Borrowing it
Nothing to install: this file belongs to berntpopp/clingen-link. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/berntpopp/clingen-link/main/.claude/skills/dependency-cve-sweep/SKILL.mdgit clone --depth 1 https://github.com/berntpopp/clingen-linkWrote 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/berntpopp/clingen-link/dependency-cve-sweep)<a href="https://agentmods.dev/skills/berntpopp/clingen-link/dependency-cve-sweep"><img src="https://agentmods.dev/badge/skills/berntpopp/clingen-link/dependency-cve-sweep/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/berntpopp/clingen-link/dependency-cve-sweep"><img src="https://agentmods.dev/badge/skills/berntpopp/clingen-link/dependency-cve-sweep.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 | $0.00033 | $0.00426 |
| Opus 5.5 | $0.00013 | $0.00170 |
| Sonnet 5.5 | $0.00007 | $0.00085 |
| Haiku 4.5 | $0.00003 | $0.00043 |
Grade A, and why
dependency-cve-sweep 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 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.
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.
This is a copy
94% identical to dependency-cve-sweep — 2 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
What it actually says
Dependency & CVE Sweep
Follow AGENTS.md first. Consolidate a repo's open Dependabot PRs into one clean PR rather than merging many.
Workflow
- Bump Python deps with
uv lock --upgrade-package <name>(targeted) oruv lock --upgrade(full); keepuv.lockcommitted and--frozenin the build. - SHA-pin GitHub Actions (
uses: owner/action@<40-char-sha> # vX.Y.Z), never floating tags. - Fix CodeQL findings at the cause; for the common
py/incomplete-url-substring-sanitizationtest-assertion false positive, switch to exact-match assertions. - Keep the Trivy gate in the ratified 2-step form (
severity: CRITICAL,HIGH+ignore-unfixed: true+exit-code: "1") and retain the SBOM (../genefoundry-router/docs/CONTAINER-HARDENING-STANDARD-v1.md). - Gate on
make ci-local; patch-bump the app version; squash-merge only on green.
Gotcha (FastMCP bumps)
When bumping FastMCP, verify validation-error wrapping: some 3.4.x releases re-raise argument-validation errors as fastmcp.exceptions.ValidationError, so a test asserting on a Pydantic ValidationError must walk __cause__. A version/catalog guard test may also need regenerating.
Common mistakes
- Merging Dependabot PRs one-by-one instead of one consolidated PR.
- Floating action tags instead of SHA pins.
- Flipping Trivy
exit-code: "1"withoutignore-unfixed: true— gates on unfixable base-image CVEs → self-inflicted outage.
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 · 27 lines · 33 tokens per session scan A 2f166dcdf36e
dependency-cve-sweep is a skill published in the GitHub repository berntpopp/clingen-link (0 stars, last pushed 3d ago), licensed MIT. It adds 33 tokens to every session and 426 once invoked, about $0.0001 per session on Opus 5.5. A static security scan graded it A with 0 findings. It is 94% identical to dependency-cve-sweep, differing in 2 lines, and is treated as a copy.
Other skills, from other repositories
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.
genomics-cnv-calling
Load when calling CNV segments via CBS-style segmentation on a bin-level log2-ratio CSV from exome / WGS coverage — emits per-segment 5-class CN state (amplification / gain / neutral / loss / deepdeletion), per-chromosome summary, genome-fraction-altered. Skip when working with single-cell / spatial CNV (use…
genomics-epigenomics
Load when summarising a peak file (BED / narrowPeak) from ATAC-seq / ChIP-seq / CUT&Tag — peak count, width distribution, per-chromosome counts, score statistics. Skip when calling peaks from BAM (run MACS / Genrich externally first); working with single-cell ATAC (use scatac-preprocessing).
genomics-phasing
Load when summarising a phased VCF (output of WhatsHap / SHAPEIT5 / Eagle2) — phased fraction of het variants, phase-block N50, PS-field parsing, pipe-delimited genotype detection. Skip when the input is unphased (run a phaser first); calling small variants (use genomics-variant-calling).
genomics-qc
Load when running pre-alignment FASTQ quality control — Phred quality scores, Q20/Q30 rates, GC / N content, read-length distribution, adapter-contamination detection. Skip when working with already-aligned BAMs (use genomics-alignment); peak / variant files are the input (use the relevant downstream skill).
genomics-sv-detection
Load when summarising structural variants from an SV VCF (DEL / DUP / INV / TRA) — INFO/SVTYPE-based classification, size classification, per-type counts. Skip when working with small SNVs / indels (use genomics-variant-calling); calling SVs from BAM (run Manta / Delly / Sniffles first).