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 orlando-japan/claude-code-setting --skill dependency-reviewgit clone --depth 1 https://github.com/orlando-japan/claude-code-settingWrote 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/orlando-japan/claude-code-setting/dependency-review)<a href="https://agentmods.dev/skills/orlando-japan/claude-code-setting/dependency-review"><img src="https://agentmods.dev/badge/skills/orlando-japan/claude-code-setting/dependency-review/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/orlando-japan/claude-code-setting/dependency-review"><img src="https://agentmods.dev/badge/skills/orlando-japan/claude-code-setting/dependency-review.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 | $0.00037 | $0.00880 |
| Opus 5 | $0.00018 | $0.00440 |
| Sonnet 5 | $0.00007 | $0.00176 |
| Haiku 4.5 | $0.00004 | $0.00088 |
Grade A, and why
dependency-review 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 9d 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 — 94 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Dependency review
The cheapest line of code is the one you don't add. The cheapest dependency is the one you don't pull.
First, question whether you need it
Before evaluating a package, ask:
- Can I write this in <50 lines? Date formatting, debouncing, UUID generation, slugify — usually yes.
- Is this already available in the stdlib? Every language has surprising breadth in its standard library.
- Is there already a similar dep in this project? Don't add a second date library.
- Is this the transitive problem of another dep? Check before adding.
If yes to any: don't add.
If you must add, check these seven things
1. Maintenance
- Last commit: <6 months is healthy, >2 years is suspicious.
- Open issues: triaged? Responded to? Or are maintainers gone?
- Release cadence: predictable or "one release 3 years ago"?
- Bus factor: solo maintainer with 20 other projects = fragile.
2. Popularity
- Weekly downloads: sanity check, not approval. Low downloads + specific-niche = fine. Low downloads + generic utility = concerning (why is nobody using it?).
- GitHub stars: weak signal, but a drop-off from a formerly popular package is a red flag.
3. License
- Permissive (MIT, BSD, Apache 2) → generally fine.
- Copyleft (GPL, AGPL) → check with legal. AGPL on server code is the big one.
- Unlicensed / "public domain" without SPDX → treat as "do not use."
- Custom licenses → read the license. No exceptions.
4. Security history
- CVE database search on the package name.
npm audit/pip-audit/cargo auditon the transitive tree.- Track record: one CVE is normal; repeated RCEs or auth bypasses = pattern.
- Does the maintainer respond to security reports?
5. Transitive weight
npm list <pkg>/ equivalent to see what it pulls in.- 5 transitive deps is fine. 500 is supply chain attack surface.
- Any of the transitives look sketchy? The risk compounds.
6. Install scripts
postinstallscripts are the most common supply-chain attack vector.- Check
package.jsonscripts.postinstallandscripts.preinstallfor this package and its transitive tree. - If you can't audit the install script, don't install.
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.
- 9d ago First seen · 94 lines · 37 tokens per session scan A ce61fb3bee94
dependency-review is a skill published in the GitHub repository orlando-japan/claude-code-setting (2 stars, last pushed 3mo ago), licensed MIT. It adds 37 tokens to every session and 880 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
supply-chain-security-expert
Secure the path from dependency to deployed artefact: SBOMs, dependency scanning, build provenance, artefact signing and CI/CD integrity. Use when the user mentions supply chain security, SBOM, CycloneDX or SPDX, SCA or dependency scanning, Sigstore or cosign, SLSA, provenance and attestation, a compromised or…
apply-contagion-risk-mapping
Use when assessing organizational risk exposure — to map how cascade failures propagate through implicit network proximity, shared infrastructure, and correlated dependencies, because organizations that assess only direct relationships systematically underestimate their exposure to others' failures.
dependency-scanning
Analyzes project dependencies for known vulnerabilities, license risks, and supply chain integrity. Auto-invoked when package manifests (package.json, requirements.txt, go.mod, pom.xml, Cargo.toml) are shared or when discussing dependency security. Produces an SBOM assessment with CVE findings triaged by EPSS and CISA…
dependency-lifecycle
Define a dependency lifecycle policy — patch/minor/major upgrade cadence, SBOM refresh, CVE triage, EOL tracking, automated PRs, lockfile hygiene, and supply-chain pinning.
vulnerability-scanner
A security scanner that checks software dependencies for known vulnerabilities, analyzes whether they can be reached, creates a software bill of materials, and audits licenses.
sbom-syft
Software Bill of Materials (SBOM) generation using Syft for container images, filesystems, and archives. Detects packages across 28+ ecosystems with multi-format output support (CycloneDX, SPDX, syft-json). Enables vulnerability assessment, license compliance, and supply chain security. Use when: (1) Generating SBOMs…