes are
- Summarize the changes for the user in bullet points
- Ask for the user to confirm
Mode B: Last-commit sync
- Use this mode when you only need to propagate the most recent changes
Check the Last Commit
- Look at the changes from the last git commit in
<SRC_DIR> - Summarize the changes for the user in bullet points
- If you are not sure about what the changes are, stop and ask for the user to confirm
Propagate the Changes
- Propagate the changes in the Docker system from
<SRC_DIR>to every<DST_DIR>found via thefindcommand in Mode A
Preserve Behavior
- Make sure not to change the behavior unless needed
Update the Docker Docs
- Update
class_project/project_template/docker_scripts.README.mdexplaining how this project uses Docker to build and execute containers given the new changes
Verification (both modes)
- All the
docker_*.shscripts work, run either directly or through the relevant pytest unit tests
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.
- 15d ago First seen · 54 lines · 11 tokens per session scan A 3bab338de106
tutorial_in_60_mins.propagate_docker_changes is a skill published in the GitHub repository causify-ai/helpers (153 stars, last pushed yesterday), licensed Apache-2.0. It adds 11 tokens to every session and 488 once invoked, about $0.0000 per session on Opus 5.5. 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 2026-10-13.
Other skills, from other repositories
yaml
Skill "yaml" from dhaupin/vant, covering yaml, when to use, what to do, 1. syntax and 2. anchors.
docker-python-lab
Generates an interactive Docker Python lab block for MkDocs textbook pages, where students write and run real Python code inside an isolated Docker container. Use this skill whenever someone asks to add a Python lab, code runner, interactive Python exercise, or runnable code block to a textbook page that uses Docker…
geogebra-setup
Set up the GeoGebra geometry plugin from a local checkout and diagnose its Node, Chromium, Gikz, and export-toolchain dependencies.
challenge-mentor
Technical mentor for Kubernetes/EKS hands-on challenges. Generates progressive labs from fundamentals to real-world troubleshooting scenarios sourced from community forums. Guides without giving answers - provokes thinking, gives progressive hints, and tracks progress. Activate when the user mentions 'desafio k8s'…
kubestronaut-coach
Coach for Kubernetes certification exams (CKA, CKAD, CKS, KCNA, KCSA) with focus on speed and shortcuts for performance-based tests. Use this skill when the user shares exam questions, challenges from KillerCoda/KillerShell, or asks for the fastest way to solve a Kubernetes task. Always provides the most performant…
lab
Sets up a Docker Compose-based lab environment. Creates a local environment for hands-on practice with technologies like Kafka, Elasticsearch, MySQL, and Redis, including monitoring. Use this skill when the user mentions practice, lab, or environment setup.