Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/nisconder/npm-safenpx agentmods add skills/nisconder/npm-safe/npm-safe-scanWrote 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/nisconder/npm-safe/npm-safe-scan)<a href="https://agentmods.dev/skills/nisconder/npm-safe/npm-safe-scan"><img src="https://agentmods.dev/badge/skills/nisconder/npm-safe/npm-safe-scan/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/nisconder/npm-safe/npm-safe-scan"><img src="https://agentmods.dev/badge/skills/nisconder/npm-safe/npm-safe-scan.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 | $0.00128 | $0.02679 |
| Opus 5 | $0.00064 | $0.01340 |
| Sonnet 5 | $0.00026 | $0.00536 |
| Haiku 4.5 | $0.00013 | $0.00268 |
Grade A, and why
npm-safe-scan 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.
How it starts
The opening of the file, as written. The whole thing — 210 lines — stays where its author put it; the contents beside it link to each section on GitHub.
npm-safe-scan
This skill invokes the npm-safe CLI to statically and semantically analyze published npm metadata and README content for supply-chain security risks. The engine inspects suspicious install and lifecycle scripts, obfuscation signals, typosquatting and homograph lookalikes, exposed secrets, malicious binary links, and registry mismatches, then assigns a security score and severity level. Results are cached in a local SQLite database (default ~/.npm-safe/npm-safe.db), requests are rate-limited to respect the registry, and everything runs locally with no external server required. The current engine does not inspect package tarball source, so never describe a clean result as proof that a package is safe.
Core rule: check before you install
Whenever the user wants to install, add, or upgrade an npm package (including transitive dependencies of something they install), run a security check FIRST:
- Identify the package name and version.
- Run
npm-safe check <name>(add--refreshif a cached result may be stale). - Interpret the result:
- safe — no configured signal was detected in the current metadata/README inspection boundary. Proceed only if the user's normal dependency policy permits it.
- suspicious — mention the findings and recommendations; install only with user consent.
- dangerous or unknown — do not install silently. Report the findings (rule, message, recommendation) and ask the user whether to continue.
- After installing a package the user picked, you may record it:
npm-safe watch add <name>if they want ongoing monitoring.
For a project-wide safety gate (e.g. before committing a lockfile change), run npm-safe ci --lockfile and act on the exit code (0 = pass, 2 = dependency reached the fail threshold).
When the user runs the install themselves (or the gate is enabled), they can use npm-safe install <pkg...> — it checks every package and asks for manual confirmation when a package scores below the threshold (default 85, configurable via npm-safe gate set-threshold).
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 · 210 lines · 128 tokens per session scan A 3f3e836dd3b8
npm-safe-scan is a skill published in the GitHub repository nisconder/npm-safe (5 stars, last pushed 7d ago), licensed Apache-2.0. It adds 128 tokens to every session and 2,679 once invoked, about $0.0006 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
edgeone skill scanner
A local static scanner that checks agent-skill files for security risks before they are installed or used. Static analysis examines files without running them.
datamol
Pythonic wrapper around RDKit with simplified interface and sensible defaults. Preferred for standard drug discovery including SMILES parsing, standardization, descriptors, fingerprints, clustering, 3D conformers, parallel processing. Returns native rdkit.Chem.Mol objects. For advanced control or custom parameters…
clinicaltrials-database
Query ClinicalTrials.gov via API v2. Search trials by condition, drug, location, status, or phase. Retrieve trial details by NCT ID, export data, for clinical research and patient matching.
esm
Comprehensive toolkit for protein language models including ESM3 (generative multimodal protein design across sequence, structure, and function) and ESM C (efficient protein embeddings and representations). Use this skill when working with protein sequences, structures, or function prediction; designing novel…
pysam
Genomic file toolkit. Read/write SAM/BAM/CRAM alignments, VCF/BCF variants, FASTA/FASTQ sequences, extract regions, calculate coverage, for NGS data processing pipelines.
openalex-database
Query and analyze scholarly literature using the OpenAlex database. This skill should be used when searching for academic papers, analyzing research trends, finding works by authors or institutions, tracking citations, discovering open access publications, or conducting bibliometric analysis across 240M+ scholarly…