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 BioSymphony/cryocore --skill cryocore-public-safetygit clone --depth 1 https://github.com/BioSymphony/cryocoreWrote 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/biosymphony/cryocore/cryocore-public-safety)<a href="https://agentmods.dev/skills/biosymphony/cryocore/cryocore-public-safety"><img src="https://agentmods.dev/badge/skills/biosymphony/cryocore/cryocore-public-safety/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/biosymphony/cryocore/cryocore-public-safety"><img src="https://agentmods.dev/badge/skills/biosymphony/cryocore/cryocore-public-safety.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 | $0.00040 | $0.00462 |
| Opus 5 | $0.00020 | $0.00231 |
| Sonnet 5 | $0.00008 | $0.00092 |
| Haiku 4.5 | $0.00004 | $0.00046 |
Grade A, and why
cryocore-public-safety 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 10d 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
CryoCore Public Safety
Use this skill before publishing, accepting PRs, or sharing generated outputs.
Read First
references/PUBLIC_RELEASE.mdreferences/SECURITY.mdreferences/data-policy.mdreferences/privacy-threat-model.mdreferences/public-repo-and-private-image-policy.mdreferences/claim-levels.md
Review Checklist
- No credentials, tokens, signed URLs, SSH keys, registry auth, or license files.
- No private paths, private clone instructions, private image namespaces, provider IDs, billing records, or raw provider logs.
- No raw movies, maps, half-maps, masks, particle stacks, private structures, unpublished sequences, model weights, or generated heavy outputs.
- No paid provider mutation or raw download is enabled by default.
- No
remote_launch_allowed: truein public bridge manifests. - Raw download contracts require explicit operator authorization at runtime.
- Claim ledgers downgrade unsupported mechanism, ligand, state, and biological claims.
- Public docs describe tool/license posture without redistributing gated tools.
Commands
make public-release-report
make release-check
Use those Make targets in a full CryoCore checkout. For targeted scans from a standalone skill install:
python3 scripts/cryocore/public_snapshot_check.py --repo-root <cryocore-repo> --profile public --json
python3 scripts/cryocore/public_release_report.py --repo-root <cryocore-repo> --json
When this skill is installed outside the CryoCore repo, resolve the bundled
scripts/cryocore/*.py paths relative to this skill folder and keep
--repo-root pointed at the CryoCore checkout being reviewed.
Output
Return findings first, ordered by severity, with file paths and line numbers. If there are no findings, say that and list residual risks such as unpinned provider images or operator-owned launch gates.
What ships with it
11 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.
- agents/openai.yaml 196 B
- agents/pack-metadata.json 662 B
- references/claim-levels.md 2.4 KB
- references/data-policy.md 2.9 KB
- references/privacy-threat-model.md 1.7 KB
- references/PUBLIC_RELEASE.md 3.5 KB
- references/public-repo-and-private-image-policy.md 1.6 KB
- references/SECURITY.md 1.5 KB
- scripts/cryocore/public_release_report.py 15 KB runs code
- scripts/cryocore/public_snapshot_check.py 6.2 KB runs code
- scripts/cryocore/runpod_manifest_check.py 14 KB runs code
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.
- 10d ago First seen · 57 lines · 40 tokens per session scan A ffbef9fe119b
cryocore-public-safety is a skill published in the GitHub repository BioSymphony/cryocore (5 stars, last pushed 9d ago), licensed MIT. It adds 40 tokens to every session and 462 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.
Other skills, from other repositories
gsva-analysis-and-visualization
Use this skill to run GSVA or ssGSEA pathway-level differential analysis from a bulk expression matrix and a sample group file, then generate a heatmap from the saved GSVA result object. Trigger keywords: GSVA, ssGSEA, pathway enrichment, KEGG pathway analysis, MSigDB. NOT for: gene-level differential expression…
lightgbm-analysis
Use when training a LightGBM model on tabular data in R and returning model metrics, feature importance ranking tables, and feature importance plots.
batch-effect-correction
Use when correcting batch effects in merged bulk expression matrices with sample-level batch metadata while preserving biological group structure and generating before-and-after QC plots. NOT for: single-cell integration, raw FASTQ processing, differential expression without batch labels, or datasets without…
decision-curve-analysis
Use when evaluating the clinical utility of a binary prediction model from a single clinical CSV file by fitting a logistic decision-curve model, plotting decision and clinical-impact curves, and exporting summary outputs. NOT for: survival calibration, ROC-only discrimination analysis, nomogram construction, or…
elastic-net-feature-selection
Use when selecting predictive genes or other molecular features from bulk expression matrices for binary case-vs-control classification with elastic net logistic regression, including coefficient path and cross-validation plots. Trigger keywords: elastic net, glmnet, feature selection, binary classification…
external-model-validation
Use when validating an existing prognostic risk signature on an external bulk expression cohort with survival outcomes, producing risk scores, Kaplan-Meier curves, risk distribution plots, heatmap, and time-dependent ROC curves. NOT for: model training, feature selection, nomogram construction, calibration analysis…