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 Mathews-Tom/armory --skill dependency-auditgit clone --depth 1 https://github.com/Mathews-Tom/armoryWrote 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/mathews-tom/armory/dependency-audit)<a href="https://agentmods.dev/skills/mathews-tom/armory/dependency-audit"><img src="https://agentmods.dev/badge/skills/mathews-tom/armory/dependency-audit/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/mathews-tom/armory/dependency-audit"><img src="https://agentmods.dev/badge/skills/mathews-tom/armory/dependency-audit.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 2 findings, up to medium
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 →
- medium Prompt Injection · line 185 Large whitespace padding was detected (a block of blank lines or a long run of spaces). This can push injected instructions below or to the right of the visible area so a human reviewer never sees them while the agent still reads them. Manual review of the hidden content is recommended.Fix: Remove the large whitespace padding (blank-line blocks or long space runs) and review any content hidden below or to the right of it. Keep skill files compact and reviewable so no instructions can be
- medium Excessive Agency · line 214 Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
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 | $0.00066 | $0.02339 |
| Opus 5.5 | $0.00026 | $0.00936 |
| Sonnet 5.5 | $0.00013 | $0.00468 |
| Haiku 4.5 | $0.00007 | $0.00234 |
Grade A, and why
dependency-audit 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.
How it starts
The opening of the file, as written. The whole thing — 228 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Dependency Audit
Comprehensive dependency risk assessment: license compatibility analysis, maintenance health scoring, CVE detection, bloat identification, and transitive dependency risk mapping. Produces an actionable report with prioritized remediation steps organized by urgency (security → license → maintenance → bloat).
Reference Files
| File | Contents | Load When |
|---|---|---|
references/license-compatibility.md |
License compatibility matrix, copyleft detection, commercial-safe licenses | Always |
references/health-metrics.md |
Maintenance health indicators, scoring criteria, abandonment detection | Always |
references/bloat-detection.md |
Identifying unused deps, duplicate functionality, heavy transitive trees | Bloat analysis requested |
references/cve-sources.md |
CVE databases, advisory sources, vulnerability severity interpretation | Security audit requested |
Prerequisites
- Access to the project's dependency files (
pyproject.toml,requirements.txt,package.json,Cargo.toml,go.mod) - Lock file (for exact versions and transitive dependencies)
- Project license (to determine compatibility requirements)
Workflow
Phase 1: Parse Dependency Tree
- Direct dependencies — Packages explicitly declared in the project.
- Transitive dependencies — Dependencies of dependencies. Often 10-50x the direct count.
- Version constraints — Pinned (
==1.2.3), ranged (>=1.0,<2.0), or floating (*). - Development vs production — Separate dev/test dependencies from production.
Tools:
- Python:
uv pip list,pip-audit,pipdeptree - Node.js:
npm list --all,npm audit - Rust:
cargo tree,cargo audit
What ships with it
5 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.
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 · 228 lines · 66 tokens per session scan A ac4756e3ef6c
dependency-audit is a skill published in the GitHub repository Mathews-Tom/armory (337 stars, last pushed yesterday), licensed MIT. It adds 66 tokens to every session and 2,339 once invoked, about $0.0003 per session on Opus 5.5. 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 2026-08-30.
Other skills, from other repositories
counterparty-guard
A Russian business-counterparty check based on an identification number called an INN. It gathers public records about a company or sole proprietor and presents deal-risk signals.
contract-review
A contract-checking tool for Russian law, aimed at small businesses without an in-house lawyer. It reviews supply, service, contractor, NDA, and SaaS agreements and explains risky or missing terms in plain language.
tax-calendar-proactive
A proactive tax calendar for Russian individual entrepreneurs and small limited companies. From a few business details, it identifies upcoming deadlines, estimated payments, and important thresholds such as VAT and the simplified-tax-system limit.
review-contract
A Russian-law contract review guide that explains agreements in plain language, identifies red flags, and prepares marked-up DOCX or PDF revisions. It uses the Russian Civil Code as its legal basis.
tax-prep
A tax-period preparation workflow for Russia’s simplified tax system (УСН), including selected calculations and a package for an accountant.
crisis-holding
Draft crisis holding statements, journalist Q&A posture, and what-not-to-say guidance from confirmed incident facts, with a hard legal-counsel gate. Builds each statement through proven crisis-comms frameworks (holding-statement anatomy, SCCT, CAP order, the legitimate non-answer, bridge/flag/block).