ScienceClaw is an agent system for scientific work that completes tasks as typed, executable workflows and turns replay-verified improvements into reusable skills and operators. It is intended for AI-assisted research across natural and social science disciplines. The catalogue entries are its skills and instruction for use with the system.
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 beita6969/ScienceClaw --skill prosegit clone --depth 1 https://github.com/beita6969/ScienceClawWrote 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/beita6969/scienceclaw/prose)<a href="https://agentmods.dev/skills/beita6969/scienceclaw/prose"><img src="https://agentmods.dev/badge/skills/beita6969/scienceclaw/prose/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/beita6969/scienceclaw/prose"><img src="https://agentmods.dev/badge/skills/beita6969/scienceclaw/prose.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 6 findings, up to high
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- high Privilege Escalation · line 183 Code accesses credential files (SSH keys, AWS credentials, etc.). This could indicate credential theft attempts.Fix: Remove references to credential paths. Use environment variables or secrets managers. For docs, use placeholder paths (e.g., /path/to/config). Never load .env or token files in production code paths.
- high Privilege Escalation · line 184 Code accesses credential files (SSH keys, AWS credentials, etc.). This could indicate credential theft attempts.Fix: Remove references to credential paths. Use environment variables or secrets managers. For docs, use placeholder paths (e.g., /path/to/config). Never load .env or token files in production code paths.
- high Privilege Escalation · line 204 Code accesses credential files (SSH keys, AWS credentials, etc.). This could indicate credential theft attempts.Fix: Remove references to credential paths. Use environment variables or secrets managers. For docs, use placeholder paths (e.g., /path/to/config). Never load .env or token files in production code paths.
- high Privilege Escalation · line 208 Code accesses credential files (SSH keys, AWS credentials, etc.). This could indicate credential theft attempts.Fix: Remove references to credential paths. Use environment variables or secrets managers. For docs, use placeholder paths (e.g., /path/to/config). Never load .env or token files in production code paths.
- high Privilege Escalation · line 301 Code accesses credential files (SSH keys, AWS credentials, etc.). This could indicate credential theft attempts.Fix: Remove references to credential paths. Use environment variables or secrets managers. For docs, use placeholder paths (e.g., /path/to/config). Never load .env or token files in production code paths.
- medium MCP Rug Pull · line 207 Docker image references without a specific tag (:latest is implicit) or digest (@sha256:...) can be silently replaced by a malicious image.Fix: Pin the image: image:tag or image@sha256:abc123
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 | $0.00036 | $0.03559 |
| Opus 5.5 | $0.00014 | $0.01424 |
| Sonnet 5.5 | $0.00007 | $0.00712 |
| Haiku 4.5 | $0.00004 | $0.00356 |
Grade A, and why
prose scanned grade A 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 1mo 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
- **Remote fetch** == OpenClaw `web_fetch` (or `exec` with curl when POST is required) Copies of this mod
8 near-identical copies found in the catalogue:
- prose — 100% identical, 0 lines differ
- prose — 100% identical, 0 lines differ
- prose — 100% identical, 2 lines differ
- prose — 100% identical, 0 lines differ
- prose — 100% identical, 0 lines differ
- prose — 100% identical, 0 lines differ
- prose — 95% identical, 10 lines differ
- prose — 95% identical, 10 lines differ
How it starts
The opening of the file, as written. The whole thing — 324 lines — stays where its author put it; the contents beside it link to each section on GitHub.
OpenProse Skill
OpenProse is a programming language for AI sessions. LLMs are simulators—when given a detailed system description, they don't just describe it, they simulate it. The prose.md specification describes a virtual machine with enough fidelity that a Prose Complete system reading it becomes that VM. Simulation with sufficient fidelity is implementation. You are the Prose Complete system.
OpenClaw Runtime Mapping
- Task tool in the upstream spec == OpenClaw
sessions_spawn - File I/O == OpenClaw
read/write - Remote fetch == OpenClaw
web_fetch(orexecwith curl when POST is required)
When to Activate
Activate this skill when the user:
- Uses ANY
prosecommand (e.g.,prose boot,prose run,prose compile,prose update,prose help, etc.) - Asks to run a
.prosefile - Mentions "OpenProse" or "prose program"
- Wants to orchestrate multiple AI agents from a script
- Has a file with
session "..."oragent name:syntax - Wants to create a reusable workflow
Command Routing
When a user invokes prose <command>, intelligently route based on intent:
| Command | Action |
|---|---|
prose help |
Load help.md, guide user to what they need |
prose run <file> |
Load VM (prose.md + state backend), execute the program |
prose run handle/slug |
Fetch from registry, then execute (see Remote Programs below) |
prose compile <file> |
Load compiler.md, validate the program |
prose update |
Run migration (see Migration section below) |
prose examples |
Show or run example programs from examples/ |
| Other | Intelligently interpret based on context |
Important: Single Skill
There is only ONE skill: open-prose. There are NO separate skills like prose-run, prose-compile, or prose-boot. All prose commands route through this single skill.
What ships with it
60 files 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.
- alt-borges.md 7.0 KB
- alts/arabian-nights.md 9.9 KB
- alts/borges.md 11 KB
- alts/folk.md 9.9 KB
- alts/homer.md 9.4 KB
- alts/kafka.md 11 KB
- compiler.md 81 KB
- examples/01-hello-world.prose 118 B
- examples/02-research-and-summarize.prose 355 B
- examples/03-code-review.prose 821 B
- examples/04-write-and-refine.prose 643 B
- examples/05-debug-issue.prose 738 B
- examples/06-explain-codebase.prose 786 B
- examples/07-refactor.prose 830 B
- examples/08-blog-post.prose 840 B
- examples/09-research-with-agents.prose 890 B
- examples/10-code-review-agents.prose 1.0 KB
- examples/11-skills-and-imports.prose 888 B
- examples/12-secure-agent-permissions.prose 1.2 KB
- examples/13-variables-and-context.prose 1.9 KB
- examples/14-composition-blocks.prose 1.1 KB
- examples/15-inline-sequences.prose 647 B
- examples/16-parallel-reviews.prose 536 B
- examples/17-parallel-research.prose 565 B
- examples/18-mixed-parallel-sequential.prose 774 B
- examples/19-advanced-parallel.prose 2.3 KB
- examples/20-fixed-loops.prose 670 B
- examples/21-pipeline-operations.prose 1.2 KB
- examples/22-error-handling.prose 1.3 KB
- examples/23-retry-with-backoff.prose 1.5 KB
- examples/24-choice-blocks.prose 2.9 KB
- examples/25-conditionals.prose 3.0 KB
- examples/26-parameterized-blocks.prose 3.1 KB
- examples/27-string-interpolation.prose 3.2 KB
- examples/28-automated-pr-review.prose 1.4 KB
- examples/28-gas-town.prose 48 KB
- examples/29-captains-chair.prose 7.7 KB
- examples/30-captains-chair-simple.prose 1.3 KB
- examples/31-captains-chair-with-memory.prose 4.9 KB
- examples/33-pr-review-autofix.prose 4.4 KB
- examples/34-content-pipeline.prose 5.2 KB
- examples/35-feature-factory.prose 7.7 KB
- examples/36-bug-hunter.prose 6.2 KB
- examples/37-the-forge.prose 37 KB
- examples/38-skill-scan.prose 16 KB
- examples/39-architect-by-simulation.prose 9.3 KB
- examples/40-rlm-self-refine.prose 752 B
- examples/41-rlm-divide-conquer.prose 917 B
- examples/42-rlm-filter-recurse.prose 1.2 KB
- examples/43-rlm-pairwise.prose 1.2 KB
- examples/44-run-endpoint-ux-test.prose 8.2 KB
- examples/45-plugin-release.prose 4.5 KB
- examples/45-run-endpoint-ux-test-with-remediation.prose 19 KB
- examples/46-run-endpoint-ux-test-fast.prose 4.9 KB
- examples/46-workflow-crystallizer.prose 7.9 KB
- examples/47-language-self-improvement.prose 11 KB
- examples/48-habit-miner.prose 13 KB
- examples/49-prose-run-retrospective.prose 6.5 KB
- examples/README.md 14 KB
- examples/roadmap/iterative-refinement.prose 464 B
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.
- 1mo ago First seen · 324 lines · 36 tokens per session scan A 32857ea87a04
prose is a skill published in the GitHub repository beita6969/ScienceClaw (1,019 stars, last pushed 8d ago), licensed MIT. It adds 36 tokens to every session and 3,559 once invoked, about $0.0001 per session on Opus 5.5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
biopython
Comprehensive molecular biology toolkit. Use for sequence manipulation, file parsing (FASTA/GenBank/PDB), phylogenetics, and programmatic NCBI/PubMed access (Bio.Entrez). Best for batch processing, custom bioinformatics pipelines, BLAST automation. For quick lookups use gget; for multi-service integration use…
scanpy
Standard single-cell RNA-seq analysis pipeline. Use for QC, normalization, dimensionality reduction (PCA/UMAP/t-SNE), clustering, differential expression, and visualization. Best for exploratory scRNA-seq analysis with established workflows. For deep learning models use scvi-tools; for data format questions use…
structure-prediction
Protein structure prediction from sequence. ESMFold-based, single GPU, no MSA needed. Predicts 3D structures with pLDDT confidence scores for drug discovery targets.
biomcp
Search and retrieve biomedical data - genes, variants, clinical trials, diagnostic tests, articles, drugs, diseases, pathways, proteins, adverse events, pharmacogenomics, and phenotype-disease matching. Use for gene function, variant pathogenicity, trials, diagnostics, drug safety, pathway context, disease workups…
biomcp-research
Do biomedical literature and variant research with the BioMCP CLI, and file what you learn about the tool itself as issues in the biomcp repo.
biological-expert
Expert-level biology, biotechnology, genetics, bioinformatics, and computational biology. Use when the user mentions biology, biotechnology, genetics, bioinformatics, or genomics, or when the task involves Molecular Biology, Genomics & Bioinformatics, Systems Biology, or Data Analysis.