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/calkit/calkit/create-pipelinenpx skills add calkit/calkit --skill create-pipelinegit clone --depth 1 https://github.com/calkit/calkitWrote 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/calkit/calkit/create-pipeline)<a href="https://agentmods.dev/skills/calkit/calkit/create-pipeline"><img src="https://agentmods.dev/badge/skills/calkit/calkit/create-pipeline.svg" alt="Measured on agentmods" 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 | $0.00047 | $0.01415 |
| Opus 5 | $0.00023 | $0.00707 |
| Sonnet 5 | $0.00009 | $0.00283 |
| Haiku 4.5 | $0.00005 | $0.00142 |
Grade A, and why
create-pipeline 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 4d 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.
How it starts
The opening of the file, as written. The whole thing — 190 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Create a Calkit pipeline
Convert an existing repo with ad hoc scripts and manual steps into a fully
reproducible Calkit pipeline. When complete, calkit run should reproduce all
important outputs from scratch.
Step 1: Understand the existing repo
Before writing any YAML, map out what's already there. Start with the README. Users will typically write manual environment creation steps, and lists of script and commands to run in order. This is like a manual pipeline. Next:
- List all scripts and notebooks: look in
scripts/,notebooks/,src/, and the repo root for.py,.R,.jl,.m,.ipynbfiles. - Read each script to understand what it reads and writes.
- Identify the dependency order: which outputs of script A become inputs to script B?
- Note which environment each script needs (Python version, packages, R, Julia, MATLAB, Docker, etc.).
Ask the user if the order or dependencies are unclear. Do not guess at data flow.
Step 2: Initialize the project
If there is no calkit.yaml, run:
calkit init
This sets up Git (if needed) and DVC. If calkit.yaml already exists but has
no pipeline section, skip this—you will add one.
Step 3: Define environments
Every stage must reference a named environment. Identify what's needed:
- Python:
requirements.txtorpyproject.toml→uv-venv;environment.yml→conda - R:
renv.lock→renv - Julia:
Project.toml→julia - LaTeX:
dockerwithtexlive/texlive:latest-full - MATLAB:
matlab
Add environments to calkit.yaml:
environments:
main:
kind: uv-venv
path: requirements.txt
python: "3.13"
Name a single Python environment main. With multiple environments, use
descriptive names (e.g., analysis, paper).
Step 4: Try calkit xr first
For each script or notebook, try xr before writing YAML by hand. It
auto-detects stage kind, environment, and I/O:
calkit xr scripts/collect-data.py --dry-run # preview first
calkit xr scripts/collect-data.py # run for real
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.
- 4d ago First seen · 190 lines · 47 tokens per session scan A d851b0d620d0
create-pipeline is a skill published in the GitHub repository calkit/calkit (55 stars, last pushed today), licensed MIT. It adds 47 tokens to every session and 1,415 once invoked, about $0.0002 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
rrdoctor-verify
Use rrdoctor as the deterministic, offline definition of done for preparing a research repository for Artifact Evaluation or public release.
figure-style
Publication-grade correctness and legibility rules for final-deliverable scientific figures, not exploratory plots. Use for a figure that will ship in a report, paper, export, or kept artifact. Covers data fidelity, label economy, color threading, chart choice, layout, and render-then-verify QA without imposing a…
paper-narrative
Judge and reshape the story told by an entire paper figure deck. Use when writing or revising a paper to derive a grounded brief from the manuscript and captions, review the full deck as a handling editor, and hand an ordered figure arc to figure-composer.
remote-compute-ssh
Evaluate and use SSH Remote Compute before choosing where to run GPU, high-memory, parallel, batch, model-inference, bioinformatics, or other long-running scientific work; supports short remote commands and asynchronous jobs with automatic harvest and analysis.
scvi-tools
Probabilistic single-cell RNA-seq with scvi-tools — scVI for a batch-corrected latent space, scANVI for semi-supervised label transfer, and Bayesian differential expression. Reach for this skill to integrate scRNA-seq batches, embed cells for clustering, transfer annotations from a reference onto a query, or score…
customize
Use when the user wants to create or manage a Specialist agent or create, revise, publish, or delete a Skill through the conversational /Customize entry. Routes Skill work to the internal skill-creator and handles Specialist work through the JavaScript host.agents SDK.