CASDA-MCP: Skill for Cursor

.cursor/skills/casda-reproducible-manifest/SKILL.md

casda-reproducible-manifest is a skill for Cursor from jbwod/CASDA-MCP. It costs 47 tokens per session (313 once invoked), scanned A, original, BSD-3-Clause.

A workflow for recording selected CASDA astronomy data products in a versioned, machine-readable manifest. CASDA is a data service for Australian astronomy observations.

In plain words
What is it for?
Use it after searching or inspecting products to record identifiers, metadata, checksums, sizes, release information, provenance, and collection details. It does not download files.
Why use it?
It preserves which products were selected and why, making a paper or data pipeline easier to reproduce without saving temporary download links.

Skill for Cursor

Written for Cursor: installed under .cursor/.

This is jbwod/CASDA-MCP's own configuration. It tells Cursor how to work on CASDA-MCP itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything CASDA-MCP configures →

Reuse

Borrowing it

Nothing to install: this file belongs to jbwod/CASDA-MCP. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/jbwod/CASDA-MCP/master/.cursor/skills/casda-reproducible-manifest/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/jbwod/CASDA-MCP

Made for: Cursor.

Wrote 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.

agentmods badge for casda-reproducible-manifest

README.md
[![agentmods](https://agentmods.dev/badge/skills/jbwod/casda-mcp/casda-reproducible-manifest/github.svg)](https://agentmods.dev/skills/jbwod/casda-mcp/casda-reproducible-manifest)
Your own site
<a href="https://agentmods.dev/skills/jbwod/casda-mcp/casda-reproducible-manifest"><img src="https://agentmods.dev/badge/skills/jbwod/casda-mcp/casda-reproducible-manifest/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.

agentmods 80×15 button for casda-reproducible-manifest

Your own site · 80×15
<a href="https://agentmods.dev/skills/jbwod/casda-mcp/casda-reproducible-manifest"><img src="https://agentmods.dev/badge/skills/jbwod/casda-mcp/casda-reproducible-manifest.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 47 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 313 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00047 $0.00313
Opus 5 $0.00023 $0.00156
Sonnet 5 $0.00009 $0.00063
Haiku 4.5 $0.00005 $0.00031

Measured 11d ago against content hash f31b5d742321, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

casda-reproducible-manifest 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 11d 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.

.cursor/skills/casda-reproducible-manifest/SKILL.md · 26 lines

What it actually says

CASDA reproducible manifest

Workflow

  1. Confirm the exact product_ids with the user after search/inspect.
  2. Optionally call casda_get_product for each ID so sizes, SBIDs, and release state are clear.
  3. Call casda_create_manifest with those IDs. Set source_name and workflow_name when the user supplies labels.
  4. Leave include_download_urls false. Artifact URLs are never persisted because opaque paths may be short-lived credentials; requesting true only records an omission warning.
  5. Re-read the manifest later via casda://manifests/{manifest_id} when persistent server state is enabled.

What the manifest includes

Typed product metadata, filenames, estimated sizes, available checksums, SBIDs, project codes, spatial/spectral fields, access state, known originating search criteria, sanitised provenance, and per-product collection_metadata (obs_collection, facility_name, release date span) plus a de-duplicated collections summary. For citation metadata call casda_resolve_collection_doi; never invent a DOI. The tool does not stage or download files.

Use MCP prompt build-reproducible-selection.

Changes

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.

  1. 11d ago First seen · 26 lines · 47 tokens per session scan A f31b5d742321

Subscribe to this mod's changes

casda-reproducible-manifest is a skill published in the GitHub repository jbwod/CASDA-MCP (0 stars, last pushed 1mo ago), licensed BSD-3-Clause. It adds 47 tokens to every session and 313 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 2026-08-31.

Related

Other skills, from other repositories

paper-search

Search, download, and read academic papers from 20+ sources (arXiv, PubMed, Semantic Scholar, CrossRef, etc). Use when the user asks to find papers, search for research, look up academic literature, download a paper PDF, or extract text from a paper.

openags/paper-search-mcp · 62 tokens

onescience-research-workflow

A research-workflow planning skill for OneScience, a system that coordinates scientific computing tasks. It creates detailed plans for fields such as weather, biology, materials, and fluid simulations, including steps, dependencies, resources, checks, and fallback paths.

onescience-ai/OneSkills · 70 tokens

onescience-modelscope-publish

A tool for preparing a reproduced research model for ModelScope, a platform for sharing machine-learning models. It organizes files into the platform’s expected directory structure and creates upload guidance.

onescience-ai/OneSkills · 81 tokens

onescience-cli

A skill for running OneScience command-line commands on remote SSH or SLURM systems. SSH is a way to use another computer remotely, while SLURM schedules jobs on shared computing clusters.

onescience-ai/OneSkills · 97 tokens

onescience-data-analyzer

A data-analysis skill for OneScience, a research-focused AI platform. It accepts task details from the conversation or from handoff files, then carries out analysis, charts, and report generation.

onescience-ai/OneSkills · 73 tokens

onescience-infer

A workflow tool for running scientific machine-learning models. It helps prepare inputs, load models or saved checkpoints, run predictions, check the results, create visualizations, and compare them with a baseline.

onescience-ai/OneSkills · 153 tokens